CN116255705B - Method, device, electronic device and storage medium for determining building spatiotemporal temperature - Google Patents
Method, device, electronic device and storage medium for determining building spatiotemporal temperatureInfo
- Publication number
- CN116255705B CN116255705B CN202211738300.0A CN202211738300A CN116255705B CN 116255705 B CN116255705 B CN 116255705B CN 202211738300 A CN202211738300 A CN 202211738300A CN 116255705 B CN116255705 B CN 116255705B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- monitoring point
- temperature
- subset
- floor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Mechanical Engineering (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Fuzzy Systems (AREA)
- Air Conditioning Control Device (AREA)
Abstract
本发明公开了一种建筑时空序列温度确定方法、装置、电子设备及存储介质。通过基于每个监测点处采集到的温度数据序列，确定楼层对应的平均温度时序数据；并从所述监测点中选取指定数量的监测点构成若干个监测点子集；从而根据所述监测点子集中监测点的温度数据序列与所述平均温度时序数据之间的第一相关数据，以及所述监测点子集中监测点的温度数据序列之间的第二相关数据，在所述若干个监测点子集中确定目标子集；进而基于所述目标子集中代表监测点的温度数据序列确定所述楼层的温度，更加准确地确定楼宇综合温度，满足楼宇中用户对冷热舒适的不同需求。
The present invention discloses a method, device, electronic device, and storage medium for determining the spatiotemporal temperature of a building. The method determines the average temperature time series data corresponding to a floor based on the temperature data sequence collected at each monitoring point; selects a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets; and determines a target subset within the plurality of monitoring point subsets based on first correlation data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time series data, as well as second correlation data between the temperature data sequences of the monitoring points in the monitoring point subsets; and then determines the temperature of the floor based on the temperature data sequence of the representative monitoring points in the target subset, thereby more accurately determining the comprehensive temperature of the building and meeting the different needs of users in the building for heating and cooling comfort.
Description
Technical Field
The invention relates to the technical field of building temperature automation control, in particular to a building space-time sequence temperature determining method, a device, electronic equipment and a storage medium.
Background
In building load prediction-based control techniques, the cooling and heating loads of a building cold and heat source system are typically characterized by calculating the comprehensive room temperature of the building. Common methods of calculating the integrated room temperature include averaging.
In the related art, first, temperature monitoring points are randomly installed in a building, and then the monitored temperature is averaged. Although the method can reflect the basic temperature level of the whole building, the accuracy of the comprehensive building temperature determined by the method needs to be improved so as to meet different requirements of users in the building on cold and hot comfort.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent. To this end, the invention provides a method, a device, electronic equipment and a storage medium for determining the temperature of a building space-time sequence.
The invention provides a building space-time sequence temperature determining method, which comprises at least one floor, wherein the floor corresponds to a temperature monitoring area, the temperature monitoring area is divided into a plurality of monitoring areas, monitoring points are arranged in the monitoring areas, temperature sensors are arranged at the monitoring points, and the method comprises the following steps:
determining average temperature time sequence data corresponding to the floors based on the temperature data sequences acquired at each monitoring point;
selecting a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets;
determining a target subset from the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subsets, wherein the target subset comprises representative monitoring points which can be used for representing the floor temperature;
the temperature of the floor is determined based on a sequence of temperature data representing monitoring points in the target subset.
In one embodiment, the determining, based on the temperature data sequences collected at each monitoring point, average temperature time series data corresponding to the floor includes:
Determining an effective monitoring point set in the monitoring points according to an initial temperature data sequence acquired at each monitoring point, wherein the effective monitoring point set comprises a plurality of effective monitoring points;
And determining average temperature time sequence data corresponding to the floors based on the effective temperature data sequences acquired at each effective monitoring point.
In one embodiment, the selecting a specified number of monitoring points from the monitoring points forms a plurality of monitoring point subsets, including:
And taking one third of the number of the effective monitoring points in the effective monitoring point set as the appointed number, and arranging and combining the effective monitoring points included in the effective monitoring point set to obtain a plurality of monitoring point subsets.
In one embodiment, the determining the target subset from the plurality of monitoring point subsets according to first correlation data between the temperature data sequences of the monitoring points in the monitoring point subset and the average temperature time series data and second correlation data between the temperature data sequences of the monitoring points in the monitoring point subset includes:
Determining an average value of first mutual information between a temperature data sequence of each monitoring point in the monitoring point subset and the average temperature time sequence data as first related data of the monitoring point subset;
determining an average value of second mutual information among monitoring points in the monitoring point subset based on a temperature data sequence of the monitoring points in the monitoring point subset, and taking the average value as second related data of the monitoring point subset;
And determining a target subset meeting a preset correlation condition from the plurality of monitoring point subsets according to the average value of the first mutual information and the average value of the second mutual information.
In one embodiment, the determining, based on the average value of the first mutual information and the average value of the second mutual information, a target subset that meets a preset relevance condition among the plurality of monitoring point subsets includes:
determining target related data of any monitoring point subset aiming at any monitoring point subset based on the average value of first mutual information of the any monitoring point subset and the average value of second mutual information of the any monitoring point subset;
And determining the monitoring point subset of which the target data meets the maximum relevant minimum redundancy condition as the target subset from the plurality of monitoring point subsets.
In one embodiment, the method further includes drawing a monitoring point image of the floor based on the representative monitoring points in the target subset.
In one embodiment, the representative monitoring point corresponds to personnel density, and the method further comprises displaying a mark object corresponding to the personnel density at the position of the representative monitoring point in the monitoring point image based on the personnel density corresponding to the representative monitoring point.
In one embodiment, the determining the temperature of the floor based on the sequence of temperature data representing the monitoring points in the target subset includes:
and inputting the temperature data sequence representing the monitoring point into a room temperature prediction neural network model corresponding to the floor for prediction, and obtaining the comprehensive room temperature of the floor.
In one embodiment, the monitoring area is divided according to the identification information of the temperature sensor, the floor corresponds to a floor category, and the floor category is any one of a top floor, an upper middle floor, a lower middle floor, a bottom floor and underground.
The invention provides a building space-time sequence temperature determining device, which comprises at least one floor, wherein the floor corresponds to a temperature monitoring area, the temperature monitoring area is divided into a plurality of monitoring areas, monitoring points are arranged in the monitoring areas, temperature sensors are arranged at the monitoring points, and the device comprises:
The average temperature determining module is used for determining average temperature time sequence data corresponding to the floors based on the temperature data sequences acquired at each monitoring point;
The monitoring point subset forming module is used for selecting a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets;
The target subset determining module is used for determining a target subset from the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subsets, wherein the target subset comprises representative monitoring points which can be used for representing the floor temperature;
and the floor temperature determining module is used for determining the temperature of the floor based on the temperature data sequence representing the monitoring points in the target subset.
The invention provides an electronic device comprising a memory storing a computer program and a processor implementing the steps of any one of the methods described above when the processor executes the computer program.
The present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the preceding claims.
According to the embodiment, the average temperature time sequence data corresponding to the floors are determined based on the temperature data sequences acquired at each monitoring point, a plurality of monitoring point subsets are formed by selecting a specified number of monitoring points from the monitoring points, accordingly, a target subset is determined among the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subsets, the temperatures of the floors are determined based on the temperature data sequences representing the monitoring points in the target subset, building comprehensive temperatures are determined more accurately, and different requirements of users in the building on cold and hot comfort are met.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1a is a schematic diagram of an application scenario of a building space-time sequence temperature determining method according to an embodiment of the present disclosure.
Fig. 1b is a schematic flow chart of a method for determining a temperature of a building space-time sequence according to an embodiment of the present disclosure.
Fig. 1c is a schematic view of a monitoring point image provided according to an embodiment of the present disclosure.
Fig. 2 is a schematic flow chart of a method for determining a temperature of a building space-time sequence according to an embodiment of the present disclosure.
Fig. 3 is a schematic flow chart of determining average temperature time series data corresponding to floors according to one embodiment of the present disclosure.
Fig. 4 is a schematic flow chart of determining a target subset among a plurality of monitoring points according to an embodiment of the present disclosure.
Fig. 5 is a schematic flow chart of determining a target subset satisfying a preset correlation condition according to an embodiment of the present disclosure.
Fig. 6 is a block diagram of a construction space-time sequence temperature determining apparatus according to an embodiment of the present disclosure.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The energy consumption of the building operation and the energy consumption of the whole process in China respectively account for 21.7 percent and 46.5 percent of the total weight of the national energy consumption, and the total energy consumption of the building can be further improved along with the deep development of industrialization and town of China. Therefore, energy conservation and emission reduction of building operation energy are important aspects of work. At present, the buildings of parks and industrial enterprises (hereinafter referred to as parks) generally have the problems of extensive energy management, low energy efficiency, large energy consumption, increased environmental pressure and the like. The public cold and hot source system of the existing old park building is provided with independent group control systems, and can realize one-key start and stop and interlocking control of a cold and hot host machine and a water pump. However, most old parks have no water temperature control strategy for the water chilling unit, or have the problems of simple and rough water chilling unit loading and unloading strategy, dependence on manual control, insufficient experience of operators and the like. In addition, the public cold and heat source system of old park building does not have cold and heat system energy efficiency monitoring and analysis means generally, can not effectively guarantee comfortable stable room indoor temperature, does not have energy-saving operation control strategy, and has very big promotion space in the aspect of energy-saving optimization operation.
In general, the cold and heat source system of the old park building adopts general preset control logic, namely, calculates the actual load of the building according to the temperature difference and water flow of the chilled water supply and return water, so as to determine whether the input of a refrigerator is needed to be increased in the building. The method can not automatically adjust the operation parameters according to the factors such as outdoor climate, indoor terminal temperature, sunlight irradiation, holidays, personnel density and the like, so that the cold and heat source system can not keep high-efficiency operation, the cold and heat comfort requirements of partial users can not be met, and energy waste is easily caused.
Therefore, in energy saving optimization of public cold and heat source systems of park buildings, a control technology based on building load prediction is generally adopted. Building load prediction techniques can be categorized into physical model-based building load prediction techniques and algorithmic model-based building load prediction techniques. In building load prediction technology based on a physical model, a thermodynamic dynamic model such as a thermal resistance-heat capacity network is used for predicting the cooling and heating load of a building cold and heat source system, a building load prediction technology based on an algorithm model is used for designing the characteristics of the building load from various aspects such as outdoor climate, historical cooling and heating of the building, and a machine learning model is used for building and constructing the mapping relation between the building load characteristics and the cooling and heating load of the building. In the building load prediction method based on the physical model, as the building usually has a complex structure, the physical model has larger difference, so that the popularization and universality of the building load prediction method based on the physical model are poor. With the rapid development of the machine learning field and the wide access of a large number of sensors of the internet of things on the building side, the building load prediction technology based on the algorithm model achieves better development and application effects. However, the current technology lacks feature extraction to factors such as indoor tail end temperature, outdoor weather, holidays, personnel density and the like of a building, is difficult to adapt to randomness and variability of user behaviors in the building, cannot meet the cold and hot comfort requirements of users, and accordingly causes energy waste.
In the related art, in a control technology based on building load prediction, the cooling and heating loads of a building cold and heat source system are generally represented by calculating the comprehensive room temperature of a building. The following two methods are commonly used for calculating the comprehensive room temperature:
(1) Averaging. The method comprises the steps of randomly installing temperature monitoring points and then averaging the monitored temperature. The method can reflect the basic temperature level of the whole building, but cannot perform differential analysis, and cannot meet the cold and hot comfort requirements of part of users, such as basement property personnel, roof users, north facing users and the like, and complaints are easily caused by the users.
(2) And (5) weighting method. The method divides the whole building into three types of users, wherein the first type is a top building, the second type is a middle user, and the third type is a side user and a bottom user. The method comprises the steps of installing typical monitoring points in three types of users, for example, installing at least one room temperature monitoring point for a first type of user respectively, installing at least two types of room temperature monitoring points for a second type of user respectively, wherein upstairs users of one type of monitoring points are heated, upstairs users of the other type of monitoring points are not heated, and installing at least two types of room temperature monitoring points for a third type of user respectively, wherein upstairs users of one type of monitoring points are heated, and upstairs users of the other type of monitoring points are not heated. Thus, at least 5 types of room temperature monitoring points are installed in total. And then setting weight for each type of user, and finally calculating the comprehensive room temperature of the whole building according to the weight. The method can better reflect the heat supply efficiency of the whole building, but the division of typical users is too rough, so that the real heat supply condition of the building can not be accurately reflected. Meanwhile, the method only aims at a building heating system, and the cooling requirement of the building is not truly embodied (for example, the cooling requirement and the heating requirement of sunny users are opposite), so that the cooling and heating comfort requirements of users in a park building cannot be well met.
In order to enable a comprehensive room temperature calculation method of a building (hereinafter referred to as a building) to be well adapted to a complex and variable user structure in the building, it is necessary to provide a building space-time sequence temperature determination method, a device, electronic equipment and a storage medium. The comprehensive room temperature of each floor of the building is calculated in real time by using representative monitoring points, so that an optimal operation decision scheme of a building cold and heat source system is provided by means of load prediction, data analysis, operation strategy optimization and the like, and energy conservation and consumption reduction are realized. The method can meet the cold and hot comfort requirements of rooms of each branch floor of the building, and each room in the building does not need to be modeled independently, so that the number of indoor temperature monitoring devices can be reduced, algorithm calculation errors caused by errors when a large number of devices transmit data are reduced, and the calculation and data storage resources of the comprehensive room temperature calculation method can be saved.
Fig. 1a is a schematic diagram of an application scenario of a building space-time sequence temperature determining method provided in the present specification. Taking a park building a comprising 15 floors as an example, a temperature sensor may be installed in each room corresponding to each floor, for acquiring a temperature data sequence of each room. It should be noted that each temperature sensor may be provided with a unique number for binding with the location of the monitoring point where it is located. Fig. 1a is a schematic diagram of a topology structure obtained by topologically dividing each floor of a park building a and monitoring point positions of temperature sensors respectively included in each floor.
In the scene example, each floor in a building A of a park is firstly divided according to a first-level topological structure of a top layer, an upper layer, a middle layer, a lower layer, a bottom layer and an underground layer, monitoring point positions of temperature sensors respectively contained in each floor are secondly divided into a second-level topology according to each floor structure, representative monitoring points respectively corresponding to each floor are selected from the monitoring point positions of the temperature sensors respectively contained in each floor, then a room temperature prediction neural network model respectively corresponding to each floor is trained according to a temperature data sequence acquired by the representative monitoring points respectively corresponding to each floor and average temperature time sequence data respectively corresponding to each floor, and finally a comprehensive room temperature respectively corresponding to each floor can be calculated according to the room temperature prediction neural network model respectively corresponding to each floor.
An example illustrates how the primary topology is partitioned. In this scenario example, according to the illumination conditions (including illumination time, illumination intensity, etc.) of each floor, each floor of the building a span is divided into a primary topology including a top-level branch (sufficient illumination, long illumination time), a middle-upper-level branch (sufficient illumination, long illumination time), a middle-lower-level branch (general illumination, general illumination time), a bottom-level branch (less illumination, short illumination time), and a subsurface branch (no illumination). In some embodiments, the attic may not be divided separately for the case where the attic has the same structure as other floors.
An example illustrates how the secondary topology is partitioned. In this scenario example, the top tier branches comprise 15 floors, the upper tier branches comprise 9-14 floors, the lower tier branches comprise 3-8 floors, the bottom tier branches comprise 1-2 floors, and the underground branches comprise B1 and B2 floors. And carrying out secondary topological division on the temperature sensors corresponding to all floors in the primary topological branch according to the structure of each floor.
In this scenario example, each floor of a campus building a may include a north-facing location, a south-facing location, and an intermediate location. For the top-level branch, as the middle position of the floor of the 15 th floor is provided with the stairs which can lead to the sky, the temperature data of the room at the middle position of the floor can be influenced, and additional attention is required, therefore, the monitoring point positions of the temperature sensors contained in the floor of the 15 th floor of the top-level branch are subjected to secondary topological division according to north, south and centering. For the middle-upper branch and the middle-lower branch, the temperature data of the middle position of each floor is similar to the average temperature time sequence data of each floor, and no additional attention is required, so that the positions of the monitoring points of the temperature sensors respectively contained in each floor in the middle-upper branch and the middle-lower branch are subjected to secondary topological division according to the north facing direction and the south facing direction. For the bottom branch, the 1-2 building mainly comprises a bottom merchant and a hall, the temperature data of the bottom merchant is generally influenced by personnel density and is different from the cold and hot comfort requirements of the north-facing and south-facing positions, and the temperature data of the hall is generally similar to the average temperature time sequence data of the floor, so that the positions of monitoring points of temperature sensors contained in the bottom branch are subjected to secondary topological division according to the hall and the bottom merchant. For the underground B1-B2 building, because the cold and hot comfort requirements of the two floors are related to the depth of the floors, the positions of monitoring points of temperature sensors contained in the underground branches are directly divided into two levels according to the floors. With continued reference to fig. 1a, it should be noted that the number of monitoring point positions included in each floor in the brackets "()" is the same as the number of monitoring point positions included in the top floor.
In this scenario example, according to the personnel density in the room corresponding to each monitoring point position, the monitoring point positions corresponding to the room with lower personnel density may be represented by a square, and the monitoring point positions corresponding to other rooms may be represented by a circle.
An example illustrates how representative monitoring points are selected. In this example, first, average temperature time series data of each floor is calculated based on temperature data acquired by a temperature sensor included in each floor. And secondly, selecting a certain number of arbitrary monitoring point positions from all monitoring point positions contained in any secondary topological branch to form a plurality of monitoring point subsets. And thirdly, for any monitoring point subset in the plurality of monitoring point subsets, calculating first related data between the temperature data of each monitoring point position contained in the any monitoring point subset and the average temperature time sequence data of the floor where the monitoring point position is located, and calculating the average value of all the first related data in the any monitoring point subset. And calculating second related data between every two of the temperature data of each monitoring point position in any monitoring point subset, and calculating the average value of all the second related data in any monitoring point subset. And then, calculating the difference value between the average value of all the first related data corresponding to any monitoring point subset and the average value of all the second related data. And finally, according to the difference values corresponding to all the monitoring point subsets in the secondary topological branch, determining the monitoring point positions in the monitoring point subset corresponding to the maximum difference value as representative monitoring points in the secondary topological branch.
In this scenario example, through actual analysis, it is found that, because the average temperature data of each floor in the middle-upper branch is close, for the middle-upper branch, only the average temperature time sequence data of one floor can be calculated, and the average temperature time sequence data is used for selecting representative monitoring points of a plurality of floors in the middle-upper branch. The method for selecting the representative monitoring points of the middle-lower branch is consistent with that of the middle-upper branch.
Referring to fig. 1b, in this scenario example, valid monitoring points may be selected before the representative monitoring points are selected. The method comprises the steps of collecting all temperature data, firstly eliminating default values and unreasonable values, secondly calculating the percentage of effective data of each monitoring point position to the total number of the original data, screening out monitoring points with the effective data accounting for more than 80% of the original data, and listing the monitoring points as effective monitoring points. Therefore, abnormal comprehensive room temperature calculation of each floor caused by temperature data distortion is prevented, and the real indoor temperature condition of the building can not be effectively reflected.
With continued reference to fig. 1b, in this scenario example, the first related data and the second related data are calculated by mutual information theory. And selecting substitution table monitoring points from the monitoring points of each branch floor (the floors of each secondary topological branch), namely selecting a subset S n formed by n (n is less than or equal to m) monitoring points from a feature set F m formed by m monitoring points. According to the maximum correlation principle, the optimal subset S n should meet the requirement that the average value of the mutual information of the monitoring point P F and the average temperature P of each floor of the target variable reaches the maximum value. And only the optimal subset selected according to the maximum correlation principle has larger redundancy (larger correlation among all monitoring points in the subset), and the constraint condition of the minimum redundancy principle is added to the optimal subset, so that the average value of mutual information among the monitoring points contained in S n is minimum. When each branch floor represents monitoring point selection, firstly calculating mutual information I (P F, P) of each monitoring point temperature P F and average temperature P of each floor, and then selecting the representative monitoring point by adopting an mRMR principle. CalculatingAll in combinationAnd (3) withAnd selecting a combination conforming to the mRMR principle to obtain an optimal subset S n, namely the combination of the representative monitoring points of each branch floor.
With continued reference to fig. 1b, an exemplary illustration of how the comprehensive room temperature for each floor is calculated is provided. In the present scenario example, based on the historical temperature data of any floor representing the monitoring point and the historical average temperature time sequence data of any floor, the room temperature prediction neural network model corresponding to any floor is obtained through training. And (3) inputting temperature data representing monitoring points of each floor into a trained model, and outputting the comprehensive room temperature of each floor.
In this scenario example, the room temperature prediction neural network model corresponding to each floor in the upper-layer branch may be the same, and the room temperature prediction neural network model corresponding to each floor in the lower-layer branch may be the same.
Further, in this scenario example, after the representative monitoring point is selected, the monitoring point images of each floor of the campus building a may be redrawn according to the representative monitoring points of each floor. Fig. 1c is a view of monitoring points for each floor of the campus building a plotted against representative monitoring points for each floor selected. According to the image, the rationality of the selection of the monitoring points can be analyzed and properly adjusted.
In this scenario example, when the personnel density at any monitoring point position of any floor of the park building a varies, or the external environmental condition of the building varies, topology division may be performed again on each floor and the monitoring point positions of the temperature sensors included in each floor, respectively, and a new representative monitoring point may be selected.
The embodiment of the specification provides a building space-time sequence temperature determining method, a building comprises at least one floor, the floor corresponds to a temperature monitoring area, the temperature monitoring area is divided into a plurality of monitoring areas, monitoring points are arranged in the monitoring areas, and temperature sensors are arranged at the monitoring points. Referring to fig. 2, the building space-time sequence temperature determining method may include the steps of:
s210, determining average temperature time sequence data corresponding to floors based on temperature data sequences acquired at each monitoring point.
The building can be an office building/industrial enterprise building and the like, the floor corresponds to a temperature monitoring area, and the temperature monitoring area can be all areas of the floor or a part of areas designated in the floor. The temperature monitoring areas are divided to obtain a plurality of monitoring areas, wherein the monitoring areas can be obtained by dividing office areas of users in floors, or can be obtained by dividing temperature demands of the users in floors. Monitoring points are deployed in the monitoring area, temperature sensors are installed at the monitoring points, and temperature data in the monitoring area are collected by the temperature sensors to form a temperature data sequence.
Specifically, each monitoring point is provided with a temperature sensor, and temperature data acquired by the temperature sensor can be sent to temperature-controlled computer equipment in a wireless communication mode. The computer equipment can directly utilize the temperature data sequences acquired at each monitoring point to perform temperature average value calculation, so as to obtain average temperature time sequence data corresponding to floors. The computer equipment can also preprocess the temperature data sequence acquired at the received monitoring point, and determine average temperature time sequence data corresponding to the floor by utilizing the preprocessed temperature data sequence.
S220, selecting a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets.
The designated number can be determined by the actual number of deployed monitoring points, or can be determined by combining the actual requirements of a user on temperature control. Specifically, a specified number of monitoring points are arbitrarily selected from a plurality of deployed monitoring points, the specified number of detected monitoring points constituting a subset of monitoring points. Similarly, several subsets of monitoring points may be obtained. It will be appreciated that there may be partial repetition of each monitoring point in the subset of monitoring points.
S230, determining a target subset from a plurality of monitoring point subsets according to first related data between temperature data sequences of the monitoring points in the monitoring point subsets and average temperature time sequence data and second related data between temperature data sequences of the monitoring points in the monitoring point subsets.
Wherein the target subset includes representative monitoring points that can be used to characterize floor temperatures.
In some cases, in order to be able to more accurately determine the floor temperature, it is necessary to select a representative monitoring point from among several monitoring points deployed, and thus, a target subset is selected from among several monitoring point subsets based on the correlation data between the temperature data sequences at the monitoring points to determine the representative monitoring point.
Specifically, for each monitoring point subset, first correlation data between the temperature data sequence and the average temperature time sequence data of the monitoring points in the monitoring point subset is calculated. And carrying out correlation calculation by using the temperature data sequences of every two monitoring points in the monitoring point subset to obtain second correlation data between the temperature data sequences of the monitoring points in the monitoring point subset. Further, the first correlation data and the second correlation data are utilized to screen the formed monitoring point subset, and the monitoring point subset meeting the correlation condition requirement, namely the target subset, is obtained. The temperature data collected by the monitoring points in the target subset can be used to characterize the floor temperature, i.e. the monitoring points comprised in the target subset are representative monitoring points.
S240, determining the temperature of the floor based on the temperature data sequence representing the monitoring points in the target subset.
Specifically, after determining the representative monitoring point, the temperature of the floor may be determined using the temperature data sequence representative of the monitoring point in the target subset. The temperature data sequence representing the monitoring points in the target subset can be input into the neural network model for prediction, and the temperature output by the neural network model is determined as the floor temperature. Further, the comprehensive floor room temperature obtained through statistical calculation of representative monitoring points can be provided with a proper running decision scheme of the cold and heat source systems of all floors through load prediction, data analysis and running strategy optimization, and the purposes of energy conservation and consumption reduction of the whole building, energy conservation and emission reduction of a park and environmental protection are achieved on the premise of effectively ensuring the indoor temperature comfort of a user.
According to the embodiment, the average temperature time sequence data corresponding to the floors are determined based on the temperature data sequences acquired at each monitoring point, a plurality of monitoring point subsets are formed by selecting the specified number of monitoring points from the monitoring points, accordingly, the target subset is determined in the plurality of monitoring point subsets according to first correlation data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time sequence data and second correlation data between the temperature data sequences of the monitoring points in the monitoring point subsets, and further, the temperature of the floors is determined based on the temperature data sequences representing the monitoring points in the target subset, the building comprehensive temperature is determined more accurately, and different requirements of users on cold and hot comfort in the building are met. Further, on the premise of effectively ensuring the indoor temperature comfort of the user, the purposes of energy conservation and consumption reduction of the whole building and energy conservation and emission reduction and environmental protection are achieved.
In some embodiments, referring to fig. 3, determining average temperature time series data corresponding to a floor based on a temperature data sequence collected at each monitoring point may include the steps of:
s310, determining a valid monitoring point set in the monitoring points according to the initial temperature data sequence acquired at each monitoring point.
S320, determining average temperature time sequence data corresponding to floors based on the effective temperature data sequences acquired at each effective monitoring point.
The effective monitoring point set comprises a plurality of effective monitoring points. Specifically, a movable temperature and humidity sensor (4G) is placed on each floor as comprehensively as possible, and indoor temperature data of a user are collected for a plurality of days continuously to obtain an initial temperature data sequence. Judging whether default values, unreasonable values and the like exist in the initial temperature data sequence, after abnormal data in the conditions are removed, calculating the percentage of effective data to the total number of the original data, screening out data monitoring points with the effective data accounting for more than 80% of the original data, and determining an effective monitoring point set in a plurality of monitoring points, wherein the monitoring points included in the effective monitoring point set are effective monitoring points. And the monitoring points with weaker signals or abnormal data of the temperature sensor are removed, so that abnormal comprehensive room temperature calculation caused by temperature data distortion is prevented, and the real indoor temperature condition can not be effectively reflected. And after eliminating the abnormal data, calculating average temperature time sequence data corresponding to the floors by utilizing the effective temperature data sequences acquired at each effective monitoring point.
In the embodiment, the effective monitoring point set is determined, the average temperature time sequence data corresponding to the floors is determined by utilizing the effective temperature data sequence acquired at the effective monitoring points in the effective monitoring point set, the influence of abnormal data on the floor comprehensive room temperature calculation is reduced, and the accuracy of the determined floor comprehensive room temperature is improved.
In some embodiments, selecting a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets may include arranging and combining the effective monitoring points included in the effective monitoring point set with one third of the number of the effective monitoring points in the effective monitoring point set as the specified number to obtain a plurality of monitoring point subsets.
Specifically, the number of effective monitoring points in the effective monitoring point set is recorded as m, n effective monitoring points are obtained from the effective monitoring point set to be arranged and combined, and a plurality of monitoring point subsets are obtained. Wherein n is equal to one third of m. Illustratively, if the number of effective monitoring points is 6, a subset of monitoring points is formed with any 2 of the 6 effective monitoring points.
In some embodiments, referring to fig. 4, determining the target subset among the plurality of monitoring point subsets based on first correlation data between the temperature data sequences of the monitoring points in the monitoring point subset and the average temperature time series data, and second correlation data between the temperature data sequences of the monitoring points in the monitoring point subset may include:
S410, determining an average value of first mutual information between the temperature data sequence and the average temperature time sequence data of each monitoring point in the monitoring point subset as first related data of the monitoring point subset.
S420, determining an average value of second mutual information among the monitoring points in the monitoring point subset based on the temperature data sequence of the monitoring points in the monitoring point subset, and taking the average value as second related data of the monitoring point subset.
S430, determining a target subset meeting the preset correlation condition in the plurality of monitoring point subsets according to the average value of the first mutual information and the average value of the second mutual information.
Specifically, a target subset is selected from a number of monitoring point subsets using mutual information (Mutual Information, MI) theory. In each floor, based on the temperature data sequence N fp of each monitoring point in a certain time period and the corresponding floor average temperature time sequence data N rp of the time period, calculating mutual information between the temperature data sequence of each monitoring point and the floor average temperature time sequence data, wherein the calculation formula is as follows:
Wherein N is the total number of data of the average temperature sequence of each floor monitoring point, and when N fp (i, j) =0, the total number is not counted. P F represents the P floor monitoring point.
And calculating an average value of first mutual information between the temperature data sequence and the average temperature time sequence data of each monitoring point in the monitoring point subset to be used as first related data of the monitoring point subset. And calculating an average value of second mutual information among the monitoring points in the monitoring point subset by using the temperature data sequence of the monitoring points in the monitoring point subset, and taking the average value as second related data of the monitoring point subset. And screening the monitoring point subset according to the average value of the first mutual information and the average value of the second mutual information to obtain a target subset meeting the preset correlation condition.
In some embodiments, referring to fig. 5, determining, among the plurality of monitoring point subsets, a target subset that satisfies a preset relevance condition based on the average value of the first mutual information and the average value of the second mutual information may include:
S510, determining target related data of any monitoring point subset based on the average value of the first mutual information of the any monitoring point subset and the average value of the second mutual information of the any monitoring point subset aiming at any monitoring point subset.
S520, determining the monitoring point subset of which the target data meets the maximum relevant minimum redundancy condition as a target subset in a plurality of monitoring point subsets.
The optimal feature subset is selected based on the maximum correlation-minimum redundancy (Minimal Redundancy Maximal Relevance, mRMR) feature method by adopting the mutual information (Mutual Information, MI) theory, so that the selected monitoring points of each floor can ensure that the redundant information and noise contained in the monitoring points are minimized while the beneficial information of the original data set is utilized to the maximum extent, and the monitoring points contained in the selected feature subset are representative monitoring points.
Specifically, a subset S n formed by n (n is less than or equal to m) monitoring points is selected from a feature set F m formed by m monitoring points. According to the maximum correlation principle, the optimal subset S n should be such that the average value of the mutual information of the monitoring point P F and the average temperature P of each floor of the target variable reaches the maximum value, namely
The optimal subset selected according to the maximum correlation principle only has larger redundancy (each monitoring point in the subset has larger correlation), and the constraint condition of the minimum redundancy principle is added to ensure that the average value of mutual information among the monitoring points contained in S n is minimum, namely
Thus, first, mutual information I (P F, P) of each monitoring point temperature P F and each floor average temperature P is calculated, and then, selecting representative monitoring points is performed using the mRMR principle. Specifically, calculateAll arranged in combinationAnd (3) withAnd selecting a combination conforming to the mRMR principle to obtain a target subset S n, namely the combination of the representative monitoring points of each floor. The mRMR principle is:
In the above embodiment, the optimal feature subset is selected from the plurality of sampling monitoring points in each floor of the building by adopting the maximum correlation-minimum redundancy feature selection method, and the features can ensure that the contained redundancy information and noise are minimized while the beneficial information of the original data set is utilized to the maximum, so that the representative monitoring points of the comprehensive room temperature of each floor of the building in the park are effectively searched.
In some embodiments, the method may further include drawing a monitoring point image of the floor based on the representative monitoring points in the target subset.
Specifically, a user monitoring point image may be drawn for each floor. And drawing a monitoring point image of the floor by combining the representative monitoring points in the target subset. Further, rationality representing the selection of monitoring points can be analyzed and appropriately adjusted.
In some embodiments, the representative monitoring point corresponds to a staffing density. The method may further include displaying a marker object corresponding to the person density at a location representative of the monitoring point in the monitoring point image based on the person density corresponding to the representative of the monitoring point.
Different personnel densities can be displayed in the monitoring point image, so that the marking object corresponding to the personnel density is displayed at the position representing the monitoring point according to the personnel density corresponding to the representative monitoring point. In particular, the marking objects may be represented in different colors, and the marking objects may also be represented in different shapes. For example, a room with a lower person density may take the form of a square, and a room with a higher person density may take the form of a circle.
In some embodiments, determining the temperature of the floor based on the temperature data sequence representing the monitoring point in the target subset may include inputting the temperature data sequence representing the monitoring point into a room temperature prediction neural network model corresponding to the floor for prediction to obtain a comprehensive room temperature of the floor.
Wherein different floors may correspond to different room temperature predicted neural network models. Specifically, for different floors, a temperature data sequence representing a monitoring point in the floor is input into a room temperature prediction neural network model corresponding to the floor for prediction, so that the comprehensive room temperature of the floor is obtained.
After each floor is selected to represent a monitoring point, an integrated room temperature model of each floor is built, A Neural Network (ANN) model is adopted, and the temperature P F of each floor representing the monitoring point and the average temperature P of each floor are input for learning and training during training, wherein an error index adopts root mean square error:
Wherein P Fi is the temperature of the representative monitoring point at the moment i, P i is the average floor temperature at the moment i, and N is the number of data points. When the comprehensive room temperature of the floor is calculated, substituting the temperature of the floor representative monitoring point into a trained model, and outputting the comprehensive room temperature of the floor.
In some embodiments, the optimal weight coefficient of each floor representing the monitoring point can be obtained through training of a cuckoo search algorithm by using the temperature P F of each floor representing the monitoring point and the average temperature P of each floor. When the comprehensive room temperature of each floor is calculated, the comprehensive room temperature of each floor can be obtained based on the temperature of the representative monitoring point of each floor and the optimal weight coefficient corresponding to the representative monitoring point of each floor.
In still other embodiments, the weight coefficient for each floor may also be calculated based on the integrated room temperature for each floor, as well as the overall average temperature of the building. Based on the comprehensive room temperature of each floor and the weight coefficient corresponding to each floor, the overall comprehensive room temperature of the building can be obtained.
In the embodiment, the floor comprehensive room temperature obtained through the statistical calculation of the representative monitoring points can be provided with the optimal running decision scheme of the cold and heat source systems of all floors through load prediction, data analysis and running strategy optimization, and the aims of energy conservation and consumption reduction of the whole building, energy conservation and emission reduction of a park and environmental protection are achieved on the premise of effectively ensuring the indoor temperature comfort of a user.
In some embodiments, the monitoring area is partitioned based on identification information of the temperature sensor. The floors correspond to floor categories, and the floor categories are any one of a top layer, an upper middle layer, a lower middle layer, a bottom layer and underground.
Specifically, the plurality of monitoring areas of each floor may be divided according to the floor categories, and the selected representative monitoring points may be representative monitoring points in each floor category. Furthermore, the monitoring areas in each floor category can be further divided according to north-facing, south-facing, central and other characteristic categories, and the selected representative monitoring points can be the representative monitoring points in each characteristic category.
The embodiment of the specification provides a building time-space sequence temperature determining device, and the building includes at least one floor, the floor corresponds to has the temperature monitoring area, the temperature monitoring area is divided into a plurality of monitoring areas, monitoring point has been installed to the monitoring area internally, temperature sensor is installed to monitoring point department. Referring to fig. 6, the building space-time sequence temperature determining device comprises an average temperature determining module, a monitoring point subset forming module, a target subset determining module and a floor temperature determining module.
The average temperature determining module is used for determining average temperature time sequence data corresponding to the floors based on the temperature data sequences acquired at each monitoring point;
The monitoring point subset forming module is used for selecting a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets;
The target subset determining module is used for determining a target subset from the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subsets, wherein the target subset comprises representative monitoring points which can be used for representing the floor temperature;
and the floor temperature determining module is used for determining the temperature of the floor based on the temperature data sequence representing the monitoring points in the target subset.
For specific limitations of the building space-time sequence temperature determination device, reference may be made to the above limitations of the building space-time sequence temperature determination method, and no further description is given here. The modules in the building space-time sequence temperature determining device can be fully or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
The present disclosure also provides an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the building space-time sequence temperature determination method of any one of the preceding embodiments when executing the computer program.
The present description further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the building space-time sequence temperature determination method of any of the preceding embodiments.
It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered as a ordered listing of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include an electrical connection (an electronic device) having one or more wires, a portable computer diskette (a magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of techniques known in the art, discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed, mechanically connected, electrically connected, directly connected, indirectly connected through an intervening medium, or in communication between two elements or in an interaction relationship between two elements, unless otherwise explicitly specified. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. A building space-time sequence temperature determining method is characterized in that the building comprises at least one floor, the floor corresponds to a temperature monitoring area, the temperature monitoring area is divided into a plurality of monitoring areas, monitoring points are arranged in the monitoring areas, temperature sensors are arranged at the monitoring points, and the method comprises the following steps:
determining average temperature time sequence data corresponding to the floors based on the temperature data sequences acquired at each monitoring point;
selecting a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets;
determining a target subset from the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subsets, wherein the target subset comprises representative monitoring points which can be used for representing the floor temperature;
Determining the temperature of the floor based on a temperature data sequence representing monitoring points in the target subset;
The determining a target subset among the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subset and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subset comprises:
Determining an average value of first mutual information between a temperature data sequence of each monitoring point in the monitoring point subset and the average temperature time sequence data as first related data of the monitoring point subset;
determining an average value of second mutual information among monitoring points in the monitoring point subset based on a temperature data sequence of the monitoring points in the monitoring point subset, and taking the average value as second related data of the monitoring point subset;
Determining a target subset meeting a preset relativity condition from the plurality of monitoring point subsets according to the average value of the first mutual information and the average value of the second mutual information;
the determining, based on the average value of the first mutual information and the average value of the second mutual information, a target subset satisfying a preset relevance condition among the plurality of monitoring point subsets includes:
determining target related data of any monitoring point subset aiming at any monitoring point subset based on the average value of first mutual information of the any monitoring point subset and the average value of second mutual information of the any monitoring point subset;
And determining the monitoring point subset of which the target data meets the maximum relevant minimum redundancy condition as the target subset from the plurality of monitoring point subsets.
2. The method of claim 1, wherein determining average temperature timing data for the floor based on the sequence of temperature data collected at each of the monitoring points comprises:
Determining an effective monitoring point set in the monitoring points according to an initial temperature data sequence acquired at each monitoring point, wherein the effective monitoring point set comprises a plurality of effective monitoring points;
And determining average temperature time sequence data corresponding to the floors based on the effective temperature data sequences acquired at each effective monitoring point.
3. The method of claim 2, wherein the selecting a specified number of monitoring points from the monitoring points comprises forming a number of subsets of monitoring points, comprising:
And taking one third of the number of the effective monitoring points in the effective monitoring point set as the appointed number, and arranging and combining the effective monitoring points included in the effective monitoring point set to obtain a plurality of monitoring point subsets.
4. The method according to claim 1, wherein the method further comprises:
and drawing a monitoring point image of the floor based on the representative monitoring points in the target subset.
5. The method of claim 4, wherein the representative monitoring point corresponds to a person density, the method further comprising:
and displaying a mark object corresponding to the personnel density at the position of the representative monitoring point in the monitoring point image based on the personnel density corresponding to the representative monitoring point.
6. The method of claim 1, wherein the determining the temperature of the floor based on the sequence of temperature data representing monitoring points in the target subset comprises:
and inputting the temperature data sequence representing the monitoring point into a room temperature prediction neural network model corresponding to the floor for prediction, and obtaining the comprehensive room temperature of the floor.
7. The method according to any one of claims 1 to 6, wherein the monitoring area is divided according to the identification information of the temperature sensor, and the floor corresponds to a floor category, and the floor category is any one of a top floor, an upper floor, a middle floor, a lower floor, a bottom floor and a ground.
8. The utility model provides a building time-space sequence temperature determination device, its characterized in that, the building includes at least one floor, the floor corresponds has the temperature monitoring area, the temperature monitoring area is divided into a plurality of monitoring areas, monitoring point has been installed to the monitoring area internally, temperature sensor is installed to monitoring point department, the device includes:
The average temperature determining module is used for determining average temperature time sequence data corresponding to the floors based on the temperature data sequences acquired at each monitoring point;
The monitoring point subset forming module is used for selecting a specified number of monitoring points from the monitoring points to form a plurality of monitoring point subsets;
The target subset determining module is used for determining a target subset from the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subsets and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subsets, wherein the target subset comprises representative monitoring points which can be used for representing the floor temperature;
The floor temperature determining module is used for determining the temperature of the floor based on the temperature data sequence representing the monitoring points in the target subset;
The target subset determining module determines a target subset among the plurality of monitoring point subsets according to first related data between the temperature data sequences of the monitoring points in the monitoring point subset and the average temperature time sequence data and second related data between the temperature data sequences of the monitoring points in the monitoring point subset, and specifically comprises the following steps:
Determining an average value of first mutual information between a temperature data sequence of each monitoring point in the monitoring point subset and the average temperature time sequence data as first related data of the monitoring point subset, determining an average value of second mutual information between monitoring points in the monitoring point subset based on the temperature data sequence of the monitoring points in the monitoring point subset as second related data of the monitoring point subset, and determining a target subset meeting a preset relativity condition in the plurality of monitoring point subsets according to the average value of the first mutual information and the average value of the second mutual information;
The target subset determining module determines a target subset meeting a preset relativity condition in the plurality of monitoring point subsets based on the average value of the first mutual information and the average value of the second mutual information, and specifically includes:
And determining target related data of any monitoring point subset based on the average value of the first mutual information of the any monitoring point subset and the average value of the second mutual information of the any monitoring point subset, and determining the monitoring point subset with the target data meeting the maximum related minimum redundancy condition as the target subset in the plurality of monitoring point subsets.
9. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211738300.0A CN116255705B (en) | 2022-12-30 | 2022-12-30 | Method, device, electronic device and storage medium for determining building spatiotemporal temperature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211738300.0A CN116255705B (en) | 2022-12-30 | 2022-12-30 | Method, device, electronic device and storage medium for determining building spatiotemporal temperature |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116255705A CN116255705A (en) | 2023-06-13 |
| CN116255705B true CN116255705B (en) | 2025-09-12 |
Family
ID=86681848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211738300.0A Active CN116255705B (en) | 2022-12-30 | 2022-12-30 | Method, device, electronic device and storage medium for determining building spatiotemporal temperature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116255705B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119063221B (en) * | 2024-10-09 | 2025-04-25 | 上海直真空点信息技术有限公司 | Building energy-saving control processing method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114757096A (en) * | 2022-04-02 | 2022-07-15 | 华南理工大学 | Bridge temperature prediction method, device, equipment and medium based on NARX neural network |
| CN115510767A (en) * | 2022-11-21 | 2022-12-23 | 四川省气象服务中心(四川省专业气象台 四川省气象影视中心) | Regional air temperature prediction method based on deep space-time network |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10895523B2 (en) * | 2015-04-30 | 2021-01-19 | The University Of Connecticut | Method of optimal sensor selection and fusion for heat exchanger fouling diagnosis in aerospace systems |
| CN107948262A (en) * | 2017-11-15 | 2018-04-20 | 成都正光恒电子科技有限责任公司 | Intelligent greenhouse management system based on Internet of Things |
| CN108564009A (en) * | 2018-03-28 | 2018-09-21 | 天津大学 | A kind of improvement characteristic evaluation method based on mutual information |
| US11487739B2 (en) * | 2019-02-19 | 2022-11-01 | Nasdaq, Inc. | System and methods for data model detection and surveillance |
| US11763198B2 (en) * | 2019-10-08 | 2023-09-19 | Nec Corporation | Sensor contribution ranking |
| CN112989529B (en) * | 2021-02-05 | 2024-01-30 | 河北农业大学 | Henhouse temperature sensor arrangement optimization method based on genetic algorithm |
| CN113108921B (en) * | 2021-04-19 | 2023-11-24 | 巴斯夫新材料有限公司 | Methods, devices and systems for monitoring the temperature of objects |
| CN113468157B (en) * | 2021-07-12 | 2024-04-26 | 博锐尚格科技股份有限公司 | Similar building selection method and device based on energy consumption analysis |
| CN115112264A (en) * | 2022-06-24 | 2022-09-27 | 国家粮食和物资储备局科学研究院 | A single-point temperature prediction method based on improved GRU grain pile |
-
2022
- 2022-12-30 CN CN202211738300.0A patent/CN116255705B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114757096A (en) * | 2022-04-02 | 2022-07-15 | 华南理工大学 | Bridge temperature prediction method, device, equipment and medium based on NARX neural network |
| CN115510767A (en) * | 2022-11-21 | 2022-12-23 | 四川省气象服务中心(四川省专业气象台 四川省气象影视中心) | Regional air temperature prediction method based on deep space-time network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116255705A (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kamel et al. | Data-driven predictive models for residential building energy use based on the segregation of heating and cooling days | |
| Zhang et al. | A systematic feature selection procedure for short-term data-driven building energy forecasting model development | |
| Yan et al. | The performance prediction of ground source heat pump system based on monitoring data and data mining technology | |
| Rylatt et al. | GIS-based decision support for solar energy planning in urban environments | |
| Cheng et al. | Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines | |
| CN104025131B (en) | Utilize layout strategy analysis and the system and method for design building structure | |
| KR102519975B1 (en) | Eco-friendly building simulation system and co-friendly building design method for reducing energy costs | |
| CN102844773B (en) | Based on building energy-saving unit and the system of interactive learning | |
| CN110264080A (en) | A kind of green building runnability evaluation method, device, equipment and storage medium | |
| CN113435657A (en) | Data integration processing method, system, energy management system, electronic device and computer readable storage medium | |
| Diakaki et al. | Performance study of a multi-objective mathematical programming modelling approach for energy decision-making in buildings | |
| Alsharif et al. | A review of building parameters’ roles in conserving energy versus maintaining comfort | |
| CN112241607A (en) | A simulation-based approach to water resources planning that takes into account climate change | |
| CN114925874A (en) | Carbon emission pre-judging method and device based on BERT neural network model | |
| CN120103768B (en) | A method and system for information collection and control of port energy-using equipment | |
| CN114909707A (en) | Heat supply secondary network regulation and control method based on intelligent balancing device and reinforcement learning | |
| CN116255705B (en) | Method, device, electronic device and storage medium for determining building spatiotemporal temperature | |
| Hong et al. | A target-driven decision-making multi-layered approach for optimal building retrofits via agglomerative hierarchical clustering: A case study in China | |
| CN118229107B (en) | A method and system for evaluating energy consumption of public institutions | |
| CN119620632A (en) | Hotel energy consumption monitoring and management system based on big data | |
| Loikkanen et al. | Multicriteria evaluation of sustainable energy solutions for Colosseum | |
| CN120124494A (en) | A big data information processing method and system based on deep learning | |
| AlFaris et al. | Using integrated control methodology to optimize energy performance for the guest rooms in UAE hospitality sector | |
| CN115879190A (en) | Model building method and device, building load forecasting method and device | |
| CN119939700A (en) | A green building information integrated management method and system based on BIM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |