WO2025233002A1

WO2025233002A1 - Increasing efficiency of signaling in networks

Info

Publication number: WO2025233002A1
Application number: PCT/EP2025/053960
Authority: WO
Inventors: John Harris; Abolfazl AMIRI
Original assignee: Nokia Technologies Oy
Current assignee: Nokia Technologies Oy
Priority date: 2024-05-10
Filing date: 2025-02-14
Publication date: 2025-11-13
Anticipated expiration: 2026-11-10

Abstract

Examples of the disclosure relate to increasing efficiency of signaling in networks using using artificial intelligence/machine learning (AI/ML) models to generate network traffic predictions. In examples of the disclosure a User Equipment (UE) receives, from a network node, configuration information relating to a network traffic prediction. The configuration information indicates criteria for skipping a measurement gap. The UE determines buffer occupancy pattern information and determines based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met and controls skipping of the measurement gap in accordance with the indicated criteria.

Description

TITLE

Increasing Efficiency of Signaling in Networks

TECHNOLOGICAL FIELD

Examples of the disclosure relate to increasing efficiency of signaling in networks using network traffic predictions. Some relate to increasing efficiency of signaling in networks using artificial intelligence/machine learning (AI/ML) models to generate network traffic predictions.

BACKGROUND

In cellular telecommunications systems, the network generally controls operations such as allocation of resources. In order to efficiently allocate resources the network requires information relating to expected network traffic. Models such as AI/ML models can be used to predict network traffic and enable the network to make decisions relating to operations such as the allocation of resources.

BRIEF SUMMARY

According to various, but not necessarily all, examples of the disclosure there is provide a User Equipment (UE) comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the UE to perform at least: receiving from a network node configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining buffer occupancy pattern information; determining based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling skipping of the measurement gap in accordance with the indicated criteria.

The criteria indicated in the configuration may comprise one or more of: a confidence threshold in a predicted data pattern; one or more frequency ranges; one or more types of measurement; prohibit timer. The criteria indicated in the configuration may comprise starting requirements for the prohibit timer.

The processor and memory may be arranged to cause the UE to perform sending the buffer occupancy pattern information to the network node.

The processor and memory may be arranged to cause the UE to perform sending to the network node an indicator configured to map a UE state to a network traffic prediction for the UE

The processor and memory may be arranged to cause the UE to perform determining whether an indicated criteria from the configuration information is met if it has detected that a measurement gap is approaching.

According to various, but not necessarily all, examples of the disclosure there is provide a method comprising: receiving from a network node configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining buffer occupancy pattern information; determining based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling skipping of the measurement gap in accordance with the indicated criteria.

According to various, but not necessarily all, examples of the disclosure there is provide a computer program comprising instructions which, when executed by a UE, cause the UE to perform at least: receiving from a network node configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining buffer occupancy pattern information; determining based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling skipping of the measurement gap in accordance with the indicated criteria. According to various, but not necessarily all, examples of the disclosure there is provide a network node comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the network node to perform at least: transmitting to a User Equipment (UE) configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap.

The processor and memory may be arranged to cause the network node to perform receiving the buffer occupancy pattern information from the UE.

The processor and memory may be arranged to cause the network node to perform using the received buffer occupancy pattern information to update a model for predicting network traffic.

The processor and memory may be arranged to cause the network node to perform receiving an indication from the UE that a measurement gap is being skipped.

The processor and memory may be arranged to cause the network node to perform reallocating resources in response to the measurement gap being skipped.

The processor and memory may be arranged to cause the network node to perform receiving from the UE an indicator configured to map a UE state to a network traffic prediction for the UE.

According to various, but not necessarily all, examples of the disclosure there is provide a method comprising: transmitting to a User Equipment (UE) configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap- According to various, but not necessarily all, examples of the disclosure there is provide a computer program comprising instructions which, when executed by a network node, cause the network node to perform at least: transmitting to a User Equipment (UE) configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap.

According to various, but not necessarily all, embodiments there is provided an apparatus comprising at least one processor; and at least one memory including computer program code; the at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to perform at least a part of one or more methods described herein.

According to various, but not necessarily all, embodiments there is provided an apparatus comprising means for performing at least part of one or more methods described herein. The description of a function and/or action should additionally be considered to also disclose any means suitable for performing that function and/or action. Functions and/or actions described herein can be performed in any suitable way using any suitable method.

According to various, but not necessarily all, embodiments there is provided examples as claimed in the appended claims.

While the above examples of the disclosure and optional features are described separately, it is to be understood that their provision in all possible combinations and permutations is contained within the disclosure. It is to be understood that various examples of the disclosure can comprise any or all the features described in respect of other examples of the disclosure, and vice versa. Also, it is to be appreciated that any one or more or all the features, in any combination, may be implemented by/comprised in/performable by an apparatus, a method, and/or computer program instructions as desired, and as appropriate. The description of a function should additionally be considered to also disclose any means suitable for performing that function BRIEF DESCRIPTION

Some examples will now be described with reference to the accompanying drawings in which:

FIG. 1 shows an example network;

FIG. 2 shows an example method;

FIGS. 3A and 3B show example methods;

FIG. 4 shows an example signal flow;

FIGS. 5A and 5B show example methods;

FIG. 6 shows an example signal flow;

FIGS. 7A and 7B show example methods;

FIG. 8 shows an example signal flow;

FIGS. 9A and 9B show example methods;

FIG. 10 shows an example signal flow; and

FIG. 11 shows an example controller.

The figures are not necessarily to scale. Certain features and views of the figures can be shown schematically or exaggerated in scale in the interest of clarity and conciseness. For example, the dimensions of some elements in the figures can be exaggerated relative to other elements to aid explication. Similar reference numerals are used in the figures to designate similar features. For clarity, all reference numerals are not necessarily displayed in all figures.

DEFINITIONS

Al Artificial Intelligence

BSR Buffer Status Report

CG Configured Grant

DL Downlink

DRX Discontinuous Reception

E-UTRA Evolved UMTS Terrestrial Radio Access gNB Base Station

MG Measurement Gap

ML Machine Learning

O-RAN Open-Radio Access Network

PDCCH Physical Downlink Control Channel PUSCH Physical Uplink Shared Channel

RAN Radio Access Network

RRC Radio Resource Control

SR Status Report

UE User Equipment

UL Uplink

UMTS Universal Mobile Telecommunications System

DETAILED DESCRIPTION

Fig. 1 illustrates an example of a communications network 100. The network 100 comprises a plurality of different types of nodes 110, 120, 130. The different types of nodes can comprise terminal nodes 110, network nodes 120 and core network nodes 130 and/or any other suitable type of nodes.

The network 100 is in this example a radio telecommunications network, in which at least some of the terminal nodes 110 and network nodes 120 communicate with each other using transmission/reception of radio waves.

The network nodes 120 can be configured to communicate with the terminal nodes 110. The one or more core network nodes 130 communicate with the network nodes 120. In some examples the one or more core network nodes 130 communicate with the terminal nodes 110.

The one or more core network nodes 130 can, in some examples, communicate with each other. The one or more network nodes 120 can, in some examples, communicate with each other.

The network 100 can be a cellular network comprising a plurality of cells 122. Each of the cells is served by a network node 120. The network node 120 can provide an access node. In this example, the interface between the terminal nodes 110 and a network node 120 defining a cell 122 is a wireless interface 124. The network node 120 comprises one or more cellular radio transceivers. The terminal node 110 comprises one or more cellular radio transceivers.

In the example illustrated the cellular network 100 is a third generation Partnership Project (3GPP) standard compliant network in which the terminal nodes 110 are user equipment (UE) and the network nodes 120 can be access nodes such as base stations (gNB). The UE can comprise a mobile equipment.

A network node 120 can be a network entity responsible for radio transmission and reception in one or more cells to or from the UE 110. A network node 120 can be a network element in a Radio Access Network (RAN), an Open-Radio Access Network (O-RAN), a E- UTRA (Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access) network, or any other suitable type of network.

The core network nodes 130 can be part of a core network. The core network nodes 130 can be configured to manage functions relating to connectivity for the UEs 110. For example, the core network nodes 130 can be configured to manage functions such as connectivity, mobility, authentication, authorization and/or other suitable functions.

In the example of Fig. 1 the core network node 130 is shown as a single entity. In some examples the core network node 130 could be distributed across a plurality of entities. For example, the core network node 130 could be cloud based or distributed in any other suitable manner.

In some examples the network 100 can be a Fifth Generation (or New Radio, NR) Radio Access network (NG-RAN). The NG-RAN consists of gNodeBs (gNBs) 120, providing the user plane and control plane (RRC) protocol terminations towards the UE 110. The gNBs 120 are interconnected with each other by means of an X2/Xn interface 126. The gNBs are also connected by means of the NG interface 128 to core network nodes 130 such as the Access and Mobility management Function (AMF).

In some examples the network 100 can be an Evolved Universal Terrestrial Radio Access network (E-UTRAN). The E-UTRAN consists of E-UTRAN NodeBs (eNBs) 120, providing the E-UTRA user plane and control plane (RRC) protocol terminations towards the UE 110. The eNBs 120 can be interconnected with each other by means of an X2 interface 126. The eNBs can also be connected by means of the S1 interface to the Mobility Management Entity (MME).

Other types of networks can be used in other examples.

In order to efficiently allocate resources the network requires information relating to expected network traffic. The performance of the network 100 can be improved if the network node 120 can anticipate when and how much uplink UL traffic will be generated by a UE 110 and when downlink (DL) traffic will arrive for delivery to the UE 110 and/or any other suitable information.

However, if the network node 120 does not anticipate the network traffic correctly this can result in delays and additional resource costs. For example, proactive UL grant transmission consumes Physical Uplink Shared Channel (PUSCH) resources and Physical Downlink Control Channel (PDCCH) resources. If a prediction of network traffic is not accurate then more of these resources would be used than if the prediction was accurate. Also additional PDCCH monitoring occasions results in the UE 110 having an increased Discontinuous Reception (DRX) active time which will drain the UE 110 battery.

Models such as artificial intelligence/machine learning (AI/ML) can be used by the UE 110 and/or the network node 120 to provide accurate network traffic predictions. For example an AI/ML model can be used to estimate the future occupancy of the UE 110 buffer. An AI/ML model implemented by a UE 110 might have advantages in estimating future occupancy of the UE 110 buffer compared to an AI/ML model implemented by a network node 120 because the UE 110 can have more information of the service requirements at the UE 110. For example, the traffic patterns for a UE 110 using an application will be dependent upon the actions or options that are used within the application. The UE 110 has information about how an application is being used at the UE 110 but the network node 120 does not.

Examples of the disclosure provide methods of increasing efficiency in signaling between a UE 110 and gNB 120 where the UE 110 is configured to use a model such as an AI/ML model to make network traffic predictions. Examples of the disclosure can enable the UE 110 to autonomously perform actions such as cancelling one or more procedures that are not needed. This can save resources that can then be allocated or reallocated by the gNB 120.

The procedures that can be cancelled, or otherwise controlled by the UE 110, can comprise sending a Buffer Status Report (BSR) or a Scheduling Request (SR), a Measurement Gap (MG), monitoring PDCCH, using a Configured Grant (CG) occasion, or any other suitable procedures.

Fig. 2 shows an example method that can be used in examples of the disclosure. The example method of Fig. 2 could be implemented by a network node 120 such as a gNB 120 or any other suitable network entity.

The method comprises, at block 200, configuring a UE 110 to use a model to predict network traffic. The model can comprise an AI/ML model or any other suitable type of model.

At block 202 the method comprises transmitting to the UE 110 configuration information relating to a network traffic prediction obtained using the model. The configuration information indicates criteria for performing an action. The configuration information can provide a policy that the UE 110 can implement to determine whether or not an action should be performed. The configuration information can be used by the UE 110 to autonomously decide whether or not to perform an action without requiring additional signaling from the gNB 120.

The configuration information can comprise any information that enables the UE 110 to autonomously determine whether to perform an action. The configuration information comprises criteria and the UE 110 can determine whether or not the criteria are met. Based on whether the criteria are met, the UE 110 can make a decision relating to an action indicated in the configuration. The criteria that are used in the configuration information can be specific to the action. In some examples the criteria in the configuration information can comprise any one or more of: an amount of network traffic predicted by the UE 110 and gNB models during an upcoming interval being greater than a threshold, an amount of network traffic predicted by the UE and network node models during an upcoming interval model being less than a threshold, a confidence threshold in a predicted data pattern, a logical channel group (LOG) to which the criteria apply, a logical channel (LOH) to which the criteria apply, a prohibit timer, a buffer occupancy matching the traffic pattern for an interval within some threshold, or any other suitable criteria.

The action that is to be performed by the UE 110 can comprise cancelling one or more procedures that are not needed. The procedures that are not needed can comprise sending a BSR or SR, an MG, monitoring PDCCH, using a CG occasion, or any other suitable procedures.

Other actions could be used in some examples. For instance, in some cases the action could comprise sending a BSR even if the buffer is empty or there has been no change in the status of the buffer. Such messaging can be used to monitor if the model is still providing sufficient accuracy for the gNB 120.

The gNB 120 knows which actions are to be performed by the UE 110. The gNB 120 configured the UE 110 with the model used for making predictions and also has access to information that is used by the UE 110 as input data for the model. The gNB 120 is therefore aware of the predictions that are made by the model at the UE 110. This enables coordination of the actions by the UE 110 and the gNB 120 while reducing the need for coordinating signaling. The actions that can be performed by the UE 110 have corresponding actions for the gNB 120. For example, the actions that could be performed by the gNB 120 could comprise cancelling a BSR, receiving an SR, receiving a BSR or SR, skipping an MG, skipping transmission of PDCCH, or cancelling of one or more CG occasions. The cancelled CG occasion could be receiving on a UL CG or transmitting on a DL UL.

At block 204 the method comprises determining if the action has been performed based on the network traffic predictions.

At block 206 the method comprises allocating resources based, at least in part, on whether the action has been performed. As an example, if a BSR or SR (or other procedure) has been cancelled by the UE 110 then the gNB 120 can allocate resources that would have been used for the BSR or SR (or other procedure) for other purposes. As another example, if an MG has been skipped then the allocation of resources can allow the gNB 120 to transmit to a different UE 110. If a CG occasion has been cancelled then resources that were allocated for the CG can be allocated to another UE 110. The allocating of the resources at block 206 can comprise changing a resource plan. For example, an initial plan could be that the UE 110 is to use a given channel x at time t to transmit or receive. After it has been determined that the action has been performed, the gNB 120 can then change the resource plan so that the UE 110 is not to use the given channel x at time t to transmit or receive. This can enable the channel x at time t to be reallocated to a different UE 110. Similarly, if the initial resource plan is that the UE 110 is not to use a given channel x at time t then this could be changed so that the UE 110 does use channel x at time t.

In some examples, the method can comprise additional blocks that are not shown in Fig. 2. In some examples the method can comprise receiving from the UE 110 a data pattern relating to network traffic that has been obtained by the UE 110. The data pattern could comprise buffer occupancy pattern information, DL data pattern information and/or any other suitable data pattern.

The gNB 120 can be configured to use the received data pattern to update the model that is used for predicting network traffic. This can be a local model that is used by the gNB 120 to predict the network traffic for the UE 110. The updating of the model can improve the accuracy of the model, for example, by taking into account status changes at the UE 110.

Figs. 3A and 3B show example methods that can be implemented in examples of the disclosure. The method of Fig. 3A could be implemented by a UE 110 and the method of Fig. 3B could be implemented by a corresponding gNB 120.

The method comprises, at block 300, receiving from the gNB 120 configuration information relating to a network traffic prediction. The configuration information indicates criteria for cancelling a BSR or SR.

The criteria that are indicated in the configuration information can comprise information relating to an action that is to be performed by the UE 110. In this example the criteria that are indicated in the configuration information can comprise criteria relating to the BSR or SR. In some examples the criteria can comprise one or more of: a confidence threshold in a predicted data pattern, an LCG to which the criteria apply, an LCH to which the criteria apply, a prohibit timer, whether a buffer occupancy matches the traffic pattern for an interval within a threshold, or any other suitable criteria. Where the criteria comprises a prohibit timer the criteria can also comprise an indication of the starting requirements for the timer. The starting requirements for the timer could comprise the sending of a data patter such a buffer occupancy pattern information or any other suitable requirements.

At block 302 the method comprises determining buffer occupancy pattern information. The buffer occupancy pattern information, and/or any other suitable data patterns, can be sent to the gNB 120.

At block 304 the method comprises determining, based at least in part on the buffer occupancy pattern information, whether an indicated criteria from the configuration information is met. The determining of whether an indicated criteria from the configuration information is met can be performed if the UE 110 has detected a trigger condition for scheduling a BSR or SR. That is, the determining if the criteria has been met can occur in response to detecting that BSR or SR is to be triggered. If it is not determined that a BSR or SR is to be triggered then the criteria do not need to be checked.

At block 306 the method comprises controlling cancelling a BSR or SR in accordance with the indicated criteria. In some examples the controlling of the cancelling can comprise cancelling the BSR or the SR. This can enable efficient use of network resources and save power at the UE 110.

In some examples the controlling of the cancelling of the BSR or SR can comprise not cancelling the BSR or SR. This can enable information that might be useful to the gNB 120 to be provided to the gNB 120. For example, it could be used by the gNB 120 to determine if the model used to predict the data pattern is still accurate.

The method of Fig. 3B corresponds to the method of Fig. 3A. The method of Fig. 3B comprises, at block 310, transmitting to the UE 110 configuration information relating to a network traffic prediction, the configuration information indicating criteria for cancelling a BSR or SR. The configuration information that is transmitted by the gNB 120 at block 310 can be received by the UE 110 at block 300.

The method that is performed by the gNB 120 can also comprise additional blocks that are not shown in Fig. 3B. For example, if the UE 110 transmits buffer occupancy pattern information, then this can be received the gNB 120. The gNB 120 can then use the received buffer occupancy pattern information for any suitable purpose. In some examples, the buffer occupancy pattern information can be used to update a model that is used for predicting network traffic. This can be a local model that is used by the gNB 120 to predict network traffic for the UE 110 and/or the model used by the UE 110.

If the BSR or SR is cancelled then the gNB 120 can reallocate resources that would have otherwise been used for the BSR or SR. In some examples the gNB 120 can receive an indication from the UE 110 that a BSR or SR has been cancelled. The gNB 120 could then perform the reallocation of the resources in response to the indication.

In examples of the disclosure, the gNB 120 can configure the UE 110 with the model. The gNB 120 can also configure the UE 110 to send an indicator of a network traffic prediction to the gNB 120. The indicator can map a UE state to a network traffic prediction of the UE 110. When the gNB 120 receives an indicator it can determine the network traffic prediction for the UE 110 from the indicator. This can be an efficient method for exchanging information relating to a network traffic prediction.

The state of the UE 110 can comprise the state of the model for predicting network traffic. The model can be configured to observe traffic patterns, and possibly other software state inputs, and can use these to correlate the software state inputs (if any) and prior/current traffic with an upcoming traffic pattern.

In some examples, the UE state is a state triggered by a change in state of an operating system of the UE 110 or a change in state of an application running on the UE 110. In some examples, the UE state can be triggered by an action of a user of the UE 110.

The indicator that is transferred from the UE 110 to the gNB 120 enables the gNB 120 to determine a network traffic prediction for the UE 110. This prediction can be used by the network to anticipate, control, or configure UE 110 and/or network resources (such as grants/allocation(s)) for network traffic. In some examples, the network traffic is a sequence of traffic for the UE 110. In some examples, the network traffic is or comprises DL data traffic from the gNB 120 to the user equipment 110. In some examples, the network traffic is or comprises UL data traffic from the UE 110 to the gNB 120 and DL data traffic from the gNB 120 to the UE 110. Fig. 4 shows an example signal flow that can be used to implement examples of the disclosure. In this example the UE 110 is configured to autonomously determine whether to cancel a BSR/SR. This provides for efficient signaling and use of network resources.

At block 400 the gNB 120 configures the UE 110 to send data pattern information such as an anticipated buffer occupancy report. The anticipated buffer occupancy report can be generated using a model such as an AI/ML model or any other suitable type of model. The gNB 120 can configure the UE 110 with the model. The gNB 120 can configure the UE 110 with indicators that map a state of the model to a predicted network traffic or buffer occupancy. The gNB 120 can configure the UE 110 to send the anticipated buffer occupancy report at regular intervals or in response to a defined trigger event such as a change in a traffic pattern state. The traffic pattern state can comprise the state of the model. For example, the traffic pattern state can comprise an output of the AI/ML model.

The anticipated buffer occupancy report can enable the UE 110 and the gNB 120 to predict future network traffic. The anticipated buffer occupancy report can enable the UE 110 and the gNB 120 to predict future network traffic for a given time interval T. The time interval T can be the time period for which the outputs of the model have a confidence level greater than, or equal to, a given confidence level C.

The configuration at block 400 configures the UE 110 to send an anticipated buffer occupancy report in response to a trigger condition. The trigger condition could be the expiry of a time period or that the confidence level of the model has fallen below a given confidence level, or could be any other suitable trigger event.

The anticipated buffer occupancy report can enable the UE 110 and the gNB 120 to predict future network with a defined confidence level. The anticipated buffer occupancy report can comprise one or more indicators that indicate a UE state.

At block 402 the gNB 120 sends configuration information to the UE 110. The configuration information indicates criteria that can be used by the UE 110 to decide whether to cancel a BSR or SR. The criteria can relate to the predicted network traffic that is generated by the model. For example, the UE 110 can determine if an output of the model satisfies one or more of the criteria when it is deciding whether to cancel a BSR or SR. The criteria that are indicated in the configuration information provides a policy that can be used by the UE 110 when determining whether or not to cancel the BSR or SR. The policy can comprise a set of rules or conditions that can be implemented by the UE 110.

The criteria comprised within the configuration information can be determined by the actions that are controlled by the configuration information. In this example the configuration information controls whether a BSR or SR is cancelled. In this example the criteria can comprise a confidence threshold in a predicted data pattern (for example a predicted buffer occupancy or network traffic prediction), an indication of LCG or LCHs for which the criteria apply, a probit timer, and/or any other suitable criteria. The prohibit timer can indicate a time period for which the UE 110 is prohibited from transmitting an SR/BSR. For instance, for a given time period after an SR/BSR has been transmitted the confidence level of the model can be high so that no further SR/BSR is needed until the confidence level has dropped below the threshold. The prohibit timer can be configured to start after the UE 110 sends buffer occupancy pattern information and/or any other suitable event.

In the example of Fig. 4 blocks 400 and 402 are shown as separate blocks. In examples of the disclosure they can be performed together.

The signal used for blocks 400 and 402 can comprise semi-static signaling such as RRC signaling.

At block 404 the gNB 120 sends a BSR/SR configuration to the UE 110. The BSR/SR configuration configures the UE 110 with rules for triggering SR/BSR. The rules can be defined per LCG. The configuring can comprise UL resource allocation for reporting SR/BSR.

In the signal flow of Fig. 4 the configuring of the UE 110 with rules for triggering SR/BSR is shown as occurring after blocks 400 and 402. These blocks could be performed at the same time or in any suitable order.

At block 406 the UE 110 can transmit buffer occupancy pattern information to the gNB 120. The buffer occupancy pattern information can be generated by a model or by any other suitable means. Other types of data pattern could be used in other examples. The transmission of the buffer occupancy pattern information can be in accordance with the configuration of bock 400. The transmission of the buffer occupancy pattern information can be triggered by a timer, by a change in traffic pattern state of the UE 110, and/or by any other suitable event. The buffer occupancy pattern information can be indicated using an indicator that maps a UE state to a network traffic prediction of the UE 110.

Any suitable signaling can be used to transmit buffer occupancy pattern information to the gNB 120. The signaling can comprise semi-static signaling such as Radio Resource Control (RRC) messages or any other suitable signaling.

At block 408 the gNB 120 uses the received buffer occupancy pattern information to update the local model at the gNB 120. The local model is used by the gNB 120 to predict network traffic for the UE 110 or to predict any other suitable data patterns. The updating of the model using the received buffer occupancy pattern information can enhance the accuracy of the model. The updating of the model can increase the confidence level of outputs of the model.

If the model is updated then the gNB 120 can reconfigure the SR/BSR configuration of the UE 110. The reconfiguration can provide a better fit for the traffic pattern. The updating can be achieved by sending another BSR/SR configuration as used at block 404 or by using any other suitable signaling.

At block 410 the UE 110 determines that a BSR or SR is triggered. The triggering of the BSR/SR can be in accordance with the configuration of block 400. The SR/BSR can triggered due to a specified condition such as a timer or a change in state of the UE 110.

After the BSR or SR is triggered the UE 110, at block 412, checks the configuration information that is received at block 402. The UE 110 uses the criteria from the configuration information to decide whether the BSR or SR that has been triggered should be cancelled.

The UE 110 can make the decision whether to cancel the BSR/SR before the buffer calculation procedure. This can save computation power at the UE 110. At block 414 the UE 110 determines that the appropriate criteria have been satisfied and cancels the BSR/SR that has been triggered. The UE 110 can cancel the SR/BSR autonomously without a specific indication from the gNB 120.

When the UE 110 cancels the SR/BSR this can free up resources for other purposes. The gNB 120 can be implicitly aware that the UE 110 has cancelled the BSR/SR and can allocate the resources that have been freed up for other purposes.

In some examples the gNB 120 can configure the UE 110 with rules that enable the UE 110 to send the SR/BSR in scenarios where the model predictions might fail or not be accurate enough to satisfy the configuration sent at block 400. In such cases, rather than cancelling the SR/BSR at block 414 the UE 110 can send the SR/BSR.

Figs. 5A and 5B show example methods that can be implemented in examples of the disclosure. The method of Fig. 5A could be implemented by a UE 110 and the method of Fig. 5B could be implemented by a corresponding gNB 120.

The method comprises, at block 500, receiving from the gNB 120 configuration information relating to a network traffic prediction. The configuration information indicates criteria for skipping an MG.

The criteria that are indicated in the configuration information can comprise information relating to an action that is to be performed by the UE 110. In this example the criteria that are indicated in the configuration information can comprise criteria relating to skipping an MG. In some examples the criteria can comprise one or more of: a confidence threshold in a predicted data pattern, one or more frequency ranges, one or more types of measurement, a prohibit timer, or any other suitable criteria. Where the criteria comprises a prohibit timer the criteria can also comprise an indication of the starting requirements for the timer. The starting requirements for the timer could comprise the sending of a data pattern such as buffer occupancy pattern information or any other suitable requirements.

At block 502 the method comprises determining buffer occupancy pattern information. The buffer occupancy pattern information, and/or any other suitable data patterns, can be sent to the gNB 120. At block 504 the method comprises determining, based at least in part on the buffer occupancy pattern information, whether an indicated criteria from the configuration information is met. The determining of whether an indicated criteria from the configuration information is met can be performed if the UE 110 has detected that an MG is approaching. For example, if an MG is within a given time period. Therefore the determining if the criteria has been met can occur in response to detecting that an MG is approaching. If it is not determined that an MG is approaching then the criteria do not need to be checked.

At block 506 the method comprises controlling skipping of an MG in accordance with the indicated criteria. Therefore, based on the criteria with which the UE 110 has been configured and the buffer occupancy pattern information the MG can be skipped or not skipped. For example, if an MG is not needed based on the predicted buffer occupancy pattern information the UE 110 can autonomously decide to skip it without specific instruction from the gNB 120. This can enable efficient use of network resources and save power at the UE 110.

In some examples the controlling of the skipping of the MG can comprise not skipping the MG. This can enable information that might be useful to be obtained. For example, the measurements could be used to determine if the model used to predict the data pattern is still accurate.

The method of Fig. 5B corresponds to the method of Fig. 5A. The method of Fig. 5B comprises, at block 510, transmitting to the UE 110 configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping an MG. The configuration information that is transmitted by the gNB 120 at block 510 can be received by the UE 110 at block 500.

The method that is performed by the gNB 120 can also comprise additional blocks that are not shown in Fig. 5B. For example, if the UE 110 transmits buffer occupancy pattern information, then this can be received the gNB 120. The gNB 120 can then use the received buffer occupancy pattern information for any suitable purpose. In some examples, the buffer occupancy pattern information can be used to update a model that is used for predicting network traffic. This can be a local model that is used by the gNB 120 to predict network traffic for the UE 110 and/or the model used by the UE 110. If the MG is skipped then the gNB 120 can reallocate resources that would have otherwise been used for the measurements. In some examples the gNB 120 can receive an indication from the UE 110 that an MG has been skipped. The gNB could then perform the reallocation of the resources in response to the indication.

In examples of the disclosure the gNB 120 can configure the UE 110 with the model. The gNB 120 can also configure the UE 110 to send an indicator of a network traffic prediction to the gNB 120. The indicator can map a UE state to a network traffic prediction of the UE 110. When the gNB 120 receives an indicator it can determine the network traffic prediction for the UE 110 from the indicator. This can be an efficient method for exchanging information relating to a network traffic prediction.

Fig. 6 shows an example signal flow that can be used to implement examples of the disclosure. In this example the UE 110 is configured to autonomously determine whether to skip an MG. This provides for efficient signaling and use of network resources.

At block 600 the gNB 120 configures the UE 110 to send data pattern information such as an anticipated buffer occupancy report. The anticipated buffer occupancy report can be generated using a model such as an AI/ML model or any other suitable type of model. The gNB 120 can configure the UE 110 with the model. The gNB 120 can configure the UE 110 with indicators that map a state of the model to a predicted network traffic or buffer occupancy. The gNB 120 can configure the UE 110 to send the anticipated buffer occupancy report at regular intervals or in response to a defined trigger event such as a change in a traffic pattern state. The traffic pattern state can comprise the state of the model. For example, the traffic pattern state can comprise an output of the AI/ML model.

The configuration at block 600 configures the UE 110 to send an anticipated buffer occupancy report in response to a trigger condition. The trigger condition could be the expiry of a time period or that the confidence level of the model has fallen below a given confidence level, or could be any other suitable trigger event.

At block 602 the gNB 120 sends configuration information to the UE 110. The configuration information indicates criteria that can be used by the UE 110 to decide whether to skip an MG. The criteria can relate to the predicted network traffic that is generated by the model. For example, the UE 110 can determine if an output of the model satisfies one or more of the criteria when it is deciding whether to skip an MG.

The criteria that are indicated in the configuration information provides a policy that can be used by the UE 110 when determining whether or not to skip the MG. The policy can comprise a set of rules or conditions that can be implemented by the UE 110.

The criteria comprised within the configuration information can be determined by the actions that are controlled by the configuration information. In this example the configuration information controls whether an MG is skipped. In this example the criteria can comprise one or more of: a confidence threshold in a predicted data pattern, one or more frequency ranges, one or more types of measurement, a prohibit timer, or any other suitable criteria. Where the criteria comprises a prohibit timer the criteria can also comprise an indication of the starting requirements for the timer. The starting requirements for the timer could comprise the sending of a data pattern such as buffer occupancy pattern information or any other suitable requirements.

In the example of Fig. 6 blocks 600 and 602 are shown as separate blocks. In examples of the disclosure they can be performed together.

The signal used for blocks 600 and 602 can comprise semi-static signaling such as RRC signaling.

At block 604 the gNB 120 sends an MG configuration to the UE 110. The MG configuration configures the UE 110 with rules for performing measurements and details about the gaps to be used for the measurements. The details about the gaps can comprise the periods, the types, or any other suitable information.

In the signal flow of Fig.6 the configuring of the UE 110 with measurement rules is shown as occurring after blocks 600 and 602. These blocks could be performed at the same time or in any suitable order.

At block 606 the UE 110 can transmit buffer occupancy pattern information to the gNB 120. The buffer occupancy pattern information can be generated by a model or by any other suitable means. Other types of data pattern could be used in other examples.

The transmission of the buffer occupancy pattern information can be in accordance with the configuration of bock 600. The transmission of the buffer occupancy pattern information can be triggered by a timer, by a change in traffic pattern state of the UE 110, and/or by any other suitable event. The buffer occupancy pattern information can be indicated using an indicator that maps a UE state to a network traffic prediction of the UE 110.

At block 608 the gNB 120 uses the received buffer occupancy pattern information to update the local model at the gNB 120. The local model is used by the gNB 120 to predict network traffic for the UE 110 or to predict any other suitable data patterns. The updating of the model using the received buffer occupancy pattern information can enhance the accuracy of the model. The updating of the model can increase the confidence level of outputs of the model.

If the model is updated then the gNB 120 can reconfigure the MG configuration of the UE 110. The reconfiguration can provide a better fit for the traffic pattern. The updating can be achieved by sending another MG configuration as used at block 604 or by using any other suitable signaling.

At block 610 the UE 110 determines that an MG is approaching. Timing of the MG can be in accordance with the configuration of block 600. After it has been determined that an MG is approaching the UE 110, at block 612, checks the configuration information that is received at block 602. The UE 110 uses the criteria from the configuration information to decide whether the MG that is approaching should be skipped.

The UE 110 can make the decision whether to skip the MG before the buffer calculation procedure. This can save computation power at the UE 110.

At block 614 the UE 110 determines that the appropriate criteria have been satisfied and skips the MG. The UE 110 can skip the MG autonomously without a specific indication from the gNB 120.

When the UE 110 skips the MG this can free up resources for other purposes. The gNB 120 can be implicitly aware that the UE 110 has skipped the MG and can allocate the resources that have been freed up for other purposes.

In some examples the gNB 120 can configure the UE 110 with rules that enable the UE 110 to perform the measurements rather than skip the MG. This can be useful in scenarios where the accuracy of the model predictions might not be high enough, for example if they are below a confidence threshold. In such cases, rather than skip the MG at block 614 the UE 110 can perform the measurements and the measurements can be used to check the accuracy of the model and make any appropriate adjustments.

Variations to the signal flow can be used in some examples. For instance, in the example of Fig. 6, at block 606 the UE 110 can transmit buffer occupancy pattern information to the gNB 120 and, at block 608, 608 the gNB 120 uses the received buffer occupancy pattern information to update the local model at the gNB 120.

In other examples instead of the UE 110 transmitting the buffer occupancy pattern information the gNB 120 can transmit DL data pattern information to the UE 110. The DL data pattern information can be generated by a model or by any other suitable means. In such examples the configuration of block 600 can configure the gNB to send the DL data pattern information. The transmission of the DL data pattern information can be triggered by a timer, by a change in traffic pattern state of the UE 110 or gNB 120, and/or by any other suitable event. The DL pattern information can be indicated using an indicator that maps a UE state or gNB state to a network traffic prediction.

Any suitable signaling can be used to transmit DL data pattern information to the UE 110. The signaling can comprise semi-static signaling such as Radio Resource Control (RRC) messages or any other suitable signaling.

Once the DL data pattern information has been sent to the UE 110. The UE 110 uses the received DL data pattern information to update the local model at the UE 110. The local model is used by the UE 110 to predict network traffic for the UE 110 or to predict any other suitable data patterns. This can be similar to block 608 but would be performed at the UE 110 rather than at the gNB 120.

Figs. 7A and 7B show example methods that can be implemented in examples of the disclosure. The method of Fig. 7A could be implemented by a UE 110 and the method of Fig. 7B could be implemented by a corresponding gNB 120.

The method comprises, at block 700, receiving from the gNB 120 configuration information relating to a network traffic prediction. The configuration information indicates criteria for skipping monitoring of a PDCCH.

The criteria that are indicated in the configuration information can comprise information relating to an action that is to be performed by the UE 110. In this example the criteria that are indicated in the configuration information can comprise criteria relating to skipping monitoring of a PDCCH. In some examples the criteria can comprise one or more of: a confidence threshold in a predicted data pattern, rules for skipping monitoring of PDCCH, a maximum time interval between skipping of the PDCCH monitoring, a prohibit timer, or any other suitable criteria. Where the criteria comprises a prohibit timer the criteria can also comprise an indication of the starting requirements for the timer. The starting requirements for the timer could comprise the receiving of a data pattern such as a DL data pattern information or any other suitable requirements.

At block 702 the method comprises receiving DL data pattern information from the gNB 120. At block 704 the method comprises, determining based at least in part on the received DL data pattern information, whether an indicated criteria from the configuration information is met. The determining of whether an indicated criteria from the configuration information is met can be performed if the UE 110 has detected that a PDCCH monitoring interval is approaching. For example, if a PDCCH monitoring interval is within a given time period. Therefore the determining if the criteria has been met can occur in response to detecting that a PDCCH monitoring interval is approaching. If it is not determined that a PDCCH monitoring interval is approaching then the criteria do not need to be checked.

At block 706 the method comprises controlling skipping monitoring of PDCCH in accordance with the indicated criteria. Therefore, based on the criteria with which the UE 110 has been configured and the buffer occupancy pattern information the monitoring of the PDCCH can be skipped or not skipped. For example, if monitoring of PDCCH is not needed based on the received DL data pattern information the UE 110 can autonomously decide to skip it without specific instruction from the gNB 120. This can enable efficient use of network resources and save power at the UE 110.

In some examples the controlling of the skipping monitoring of PDCCH can comprise not skipping the monitoring. This can enable information that might be useful to be obtained. For example, monitoring the PDCCH could be used to determine if the model used to predict the data pattern is still accurate.

The method that is performed by the UE 110 can also comprise additional blocks that are not shown in Fig. 7A. For instance, when the UE 110 receives the DL data pattern information this can be used for any suitable purpose. In some examples, the DL data pattern information can be used to update a model that is used for predicting network traffic.

The method of Fig. 7B corresponds to the method of Fig. 7A. The method of Fig. 7B comprises, at block 710, transmitting to the UE 110 configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping monitoring of a PDCCH. The configuration information that is transmitted by the gNB 120 at block 710 can be received by the UE 110 at block 700. The method that is performed by the gNB 120 can also comprise additional blocks that are not shown in Fig. 7B. For example, the gNB 120 transmits the DL data pattern to the UE 110.

If the monitoring of the PDCCH is skipped then the gNB 120 can reallocate resources that would have otherwise been used for monitoring the PDCCH. In some examples the gNB 120 can receive an indication from the UE 110 that the monitoring of the PDCCH is skipped. The gNB could then perform the reallocation of the resources in response to the indication.

Fig. 8 shows an example signal flow that can be used to implement examples of the disclosure. In this example the UE 110 is configured to autonomously determine whether to skip monitoring of a PDCCH. This provides for efficient signaling and use of network resources.

At block 800 the gNB 120 configures the UE 110 to receive data pattern information such as anticipated DL data pattern information. In some examples the gNB 120 can be configured to receive anticipated data pattern information such as UL data pattern information. The anticipated DL data pattern information (and/or the anticipated UL data pattern information) can be generated using a model such as an AI/ML model or any other suitable type of model. The gNB 120 can configure the UE 110 with the model. The gNB 120 can configure the UE 110 with indicators that map a state of the model to a predicted network traffic or buffer occupancy. The gNB 120 can configure the UE 110 to receive the anticipated DL data pattern information at regular intervals or in response to a defined trigger event such as a change in a traffic pattern state. The traffic pattern state can comprise the state of the model. For example, the traffic pattern state can comprise an output of the AI/ML model. The anticipated DL data pattern information can enable the UE 110 and the gNB 120 to predict future network traffic. The anticipated DL data pattern information can enable the UE 110 and the gNB 120 to predict future network traffic for a given time interval T. The time interval T can be the time period for which the outputs of the model have a confidence level greater than, or equal to, a given confidence level C.

The configuration at block 800 configures the UE 110 to receive an anticipated DL data pattern information in response to a trigger condition. The trigger condition could be the expiry of a time period or that the confidence level of the model has fallen below a given confidence level, or could be any other suitable trigger event.

The anticipated DL data pattern information can enable the UE 110 and the gNB 120 to predict future network with a defined confidence level. The anticipated DL data pattern information can comprise one or more indicators that indicate a UE state.

At block 802 the gNB 120 sends configuration information to the UE 110. The configuration information indicates criteria that can be used by the UE 110 to decide whether to skip monitoring of a PDCCH. The criteria can relate to the predicted network traffic that is generated by the model. For example, the UE 110 can determine if an output of the model satisfies one or more of the criteria when it is deciding whether to skip monitoring of a PDCCH.

The criteria that are indicated in the configuration information provides a policy that can be used by the UE 110 when determining whether or not to skip monitoring of a PDCCH. The policy can comprise a set of rules or conditions that can be implemented by the UE 110.

The criteria comprised within the configuration information can be determined by the actions that are controlled by the configuration information. In this example the configuration information controls whether monitoring of a PDCCH is skipped. In this example the criteria can comprise one or more of: a confidence threshold in a predicted data pattern, rules for skipping monitoring of PDCCH, a maximum time interval between skipping of the PDCCH monitoring, a prohibit timer, or any other suitable criteria. Where the criteria comprises a prohibit timer the criteria can also comprise an indication of the starting requirements for the timer. The starting requirements for the timer could comprise the receiving of a data pattern such as a DL data pattern information or any other suitable requirements. In the example of Fig. 8 blocks 800 and 802 are shown as separate blocks. In examples of the disclosure they can be performed together.

The signal used for blocks 800 and 802 can comprise semi-static signaling such as RRC signaling.

At block 804 the gNB 120 sends a DRX configuration to the UE 110. The DRX configuration configures the UE 110 with rules for PDCCH monitoring and any other suitable actions.

In the signal flow of Fig.8 the configuring of the UE 110 with the DRX configuration is shown as occurring after blocks 800 and 802. These blocks could be performed at the same time or in any suitable order.

At block 806 the gNB 120 can transmit DL data pattern information to the UE 110. The DL data pattern information can be generated by a model or by any other suitable means. Other types of data pattern could be used in other examples.

The transmission of the DL data pattern information can be in accordance with the configuration of bock 800. The transmission of the DL data pattern information can be triggered by a timer, by a change in traffic pattern state of the UE 110 or gNB 120, and/or by any other suitable event. The DL pattern information can be indicated using an indicator that maps a UE state or gNB state to a network traffic prediction.

At block 808 the UE 110 uses the received DL data pattern information to update the local model at the UE 110. The local model is used by the UE 110 to predict network traffic for the UE 110 or to predict any other suitable data patterns. The updating of the model using the received DL data pattern information can enhance the accuracy of the model. The updating of the model can increase the confidence level of outputs of the model. If the model is updated then the gNB 120 can reconfigure the DRX configuration of the UE 110. The reconfiguration can provide a better fit for the traffic pattern. The updating can be achieved by sending another DRX configuration as used at block 804 or by using any other suitable signaling. The updates to the DRX configuration can depend on the DL traffic that has been predicted.

In some examples updates to the model can be made to take into account UL traffic. The UE 110 may be better able to predict network traffic than the gNB 120 because it has more knowledge of how an application is being used. Updates to the model and/or the DRX configuration can depend on predicted DL traffic and/or predicted UL traffic where UL traffic requires dynamic grant.

At block 810 the UE 110 determines that a PDCCH monitoring interval is approaching. Timing of the PDCCH monitoring interval can be in accordance with the configuration of block 800.

After it has been determined that a PDCCH monitoring interval is approaching the UE 110, at block 812, checks the configuration information that is received at blocks. The UE 110 uses the criteria from the configuration information to decide whether the a PDCCH monitoring interval that is approaching should be skipped.

The UE 110 can make the decision whether to skip the a PDCCH monitoring interval before the buffer calculation procedure. This can save computation power at the UE 110.

At block 814 the UE 110 determines that the appropriate criteria have been satisfied and skips the PDCCH monitoring. The UE 110 can skip the a PDCCH monitoring autonomously without a specific indication from the gNB 120.

When the UE 110 skips the a PDCCH monitoring interval this can free up resources for other purposes. The gNB 120 can be implicitly aware that the UE 110 has skipped the a PDCCH monitoring interval and can allocate the resources that have been freed up for other purposes.

In some examples the gNB 120 can configure the UE 110 with rules that enable the UE 110 to monitor the PDCCH rather than skip the monitoring. This can be useful in scenarios where the accuracy of the model predictions might not be high enough, for example if they are below a confidence threshold. In such cases, rather than skip the monitoring at block 814 the UE 110 can perform the monitoring to check the accuracy of the model and make any appropriate adjustments.

Figs. 9A and 9B show example methods that can be implemented in examples of the disclosure. The method of Fig. 9A could be implemented by a UE 110 and the method of Fig. 9B could be implemented by a corresponding gNB 120.

The method comprises, at block 900, receiving from the gNB 120 configuration information relating to a network traffic prediction. The configuration information indicates criteria for cancelling CG occasions.

The criteria that are indicated in the configuration information can comprise information relating to an action that is to be performed by the UE 110. In this example the criteria that are indicated in the configuration information can comprise criteria relating to cancelling CG occasions. In some examples the criteria can comprise one or more of: a confidence threshold in a predicted data pattern, an LCG to which the criteria apply, an LCH to which the criteria apply, a prohibit timer, or any other suitable criteria. Where the criteria comprises a prohibit timer the criteria can also comprise an indication of the starting requirements for the timer. The starting requirements for the timer could comprise the sending of a data pattern such as buffer occupancy pattern information or any other suitable requirements.

At block 902 the method comprises determining buffer occupancy pattern information. The buffer occupancy pattern information, and/or any other suitable data patterns, can be sent to the gNB 120.

At block 904 the method comprises, determining based at least in part on the buffer occupancy pattern information, whether an indicated criteria from the configuration information is met. The determining of whether an indicated criteria from the configuration information is met can be performed if the UE 110 has detected that a eg occasion is approaching. For example, if a CG occasion is within a given time period. Therefore the determining if the criteria has been met can occur in response to detecting that a CG occasion is approaching. If it is not determined that a CG occasion is approaching then the criteria do not need to be checked. At block 906 the method comprises controlling cancelling of a CG occasion in accordance with the indicated criteria. Therefore, based on the criteria with which the UE 110 has been configured and the buffer occupancy pattern information the CG can be cancelled or not cancelled. For example, if a CG occasion is not needed based on the predicted buffer occupancy pattern information the UE 110 can autonomously decide to cancel the CG occasion without specific instruction from the gNB 120. This can enable efficient use of network resources and save power at the UE 110.

In some examples the controlling of the cancelling of the CG occasion can comprise not cancelling the CG. If the CG occasion is not cancelled this can be used to determine if the model used to predict the data pattern is still accurate.

The method of Fig. 9B corresponds to the method of Fig. 9A. The method of Fig. 9B comprises, at block 910, transmitting to the UE 110 configuration information relating to a network traffic prediction, the configuration information indicating criteria for cancelling CG occasions. The configuration information that is transmitted by the gNB 120 at block 910 can be received by the UE 110 at block 900.

The method that is performed by the gNB 120 can also comprise additional blocks that are not shown in Fig. 9B. For example, if the UE 110 transmits buffer occupancy pattern information, then this can be received the gNB 120. The gNB 120 can then use the received buffer occupancy pattern information for any suitable purpose. In some examples, the buffer occupancy pattern information can be used to update a model that is used for predicting network traffic. This can be a local model that is used by the gNB 120 to predict network traffic for the UE 110 and/or the model used by the UE 110.

If the CG occasion is cancelled then the gNB 120 can reallocate resources that would have otherwise been used for the CG. In some examples the gNB 120 can receive an indication from the UE 110 that a CG occasion has been cancelled. The gNB could then perform the reallocation of the resources in response to the indication.

Fig. 10 shows an example signal flow that can be used to implement examples of the disclosure. In this example the UE 110 is configured to autonomously determine whether to cancel a CG occasion. This provides for efficient signaling and use of network resources.

At block 1000 the gNB 120 configures the UE 110 to send data pattern information such as an anticipated buffer occupancy report. The anticipated buffer occupancy report can be generated using a model such as an AI/ML model or any other suitable type of model. The gNB 120 can configure the UE 110 with the model. The gNB 120 can configure the UE 110 with indicators that map a state of the model to a predicted network traffic or buffer occupancy. The gNB 120 can configure the UE 110 to send the anticipated buffer occupancy report at regular intervals or in response to a defined trigger event such as a change in a traffic pattern state. The traffic pattern state can comprise the state of the model. For example, the traffic pattern state can comprise an output of the AI/ML model.

The configuration at block 1000 configures the UE 110 to send an anticipated buffer occupancy report in response to a trigger condition. The trigger condition could be the expiry of a time period or that the confidence level of the model has fallen below a given confidence level, or could be any other suitable trigger event.

At block 1002 the gNB 120 sends configuration information to the UE 110. The configuration information indicates criteria that can be used by the UE 110 to decide whether to cancel a CG occasion. The criteria can relate to the predicted network traffic that is generated by the model. For example, the UE 110 can determine if an output of the model satisfies one or more of the criteria when it is deciding whether to cancel a CG occasion.

The criteria that are indicated in the configuration information provides a policy that can be used by the UE 110 when determining whether or not to cancel the CG occasion. The policy can comprise a set of rules or conditions that can be implemented by the UE 110.

The criteria comprised within the configuration information can be determined by the actions that are controlled by the configuration information. In this example the configuration information controls whether a CG occasion is canceled. In this example the criteria can comprise one or more of: a confidence threshold in a predicted data pattern, an LCG to which the criteria apply, an LCH to which the criteria apply, a prohibit timer, or any other suitable criteria. Where the criteria comprises a prohibit timer the criteria can also comprise an indication of the starting requirements for the timer. The starting requirements for the timer could comprise the sending of a data pattern such as buffer occupancy pattern information or any other suitable requirements.

In the example of Fig. 10 blocks 1000 and 1002 are shown as separate blocks. In examples of the disclosure they can be performed together.

The signal used for blocks 1000 and 1002 can comprise semi-static signaling such as RRC signaling.

At block 1004 the gNB 120 sends a CG configuration to the UE 110. The CG configuration configures the UE 110 with different parameter values such as periodicity and allocation information, and any other suitable parameter values.

In the signal flow of Fig. 10 the configuring of the UE 110 with a CG configuration is shown as occurring after blocks 1000 and 1002. These blocks could be performed at the same time or in any suitable order.

At block 1006 the UE 110 can transmit buffer occupancy pattern information to the gNB 120. The buffer occupancy pattern information can be generated by a model or by any other suitable means. Other types of data pattern could be used in other examples. The transmission of the buffer occupancy pattern information can be in accordance with the configuration of bock 1000. The transmission of the buffer occupancy pattern information can be triggered by a timer, by a change in traffic pattern state of the UE 110, and/or by any other suitable event. The buffer occupancy pattern information can be indicated using an indicator that maps a UE state to a network traffic prediction of the UE 110.

At block 1008 the gNB 120 uses the received buffer occupancy pattern information to update the local model at the gNB 120. The local model is used by the gNB 120 to predict network traffic for the UE 110 or to predict any other suitable data patterns. The updating of the model using the received buffer occupancy pattern information can enhance the accuracy of the model. The updating of the model can increase the confidence level of outputs of the model.

If the model is updated then the gNB 120 can reconfigure the CG configuration of the UE 110. The reconfiguration can provide a better fit for the traffic pattern. The updating can be achieved by sending another CG configuration as used at block 1004 or by using any other suitable signaling.

At block 1010 the UE 110 determines that a CG occasion is approaching. Timing of the CG occasion can be in accordance with the configuration of block 1000.

After it has been determined that a CG occasion is approaching the UE 110, at block 1012, checks the configuration information that is received at block 1002. The UE 110 uses the criteria from the configuration information to decide whether the CG occasion that is approaching should be skipped.

The UE 110 can make the decision whether to cancel the CG occasion before the buffer calculation procedure. This can save computation power at the UE 110. At block 1014 the UE 110 determines that the appropriate criteria have been satisfied and cancels the CG occasion. The UE 110 can cancel the CG occasion autonomously without a specific indication from the gNB 120.

When the UE 110 cancels the CG occasion this can free up resources for other purposes. The gNB 120 can be implicitly aware that the UE 110 has cancelled the CG occasion and can allocate the resources that have been freed up for other purposes.

In some examples the gNB 120 can configure the UE 110 with rules that enable the UE 110 to decide not to cancel the CG occasion. This can be useful in scenarios where the accuracy of the model predictions might not be high enough, for example if they are below a confidence threshold. In such cases, rather than cancel the CG occasion at block 1014 the UE 110 can proceed with the CG. This can enable the model to be adjusted to improve the accuracy of the model.

The models that are used to predict the data patterns can comprise AI/ML models. The AI/ML models can comprise any model that is trainable or tuneable using data. The AI/ML model can comprise a computer program. The AI/ML model can be trained to perform a task, such as predicting data patterns, without being explicitly programmed to perform that task. The AI/ML model can be configured to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E. In these examples the AI/ML model can learn from previous data patterns or other suitable data. The AI/ML model can also be a trainable computer program. Other types of AI/ML models could be used in other examples.

Any suitable process can be used to train the AI/ML model. The training of the AI/ML model can be performed using real world/or simulation data. The training data used to train the AI/ML model can comprise historical data collected from the network 100 and/or live data collected by the UE 110 and network. The training of the AI/ML model can be repeated as appropriate until the AI/ML model has attained a sufficient level of stability. The AI/ML model has a sufficient level of stability when fluctuations in the predictions provided by the AI/ML model are low enough to enable the AI/ML model to be used to predict the data patterns. The AI/ML model has a sufficient level of stability when fluctuations in the predictions provided by the AI/ML model are low enough so that the AI/ML model provides consistent responses to test inputs. In some examples the training of the AI/ML model can be repeated as appropriate until one or more parameters of the outputs have reached a pre-defined threshold and/or until a predefined accuracy has been attained and/or until any other suitable criteria are satisfied.

It is also possible to train one AI/ML model with specific architecture, then derive another AI/ML model from that using processes such as compilation, pruning, quantization or distillation. The term “AI/ML Model” covers also all these use cases and the outputs of them. The AI/ML model can be executed using any suitable apparatus, for example CPU, GPU, ASIC, FPGA, compute-in-memory, analog, or digital, or optical apparatus. It is also possible to execute the AI/ML model in apparatus that combine features from any number of these, for instance digital-optical or analog-digital hybrids. In some examples the weights and required computations in these systems can be programmed to correspond to the AI/ML model.

Fig. 11 shows an example controller 1100. The controller 1100 could be provided within an entity such as a UE 110, a gNB 120 or any other suitable entity. Implementation of the controller 1100 may be as controller circuitry. The controller 1100 may be implemented in hardware alone, have certain aspects in software including firmware alone or can be a combination of hardware and software (including firmware).

As illustrated in Fig. 11 the controller 1100 can be implemented using instructions that enable hardware functionality, for example, by using executable instructions of a computer program 1106 in a general-purpose or special-purpose processor 1102 that may be stored on a computer readable storage medium (disk, memory etc.) to be executed by such a processor 1102.

The processor 1102 is configured to read from and write to the memory 1104. The processor 1102 may also comprise an output interface via which data and/or commands are output by the processor 1102 and an input interface via which data and/or commands are input to the processor 1102.

The memory 1104 stores a computer program 1106 comprising computer program instructions (computer program code) that controls the operation of the apparatus when loaded into the processor 1102. The computer program instructions, of the computer program 1106, provide the logic and routines that enables the apparatus to perform the methods illustrated in the Figs. The processor 1102 by reading the memory 1104 is able to load and execute the computer program 1106.

In some examples where the controller 1100 is provided within a device such as a network node the controller 1100 therefore comprises means for: transmitting 510 to a UE 110 configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap.

In some examples where the controller 1100 is provided within a device such as a UE 110 the controller 1100 therefore comprises means for: receiving 500 from a network node 120 configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining 502 buffer occupancy pattern information; determining 504 based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling 506 skipping of the measurement gap in accordance with the indicated criteria.

The computer program 1106 may arrive at the apparatus via any suitable delivery mechanism 1108. The delivery mechanism 1108 may be, for example, a machine-readable medium, a computer-readable medium, a non-transitory computer-readable storage medium, a computer program product, a memory device, a record medium such as a Compact Disc Read-Only Memory (CD-ROM) or a Digital Versatile Disc (DVD) or a solid- state memory, an article of manufacture that comprises or tangibly embodies the computer program 1106. The delivery mechanism may be a signal configured to reliably transfer the computer program 1106. The apparatus may propagate or transmit the computer program 1106 as a computer data signal.

The computer program 1106 can comprise computer program instructions for causing a network node 120 to perform at least the following or for performing at least the following: transmitting 510 to a UE 110 configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap. The computer program 1106 can comprise computer program instructions for causing a UE 110 to perform at least the following or for performing at least the following: receiving 500 from a network node 120 configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining 502 buffer occupancy pattern information; determining 504 based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling 506 skipping of the measurement gap in accordance with the indicated criteria.

The computer program instructions may be comprised in a computer program, a non- transitory computer readable medium, a computer program product, a machine-readable medium. In some but not necessarily all examples, the computer program instructions may be distributed over more than one computer program.

Although the memory 1104 is illustrated as a single component/circuitry it may be implemented as one or more separate components/circuitry some or all of which may be integrated/removable and/or may provide permanent/semi-permanent/ dynamic/cached storage.

Although the processor 1102 is illustrated as a single component/circuitry it may be implemented as one or more separate components/circuitry some or all of which may be integrated/removable. The processor 1102 may be a single core or multi-core processor.

References to “computer-readable storage medium”, “computer program product”, “tangibly embodied computer program” etc. or a “controller”, “computer”, “processor” etc. should be understood to encompass not only computers having different architectures such as single /multi- processor architectures and sequential (Von Neumann)/parallel architectures but also specialized circuits such as field-programmable gate arrays (FPGA), application specific circuits (ASIC), signal processing devices and other processing circuitry. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc.

As used in this application, the term “circuitry” can refer to one or more or all of the following:

(a) hardware-only circuitry implementations (such as implementations in only analog and/or digital circuitry) and

(b) combinations of hardware circuits and software, such as (as applicable):

(i) a combination of analog and/or digital hardware circuit(s) with software/firmware and

(ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions and

(c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g. firmware) for operation, but the software might not be present when it is not needed for operation.

This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor and its (or their) accompanying software and/or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit for a mobile device or a similar integrated circuit in a server, a cellular network device, or other computing or network device.

The blocks illustrated in the Figs, can represent steps in a method and/or sections of code in the computer program 1106. The illustration of a particular order to the blocks does not necessarily imply that there is a required or preferred order for the blocks and the order and arrangement of the block can be varied. Furthermore, it can be possible for some blocks to be omitted.

Examples of the disclosure can be provided in an electronic device, for example, a mobile terminal such as a UE. It should be understood, however, that a mobile terminal is merely illustrative of an electronic device that would benefit from examples of implementations of the present disclosure and, therefore, should not be taken to limit the scope of the present disclosure to the same. While in certain implementation examples, an apparatus that enables examples of the disclosure can be provided in a mobile terminal, other types of electronic devices, such as, but not limited to: mobile communication devices, hand portable electronic devices, wearable computing devices, portable digital assistants (PDAs), pagers, mobile computers, desktop computers, televisions, gaming devices, laptop computers, cameras, video recorders, GPS devices and other types of electronic systems, can readily employ examples of the present disclosure. Furthermore, devices can readily employ examples of the present disclosure regardless of their intent to provide mobility.

The term ‘comprise’ is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising Y indicates that X may comprise only one Y or may comprise more than one Y. If it is intended to use ‘comprise’ with an exclusive meaning then it will be made clear in the context by referring to ‘comprising only one...’ or by using ‘consisting.’

In this description, the wording ‘connect’, ‘couple’ and ‘communication’ and their derivatives mean operationally connected/coupled/in communication. It should be appreciated that any number or combination of intervening components can exist (including no intervening components), i.e., to provide direct or indirect connection/coupling/communication. Any such intervening components can include hardware and/or software components.

As used herein, the term "determine/determining" (and grammatical variants thereof) can include, not least: calculating, computing, processing, deriving, measuring, investigating, identifying, looking up (for example, looking up in a table, a database, or another data structure), ascertaining and the like. Also, "determining" can include receiving (for example, receiving information), accessing (for example, accessing data in a memory), obtaining and the like. Also, " determine/determining" can include resolving, selecting, choosing, establishing, and the like.

In this description, reference has been made to various examples. The description of features or functions in relation to an example indicates that those features or functions are present in that example. The use of the term ‘example’ or ‘for example’ or ‘can’ or ‘may’ in the text denotes, whether explicitly stated or not, that such features or functions are present in at least the described example, whether described as an example or not, and that they can be, but are not necessarily, present in some of or all other examples. Thus ‘example’, ‘for example’, ‘can’, or ‘may’ refers to a particular instance in a class of examples. A property of the instance can be a property of only that instance or a property of the class or a property of a sub-class of the class that includes some but not all the instances in the class. It is therefore implicitly disclosed that a feature described with reference to one example but not with reference to another example, can where possible be used in that other example as part of a working combination but does not necessarily have to be used in that other example.

As used herein, “at least one of the following:” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or” mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

Although examples have been described in the preceding paragraphs with reference to various examples, it should be appreciated that modifications to the examples given can be made without departing from the scope of the claims.

Features described in the preceding description may be used in combinations other than the combinations explicitly described above.

Although functions have been described with reference to certain features, those functions may be performable by other features whether described or not.

The description of a feature, such as an apparatus or a component of an apparatus, configured to perform a function, or for performing a function, should additionally be considered to also disclose a method of performing that function. For example, description of an apparatus configured to perform one or more actions, or for performing one or more actions, should additionally be considered to disclose a method of performing those one or more actions with or without the apparatus.

Although features have been described with reference to certain examples, those features may also be present in other examples whether described or not.

The term ‘a’, ‘an’ or ‘the’ is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising a/an/the Y indicates that X may comprise only one Y or may comprise more than one Y unless the context clearly indicates the contrary. If it is intended to use ‘a’, ‘an’ or ‘the’ with an exclusive meaning then it will be made clear in the context. In some circumstances the use of ‘at least one’ or ‘one or more’ may be used to emphasis an inclusive meaning but the absence of these terms should not be taken to infer any exclusive meaning.

The presence of a feature (or combination of features) in a claim is a reference to that feature or (combination of features) itself and to features that achieve substantially the same technical effect (equivalent features). The equivalent features include, for example, features that are variants and achieve substantially the same result in substantially the same way. The equivalent features include, for example, features that perform substantially the same function, in substantially the same way to achieve substantially the same result.

In this description, reference has been made to various examples using adjectives or adjectival phrases to describe characteristics of the examples. Such a description of a characteristic in relation to an example indicates that the characteristic is present in some examples exactly as described and is present in other examples substantially as described.

The above description describes some examples of the present disclosure however those of ordinary skill in the art will be aware of possible alternative structures and method features which offer equivalent functionality to the specific examples of such structures and features described herein above and which for the sake of brevity and clarity have been omitted from the above description. Nonetheless, the above description should be read as implicitly including reference to such alternative structures and method features which provide equivalent functionality unless such alternative structures or method features are explicitly excluded in the above description of the examples of the present disclosure.

Whilst endeavoring in the foregoing specification to draw attention to those features believed to be of importance the Applicant may seek protection via the claims in respect of any patentable feature or combination of features hereinbefore referred to and/or shown in the drawings whether or not emphasis has been placed thereon.

Claims

1 . A User Equipment (UE) comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the UE to perform at least: receiving from a network node configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining buffer occupancy pattern information; determining based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling skipping of the measurement gap in accordance with the indicated criteria.

2. The UE as claimed in claim 1 wherein the criteria indicated in the configuration comprises one or more of: a confidence threshold in a predicted data pattern; one or more frequency ranges; one or more types of measurement; prohibit timer.

3. The UE as claimed in claim 2 wherein the criteria indicated in the configuration comprise starting requirements for the prohibit timer.

4. The UE as claimed in any preceding claim wherein the processor and memory are arranged to cause the UE to perform sending the buffer occupancy pattern information to the network node.

5. The UE as claimed in any preceding claim wherein the processor and memory are arranged to cause the UE to perform sending to the network node an indicator configured to map a UE state to a network traffic prediction for the UE

6. The UE as claimed in any preceding claim wherein the processor and memory are arranged to cause the UE to perform determining whether an indicated criteria from the configuration information is met if it has detected that a measurement gap is approaching.

7. A method comprising: receiving from a network node configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining buffer occupancy pattern information; determining based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling skipping of the measurement gap in accordance with the indicated criteria.

8. A computer program comprising instructions which, when executed by a UE, cause the UE to perform at least: receiving from a network node configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap; determining buffer occupancy pattern information; determining based at least in part on the buffer occupancy pattern information whether an indicated criteria from the configuration information is met; and controlling skipping of the measurement gap in accordance with the indicated criteria.

9. A network node comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the network node to perform at least: transmitting to a User Equipment (UE) configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap-

10. The network node as claimed in any preceding claim wherein the processor and memory are arranged to cause the network node to perform receiving the buffer occupancy pattern information from the UE.

11. The network node as claimed in claim 8 wherein the processor and memory are arranged to cause the network node to perform using the received buffer occupancy pattern information to update a model for predicting network traffic.

12. The network node as claimed in any of claims 9 to 11 wherein the processor and memory are arranged to cause the network node to perform receiving an indication from the UE that a measurement gap is being skipped.

13. The network node as claimed in any of claims 9 to 12 wherein the processor and memory are arranged to cause the network node to perform reallocating resources in response to the measurement gap being skipped.

14. The network node as claimed in any of claims 9 to 13 wherein the processor and memory are arranged to cause the network node to perform receiving from the UE an indicator configured to map a UE state to a network traffic prediction for the UE.

15. A method comprising: transmitting to a User Equipment (UE) configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap-

16. A computer program comprising instructions which, when executed by a network node, cause the network node to perform at least: transmitting to a User Equipment (UE) configuration information relating to a network traffic prediction, the configuration information indicating criteria for skipping a measurement gap-