KR20170089549A - System and method for managing bid based on intelligent demand response - Google Patents

Abstract

The present invention relates to an intelligent demand response bid management system and a method thereof. In particular, a reducible resource capacity is intelligently calculated for a customer desiring a bid, and a bid strategy capable of maximizing earnings is automatically produced. Moreover, according to the present invention, the intelligent demand response bid management system comprises: a data storage for storing past electricity usage information of a customer; an intelligent energy analysis engine for extracting a usage pattern by using the past electricity usage information stored in the data storage, and performing demand prediction on the basis of the extracted usage pattern; and a process module for performing a bid by generating a bid strategy by using the usage pattern and the demand prediction of the customer. Bid participants can easily respond to a demand response bid.

Description

[0001] The present invention relates to an intelligent demand response bidding management system, and more particularly,

The present invention relates to a demand response bidding management system and method, and more particularly, to an intelligent demand response bidding management system that intelligently estimates reducible resource capacity for a bidding customer and automatically generates a bidding strategy capable of maximizing profit And a method thereof.

Demand Response Management Businesses are divided into Reliable Demand Response and Economical Demand Response, each with differentiated bidding method and transaction process.

As of March 2015, the ratio of occurrence of reliability demand response (3 times) and economical demand response (41 times) is about 1:13. Economy Demand response business is getting bigger, economy is stronger in demand response business It is necessary to introduce differentiated technologies.

The most economical demand response agency business follows the manual type economical demand response agent service system format of Figure 1 in most cases.

Manual-based economics Demand response service systems require a lot of manual work by operators and bidders and depend entirely on operator expertise to build effective bid strategies.

This economic demand response business attracts individual business operators such as kt, Byucksan, and Enernoc as members, and acts as an intermediary between individual and KPX.

To operate the demand reaction system that each company has, manual operation of a specialist with knowledge of energy management is required.

Operators should also constantly monitor when the SMP (power market price) is high and configure optimal bidding strategies that maximize revenue for each individual customer based on SMP and CBL.

At this time, since there is no analytical technology capable of precisely predicting the usage amount of the customer, it is inevitable to estimate the savings by predicting only on the basis of CBL.

CBL is based on a simple average for each hour of 6 days, so the actual customer usage prediction accuracy is poor.

In addition, the operator re-groups the bidders scattered over several time zones to bid on the final power exchange so as to be competitive bidding (sufficient reduction).

At this time, it is necessary to strategically group them in consideration of the situation of individual customers, but the present system does not have such a function.

On the other hand, the current system should input the amount of time and amount that can be directly reduced by customers who want to bid. As a result, maximizing profits can not be achieved because there is no prior knowledge of the time to maximize profits or the amount that can reasonably be reduced.

In addition, it is more dependent on the operator to receive feedback on the bid strategy.

Demand Response Most customers have power plants, but their power plant operation schedules based on customers' savings inputs have to be coordinated entirely by customers.

Thus, the conventional economical demand response system requires direct involvement of many energy management experts and customers in constructing the operation and bid plan.

Prior Art 1: KR Patent Publication No. 2014-0069737 Prior Art 2: KR Patent Publication No. 2012-0000116 Prior Art 3: KR Patent Publication No. 2002-0066654

According to an aspect of the present invention, there is provided a data storage system, comprising: a data store storing past power usage information of a customer; An intelligent energy analysis engine that extracts a usage pattern from past power usage information of a customer stored in the data store and performs demand prediction based on the extracted usage pattern; And a processing module for generating a bid strategy using the customer usage pattern and demand forecast to perform bidding.

According to an embodiment of the present invention, the data storage stores past weather information, and the intelligent energy analysis engine associates and analyzes past power usage information of a customer stored in the data store with past weather information, .

Also, the intelligent energy analysis engine according to an aspect of the present invention performs demand forecasting using Equation (1) below based on the extracted usage pattern.

(1)

Y _D = β ₁ Y _D-21- β ₂ Y _D-14- β ₃ Y _D-7 +

Where Y is the energy demand, D is the day of use and β is the weighting factor.

In addition, the intelligent energy analysis engine according to an aspect of the present invention reduces the weighting coefficient from the present to a far distance from the present, and is differently applied to each business type.

The intelligent energy analysis engine according to an embodiment of the present invention calculates a point of time when the power consumption is below an average value through demand forecasting and the processing module proposes to artificially increase the usage amount at a time when the power consumption is below the average value And an operation schedule recommendation module.

The intelligent energy analysis engine according to an aspect of the present invention classifies customers having similar consumption patterns into a plurality of groups and classifies customers in each group into biddable customers with a fixed-time bidding customer in a fluid manner, Group bidding by grouping the bidding time points of the individual customers in the group and adjusting the bidding amount of the customers in the group using the customer subdivisions classified by the intelligent energy analysis engine, Strategy module.

In addition, the group bid strategy module according to an aspect of the present invention performs re-grouping with another group in another time zone when the group is not collected with a certain amount of savings even if grouping is performed.

In addition, the processing module of one aspect of the present invention includes: a customer portfolio creation module for generating a customer portfolio using past past power usage information, usage pattern, and demand forecast information; And a customer portfolio management module for updating the customer portfolio.

In addition, the processing module of one aspect of the present invention includes a customer profit prediction module that calculates sales revenue using the SMP unit price on the bidding day and allows the customer to decide whether to final bid.

Also, the intelligent energy splitting engine according to an aspect of the present invention recommends a time point when a demand response bidding is reversed when idle power remaining in the facility is generated.

According to another aspect of the present invention, there is provided an intelligent energy analysis engine, comprising: (A) an intelligent energy analysis engine extracting a usage pattern from past power usage information of a customer and performing a demand prediction based on the extracted usage pattern; And (B) the processing module generates a bid strategy using the customer's usage pattern and demand forecast to perform the bid.

Further, in the step (A) of another aspect of the present invention, the intelligent energy analysis engine extracts a usage pattern by correlating past past power usage information with past weather information.

Further, the intelligent energy analysis engine of another aspect of the present invention performs demand forecasting using Equation 1 below based on the extracted usage pattern.

(1)

Y _D = β ₁ Y _D-21- β ₂ Y _D-14- β ₃ Y _D-7 +

Where Y is the energy demand, D is the day of use and β is the weighting factor.

According to another aspect of the present invention, (C) the intelligent energy analysis engine includes: calculating a time point at which power consumption is below an average value through demand prediction; And (D) the processing module includes a step of artificially increasing the amount of usage to a customer at a time when the power consumption is below the average value.

According to another aspect of the present invention, (E) the intelligent energy analysis engine includes the steps of: classifying customers having similar consumption patterns into a plurality of groups; (F) the intelligent energy analysis engine classifying the customers in each group into biddable customers with a fixed-time bidding customer; (G) coordinating the bidding time and the bidding amount of the individual customers in the group using the plurality of groups classified by the intelligent energy analysis engine and the customer detail classification in the group; And (H) the processing module further comprises performing group bidding by unifying bidding points of customers in the group.

In another aspect of the present invention, there is provided a method for processing a program, the method comprising the steps of: (I) after the step (G), if the processing module performs grouping, .

According to another aspect of the present invention, there is provided a method for managing customer information, comprising the steps of: (J) generating a customer portfoly by using the customer's past power usage information, usage pattern, and demand forecast information; And (K) the processing module updating the customer portfolio.

According to another aspect of the present invention, (L) the intelligent energy distribution engine further includes a step of recommending a demand reaction bid time when idle power remaining in the facility is generated.

SUMMARY OF THE INVENTION Accordingly, the present invention has been made to solve the above problems, and an intelligent demand response bidding management system that intelligently estimates a reducible resource capacity to a customer wishing to bid and automatically generates a bid strategy capable of maximizing profit, .

In accordance with the present invention, a variety of analysis algorithms can be tailored to individual optimized bidding strategies (efficient CBL management, reasonable savings and bidding time), allowing customers to return maximum sales revenue and achieve higher commissions.

According to the present invention, bidders having a similar power consumption pattern are grouped and grouped into a group so that the DR bidding can have sufficient competitiveness to become a winning bid, and the bidding time is reasonably unified .

In addition, according to the present invention, the convenience and reliability of the customer are increased because the profit is increased and unnecessary direct intervention is mostly eliminated.

Also, according to the present invention, the labor cost of the operation management expert is reduced due to the automation of the operation management.

Further, according to the present invention, it is possible to manage individual customers by continuously creating individual portfolios, and automatically updating customer feedback or changes when they occur.

Further, according to the present invention, when the amount of power generated by the energy facility exceeds the expected demand value (30% or more), economical DR participation can be recommenced to secure profit.

Further, according to the present invention, it is possible to automate the operation scheduling of a power generation facility owned by a customer who can provide savings according to the target reduction amount of the customer, thereby assuring that the customer can achieve the reduction target with certainty, The failure rate can be lowered.

1 is a conceptual diagram of a prior art DR based bidding system.
2 is a conceptual diagram of an intelligent demand response bidding management system according to the present invention.
3 is a detailed block diagram of an intelligent demand response bidding management system according to a preferred embodiment of the present invention.
4 is a conceptual diagram of a group bid management method according to the present invention.
5 is a flowchart of a method for managing intelligent demand response bids according to a preferred embodiment of the present invention.
FIG. 6 is a flowchart of a bid management process for each group in FIG.
7 is a flowchart of a CBL efficiency management method used in the present invention.
8 is a flowchart of a portfolio making process used in the present invention.
9 is a flowchart of a power generation facility operation schedule and DR bid schedule recommendation process used in the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments will be described in detail below with reference to the accompanying drawings.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various components, but the components are not limited by the terms, and the terms are used only for the purpose of distinguishing one component from another Is used.

2 is a conceptual diagram of an intelligent demand response bidding management system according to the present invention.

Referring to FIG. 2, the intelligent demand response bidding management system according to the present invention includes a scheduling system for scheduling generation facility operation by presenting a time zone and a reduction amount capable of maximizing profit per individual customer, CBL efficiency, And so on.

For this purpose, the intelligent demand response bidding management system makes sophisticated demand forecasts in units of hours / days / weeks using the data mining algorithm based on the customer's past power usage data, Is automatically set as a reduction amount to form a bid strategy.

In addition, the intelligent demand response bidding management system systematically manages a DR portfolio for each customer, and automatically updates the current status of use of the electric power, bidding information, facilities, and the like when a change occurs.

As described above, according to the present invention, it is possible to reduce costs by being convenient to operate and substitute professional manpower, maximizing the profit of the customer, thereby increasing the DR agency commission and improving the reliability of the customer's service.

3 is a detailed block diagram of an intelligent demand response bidding management system according to a preferred embodiment of the present invention.

3, an intelligent demand response bidding management system according to an exemplary embodiment of the present invention includes an intelligent energy analysis engine 100 for providing various analysis functions, a processing module 200 and a data storage 400 have.

The processing module 200 includes a trust customer selection module 210, a customer characteristic extraction module 220, a customer portfolio creation module 230, a customer optimal bid strategy module 240, Module 250, a facility operation schedule recommendation module 260, an external interlock module 270, a customer feedback processing module 280, a customer portfolio management module 290, a customer bidder creation module 300, A customer profit prediction module 310, and a bid module 320.

The data store 400 includes a customer portfolio database 410, a weather information database 420, and a power market information database 430.

In this configuration, the intelligent energy analysis engine 100 analyzes the customer pattern by extracting regular and distinct power consumption patterns based on the past power usage data of the customer.

Then, the intelligent energy analysis engine 100 predicts the future use of power in a time / day / week basis based on the extracted customer pattern, and performs demand prediction analysis.

This demand forecasting analysis extracts and predicts patterns based on data for the past three weeks.

For example, the power usage forecast for Monday is calculated using only data from Monday for the past three weeks.

The prediction equation is shown in Equation 1 below. The weighting factor decreases with the distance from the present, and this weighting coefficient is applied differently for each business type (factory, hotel, hospital, etc.).

The demand forecasting formula shown in the following Equation 1 is more accurate than the CBL of other companies that use the average of the past past ten coincidences by reflecting the use pattern subdivided by the day of the week.

(1)

Y _D = β ₁ Y _D-21- β ₂ Y _D-14- β ₃ Y _D-7 +

Where Y is energy demand, D is the day of use, and? Is a weighting factor.

Meanwhile, the intelligent energy analysis engine 100 performs a meteorological fusion analysis for analyzing an association pattern by fusing past past power usage data and past weather information.

In addition, since the intelligent energy analysis engine 100 generates revenue based on the difference between the CBL and the actual amount of electric power, if the customer desires to bid in advance (7 to 5 days before), the electric power consumption We propose to artificially increase the amount of usage at the point where the average value drops significantly, and perform the CBL efficiency analysis that raises the overall CBL.

For example, the intelligent energy analysis engine 100 suggests that when the CBL efficiency level is predicted to be significantly low, do not use the power generation facilities on the previous day, and use the electric power supplied by KEPCO. (However, The cost of artificially consumed power use is lower than expected revenues from DR participation).

The intelligent energy analysis engine 100 performs facility operation scheduling for efficiently analyzing an operation schedule of an electric power generation facility in order to maximize savings when a usage pattern of the user and a corresponding optimal savings amount according to a demand forecast are determined.

Also, the intelligent energy analysis engine 100 analyzes the operation schedule of the power generation facilities to artificially raise the CBL through the CBL efficiency analysis.

Also, the intelligent energy analysis engine 100 can automatically obtain the revenue by recommending the economical DR bid to the customer when the amount of power charged to the power generation facility is more than + 30% It does.

In addition, the intelligent energy analysis engine 100 needs to be competent enough to win the DR bidding. For this purpose, the bidders are grouped into a group, and the bidding times of the bidders are unified to some extent, The customer grouping operation is performed.

In this regard, referring to FIG. 4, the intelligent energy analysis engine 100 first classifies groups having similar consumption patterns for a customer grouping operation. If you categorize groups with similar consumption patterns, bidding management is similar because bidding patterns are similar.

Then, the intelligent energy analysis engine 100 analyzes the past bidding pattern for the customer grouping operation, and classifies the customer who is allowed to bid only at a fixed time and the customer who can bid at a fixed time.

This sorting ensures the reliability of the savings implementation because it considers the customer situation.

In addition, the intelligent energy analysis engine 100 repeatedly combines the various time zone unification criteria for the customer grouping operation so as to be optimized according to the demand situation of each customer.

On the other hand, the trusted customer selection module 210 utilizes the customer reliability analysis function of the intelligent energy analysis engine 100 to determine whether the usage patterns are sufficiently regular and to operate the economical demand response bidding pool based thereon.

The customer characteristic extraction module 220 derives the usage pattern from the past data of the customer by utilizing the customer pattern analysis, the demand prediction analysis and the weather information fusion analysis function of the intelligent energy analysis engine, and based on the time / day / week unit The demand forecasting information is generated.

Next, the customer portfolio creation module 230 generates the customer's past power usage information, the characteristics of the usage pattern, the prediction information of the time / day / week unit, the real-time CBL information, the customer's facility operation schedule information, We synthesize and make a portfolio.

If the customer desires to bid 5 to 7 days before the bid, the customer optimal bid strategy module 240 calculates the time point when the corresponding demand forecast amount is lower than the CBL standard by 10% or more in real time every day from the day onwards until the end of the bid And 10% ~ 30% as the savings according to the customer type (whether or not the power plant is available).

In addition, the CBL efficiency analysis function of the intelligent analysis engine allows the customer to artificially increase the amount of usage at the point where the power consumption is predicted to be much lower than the cumulative average, thereby raising the overall CBL.

Meanwhile, the bid management module 250 for each group provides an optimal bid strategy for each customer. However, in order to increase the final bid rate, a strategy of bidding by combining the savings of individual customers by group is required. The bidders of similar power consumption patterns are classified into groups, and the bidding plans of individual customers within each group are coordinated based on the personal portfolio and the existing optimal bidding strategy to unify the bidding points to some extent.

Then, the bid management module 250 for each group combines the savings of the unified customers, and then bids them on a group basis to guarantee a high winning rate.

Next, the facility operation schedule recommendation module 260 determines whether the customer has a power generation facility (most of the customers of the demand management business in kt have the power generation facility). In order to secure the proposed reduction amount at the time of bidding, The optimal operation time is recommended by utilizing the facility operation scheduling function.

 In addition, when the amount of power charged to the power generation facility is more than + 30% more than the expected demand value within 1 ~ 2 days, it can automatically recommend the economic DR bidding to customers and secure the profit.

Meanwhile, the external interworking module 270 fetches real-time power usage information, SMP unit price, power market information such as a bid, weather information, and the like from an external system in real time.

Next, the customer feedback processing module 280 re-adjusts the bid strategy and the facility operation schedule to reflect the customer's feedback on the optimal bid plan proposed by the system.

In addition, the customer portfolio management module 290 periodically manages the customer portfolio, and automatically updates the status of real-time customer power usage, bid information, facilities, and the like when they occur.

Next, when the customer accepts the bid strategy proposed by the system, the client bid module 300 automatically generates a bid book reflecting the related bid information.

Then, the customer profit prediction module 310 calculates the sales revenue using the SMP unit price of the bid day, and the customer decides whether or not to final bid.

Next, the bidding module 320 groups the time-based bidders through the analysis of the customer grouping of the intelligent energy analysis engine so that the system can be competitive so that the DR bid can be won, Grouping with other groups in the nearest time zone and bidding to the final power exchange.

Meanwhile, the customer portfolio database 410 of the data store 400 stores real-time power usage information, usage patterns and prediction information of customers, bidding information, power generation facility information, and the like.

The power market information database 420 stores power market information such as real-time SMP unit price, past bids, and winning status.

The weather information database 430 stores real-time weather information by region.

The operation of the intelligent demand response bidding management system according to an embodiment of the present invention constructed as above will be described with reference to a flowchart of the intelligent acceptance response bidding method of FIG.

First, the trusted customer selection module 210 utilizes the customer reliability analysis function of the intelligent energy analysis engine 100 to determine whether the usage pattern is sufficiently regular, selects the reliable customers based on the usage pattern, The reaction bidding pool is operated (SlOO).

When the customer corresponding to the demand response bidding pool (poo) requests a bid for the intelligent demand response bidding management system, the customer characteristics extracting module 220 analyzes the customer pattern analysis of the intelligent energy analysis engine 100, And a meteorological information fusion analysis function to derive a usage pattern from the customer's past data and generate demand forecast information on a time / day / week basis based on the usage pattern (S110).

If the customer desires to bid 5 to 7 days before the bid, the customer optimal bid strategy module 240 determines the time point at which the corresponding demand forecast amount is lower than the CBL standard by 10% or more on a daily basis from the day after the application date to the end of the bid, , And 10% ~ 30% is calculated as the savings based on the customer type (whether or not the power plant is available).

In addition, the customer optimal bidding power module 240 proposes to artificially increase the amount of consumption at a point of time when the power consumption is predicted to be much lower than the cumulative average through the CBL efficiency analysis function of the intelligent energy analysis engine 100, So that it can be uploaded.

Meanwhile, the customer profit prediction module 310 calculates the expected profit based on the SMP at the time of the bidding.

The customer optimal bidding power module 240 generates bidding power for each customer based on the bidding time and the amount of reduction thus calculated and the estimated profit of the customer profit prediction module 310 to propose to the customer, .

That is, the customer optimal bidding power module 240 calculates the bidding time, the reduction amount, and the estimated profit based on the demand forecast information according to the usage pattern of the customer, thereby creating the best bidding strategy for each customer (S120).

Next, the facility operation schedule recommendation module 260 determines whether the customer has a power generation facility (most of the customers of the demand management business in kt have the power generation facility). In order to secure the proposed reduction amount at the time of bidding, The optimal operation time is recommended by utilizing the facility operation scheduling function.

At this time, the customer feedback processing module 280 re-adjusts the bid strategy and the facility operation schedule by reflecting the customer's feedback on the bid plan proposed by the customer's optimal bidding power module 240 (S130).

Then, the bid strategy module 250 for each group performs bid management for each group (S140).

The bidding management process for each group will be described using the bidding management flowchart of FIG. 6 as follows.

First, the intelligent energy analysis engine 100 analyzes the customer demand pattern (S200) when the bidding power of the individual customer is configured, and groups similar customers on the basis of the recent one to two weeks and classifies them into a plurality of groups (S210). The reason for this classification is that customers with similar consumption patterns are likely to have similar bidding strategies.

In addition, the intelligent energy analysis engine 100 performs customer subcategorization in a group as a customer who has a customer who has to bid only at a fixed point of time, .

At this time, the intelligent energy analysis engine 100 analyzes the current state of the customer's power generation facility, the customer strategy use history, the customer's reaction history, the bid history, Customer demand prediction information, and the like.

As described above, the group-specific bidding power module 250 adjusts the bidding time and the bidding amount of the individual customers in each group when the customer in-group classification is completed (S230).

The reason why the existing individual customers need to adjust the bidding time and the reduction amount is that the bidding should be done by collecting sufficient savings for each group, and the time and amount of adjustment should not significantly hinder the individual customer's expected bid profit do.

Various criteria elements are reflected in the selection of the optimal bid time by the bid strategy module 250 for each group, and the reflected reference elements include customers' portfolio and external information (time-based SMP information, past time-zone winning rate, etc.).

That is, the following reference elements 1) to 6) are considered.

One. High SMP time zone

2. Time zone with high winning rate and minimum saving

3. Time zones selected by high-value customers in the group: Customer confidence and best customers can be judged based on past bid performance and bidding savings, and can be based on bidding time of these customers

4. Time zones selected by a large number of customers within the group: can be based on the number of times customers have bid in the group

5. Fixed-point + 1 hour can be adjusted for customers in a group that can only bid at fixed time. If the time is adjusted, final target savings can also be changed based on existing demand forecast. Considering this, even if adjusted to the existing expected profit, there should be no significant fluctuation.

6. Customers in the group who can bid with liquidity due to power generation facilities comprehensively judge 1, 2, 3, 4, and tune to the point where the winning bid rate is high and the maximum profit is possible. If these customers are tuned to their expected revenue, they should not change very much.

Meanwhile, the group-specific bid strategy module 250 repeatedly combines the reference elements (1, 2, 3, 4, 5, 6) repeatedly to determine the high probability of winning and the individual (3) to (5), the bidding time point of the customers in the group is unified according to the overall profitability of the customers (S240).

In the case of a group in which a sufficient amount of savings has not been collected even if grouping is performed, the bid strategy module 250 per group performs re-grouping by combining with other clusters in the closest time zone (S250).

The group-specific bidding power module 250 informs the customer who has changed the existing bidding plan and receives the final approval (S260). It shows you why it was tuned, along with details.

It is also possible to intuitively identify the change in the expected profit of the customer according to the winning bid probability (based on the success rate of the past winning bid data) and the bid time, Let them choose.

For those customers who can only bid at fixed times, only one or two tune-up bidding points are presented. However, customers with flexible bidding can offer a wide range of tune-up time points.

Through the above process, the bidding strategy module 250 for each group can cancel the bidding or directly input the bidding to the bidding point adjustment step of individual customers in each group. When the customer makes a final approval, the bidding is completed for each group (S150).

In other words, the bidder creates a bid document using the customer bidder creation module 300, and proceeds to the power exchange bid through the bid module 310.

Meanwhile, as shown in FIG. 7, the facility operation schedule recommendation module 260 starts CBL efficiency management up to 7 days after the request for a request when a request for bidding of a customer occurs (S300).

The facility operation schedule recommendation module 260 suggests a method of artificially increasing the CBL when the demand forecast value at a specific point of time is measured 30% lower than the predicted average of 7 days (S310).

For example, the facility operation schedule recommendation module 260 provides a plan for the customer having a power generation facility, such as "Do not start the power generation facility the day before at that time, (However, the cost of artificially consumed electric power is lower than expected revenues from DR participation).

Thus, if the customer follows the recommendation of the facility operation schedule recommendation module 260, the CBL value increases and the actual DR compensation increases.

Next, the customer portfolio creation module 230 creates a customer portfolio. Referring to FIG. 8, a customer-specific portfolio is created (S400).

Then, the customer portfolio creation module 230 writes the customer's power generation facility, business size, type, and place in the portfolio (S410).

Next, the customer portfolio creation module 240 writes the customer's power generation facility operation schedule into the portfolio (S420).

In addition, the customer portfolio creation module 240 fetches the customer's power usage data from the ISmart system of KEPCO in real time through the external interworking module 270 and records it in the portfolio (S430).

Next, the customer portfolio creation module 240 records the consumption patterns extracted based on the customer's past power usage data from the customer characteristics extraction module 220 in the portfolio (S440).

In addition, the customer portfolio creation module 240 records the CBL calculated every time based on the past power usage amount in the portfolio by the customer characteristic extraction module 220 (S450).

In addition, the customer portfolio creation module 240 records in the portfolio each time the customer makes a bid, and records the success and the secured profit in the portfolio (S460).

Next, the customer portfolio management module 290 updates the customer portfolio every time the related information is newly changed (S470).

On the other hand, the customer optimal bid strategy module 240 performs a power generation facility operation schedule and DR bid timing recommendation. Referring to FIG. 9, the customer optimal bid strategy module 240 determines a bid timing and a reduction amount of a customer (S500).

Then, the customer optimal bid strategy module 240 reads the existing facility schedule from the customer's portfolio (S510).

Next, the customer optimal bid strategy module 240 adjusts the operation schedule of the power generation facility from -1 day to +1 day at the bidding time of the customer (S520).

By adjusting the operation schedule, the customer can secure the savings by producing the own power through the operation of the power generation facility.

On the other hand, when the amount of electric power charged to the power generation facility is more than + 30% higher than the demand forecast value within 1 to 2 days, the intelligent energy analysis engine 100 automatically recommends the customer to the DR (S530).

In accordance with the present invention, a variety of analysis algorithms can be tailored to individual optimized bidding strategies (efficient CBL management, reasonable savings and bidding time), allowing customers to return maximum sales revenue and achieve higher commissions.

According to the present invention, bidders having a similar power consumption pattern are grouped and grouped into a group so that the DR bidding can have sufficient competitiveness to become a winning bid, and the bidding time is reasonably unified .

In addition, according to the present invention, the convenience and reliability of the customer are increased because the profit is increased and unnecessary direct intervention is mostly eliminated.

Also, according to the present invention, the labor cost of the operation management expert is reduced due to the automation of the operation management.

Further, according to the present invention, it is possible to manage individual customers by continuously creating individual portfolios, and automatically updating customer feedback or changes when they occur.

Further, according to the present invention, when the amount of power generated by the energy facility exceeds the expected demand value (30% or more), economical DR participation can be recommenced to secure profit.

Further, according to the present invention, it is possible to automate the operation scheduling of a power generation facility owned by a customer who can provide savings according to the target reduction amount of the customer, thereby assuring that the customer can achieve the reduction target with certainty, The failure rate can be lowered.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. And changes may be made without departing from the spirit and scope of the invention.

100: intelligent energy analysis engine 200: processing module
210: Trusted customer selection module 220: Customer characteristic extraction module
230: customer portfolio creation module 240: customer optimal bid strategy module
250: Bid strategy module per group 260: Equipment operation schedule recommendation module
270: external interlock module 280: customer feedback processing module
290: Customer Portfolio Management Module 300: Passbook Tender Production Module
310: Customer Revenue Forecasting Module 320: Bidding Module
400: Data Store 410: Customer Portfolio Database
420: weather information database 430: electric power market information database

Claims (18)

A data store that stores past historical power usage information;
An intelligent energy analysis engine that extracts a usage pattern from past power usage information of a customer stored in the data store and performs demand prediction based on the extracted usage pattern; And
And a processing module for generating a bid strategy by using the customer's usage pattern and demand forecast to perform bidding. The method according to claim 1,
The data store stores past weather information,
Wherein the intelligent energy analysis engine extracts a usage pattern by associating and analyzing past power usage information of a customer stored in the data store with past weather information. The method according to claim 1,
Wherein the intelligent energy analysis engine performs demand forecasting using Equation (1) based on the extracted usage pattern.
(1)
Y _D = β ₁ Y _D-21- β ₂ Y _D-14- β ₃ Y _D-7 +
Where Y is the energy demand, D is the day of use and β is the weighting factor. The method according to claim 3,
The intelligent energy analysis engine makes the weighting factor lower as the past is farther away from the present, and applies differently for each business type. The method according to claim 1,
The intelligent energy analysis engine calculates a time point at which the power consumption is below an average value through demand forecasting,
Wherein the processing module includes a facility operation schedule recommendation module that suggests that the usage amount is artificially increased at a time when a power consumption amount is below an average value to a customer. The method according to claim 1,
The intelligent energy analysis engine classifies customers having similar consumption patterns into a plurality of groups, classifies the customers in each group into biddable customers with a fixed-time bidding customer,
The processing module uses a plurality of groups classified by the intelligent energy analysis engine to classify the bidding time and the amount of reduction of the individual customers in the group to classify the bidding time points of the customers in the group, And a bid strategy module for each group. The method of claim 6,
The bid strategy module for each group performs re-grouping with another group in another time zone if the group is not collected in a certain amount of savings even if grouping is performed. The method of claim 6,
The processing module
A customer portfolio creation module for generating a customer portfolio by using the customer's past power usage information, usage pattern, and demand forecast information; And
And a customer portfolio management module for updating the customer portfolio. The method of claim 6,
The processing module
An intelligent demand response bidding system that includes a customer revenue prediction module that calculates the sales revenue using the SMP unit price on the bidding day and allows the customer to decide whether to final bid. The method according to claim 1,
The intelligent energy distribution engine is an intelligent demand response bidding management system that recommends bid response times when idle power is generated while equipment is operated. (A) an intelligent energy analysis engine extracting a usage pattern from past power usage information of a customer and performing a demand prediction based on the extracted usage pattern; And
(B) the intelligent demand response bidding method, wherein the processing module generates a bid strategy using the customer's usage pattern and demand forecast to perform a bid. 12. The method of claim 11,
Wherein the intelligent energy analysis engine extracts a usage pattern by associating and analyzing past power usage information of a customer with past weather information in step (A). 12. The method of claim 11,
Wherein the intelligent energy analysis engine performs demand forecasting using Equation (1) based on the extracted usage pattern.
(1)
Y _D = β ₁ Y _D-21- β ₂ Y _D-14- β ₃ Y _D-7 +
Where Y is the energy demand, D is the day of use and β is the weighting factor. 12. The method of claim 11,
(C) the intelligent energy analysis engine calculating a time point at which the power consumption is below an average value through demand forecasting; And
(D) The process module proposes to artificially increase the amount of usage at a time when the power usage is below the average value. 12. The method of claim 11,
(E) the intelligent energy analysis engine classifying customers having similar consumption patterns into a plurality of groups;
(F) the intelligent energy analysis engine classifying the customers in each group into biddable customers with a fixed-time bidding customer;
(G) coordinating the bidding time and the bidding amount of the individual customers in the group using the plurality of groups classified by the intelligent energy analysis engine and the customer detail classification in the group; And
(H) The intelligent demand response bidding method further comprises the step of unifying the bidding time of customers in the group to perform the group bidding. The method of claim 15,
After the step (G)
(I) performing the re-grouping with another group in another time zone if the processing module is a group that does not collect more than a predetermined amount even if grouping is performed. 12. The method of claim 10,
(J) generating the customer portfoly using the past power usage information, usage pattern, and demand forecast information of the customer; And
(K) the intelligent demand response bid management method further comprising the processing module updating a customer portfolio. 12. The method of claim 10,
(L) The intelligent demand response bidding method further includes a step of recommending a demand response bidding time when the idle power remaining in the intelligent energy distribution engine is generated while the facility is operated.

Images