Demand response potential assessment method and device, computer equipment, readable storage medium and program product
By processing and clustering the user's power data through multiple preset indicator evaluation strategies, multiple target power consumption patterns are obtained and demand response calculations are performed, which solves the problem of inaccurate assessment of demand response potential in the prior art, and achieves higher evaluation accuracy and flexibility.
Patent Information
- Application Number
- CN202411671559.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-04-11
AI Technical Summary
The accuracy of evaluating the demand response potential of different users in the prior art is low, especially when faced with rapidly changing load demands and complex electricity price structures.
The target power data is processed based on multiple preset indicator evaluation strategies, clustered to obtain multiple target power consumption modes, and the demand response calculation is performed for each power consumption mode to obtain the demand response potential evaluation results.
A hierarchical evaluation of the potential for response to user demands is achieved, the accuracy of the evaluation is improved, and it can more effectively assist users in adjusting their power consumption plans in response to the supply and demand balance of the power grid.
Smart Images
Figure CN119809405A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a demand response potential assessment method, apparatus, computer equipment, readable storage medium and program product. Background Art
[0002] With the rapid development of renewable energy and the continuous reform of the power market, demand response (DR) on the user side has become an important means to achieve optimal allocation of power resources. Users can voluntarily increase, reduce or delay part of their electricity demand according to the demand and price signals of the power grid, and adjust their electricity consumption plans to respond to the supply and demand balance of the power grid. Demand response can effectively reduce the load pressure during peak hours.
[0003] However, in the face of rapidly changing load demands and complex electricity price structures, users often require higher flexibility. Therefore, the accuracy of evaluating the demand response potential of different users in related technologies is low. Summary of the invention
[0004] Based on this, it is necessary to provide a demand response potential assessment method, apparatus, computer equipment, readable storage medium and program product that can improve the accuracy of assessing the demand response potential of different users in response to the above technical problems.
[0005] In a first aspect, the present application provides a method for evaluating demand response potential, comprising:
[0006] Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy;
[0007] Clustering the target power data based on the indicator information to obtain multiple target power consumption modes;
[0008] The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
[0009] In one embodiment, clustering the target power data based on the indicator information to obtain multiple target power consumption modes includes:
[0010] Performing global clustering processing on the target power data to obtain multiple first power usage modes;
[0011] Based on a preset density space clustering algorithm, each first power usage mode is subdivided and clustered to obtain multiple second power usage modes;
[0012] The second power usage mode is processed based on the indicator information to obtain a reconstruction suggestion, and a plurality of target power usage modes are obtained based on the reconstruction suggestion.
[0013] In one embodiment, performing demand response calculation on the target power data corresponding to each target power consumption mode to obtain a demand response potential assessment result includes:
[0014] For each power consumption mode, calculate the maximum value of the target power data per unit time;
[0015] Calculating the difference between the maximum value and the predicted load value, and determining the difference greater than a preset value as a demand response potential quantification value;
[0016] The demand response potential quantification value is visualized in a graph based on the sliding window average value to obtain a visualization result; based on the visualization result and the portrait information, a demand response potential evaluation result is determined.
[0017] In one embodiment, the method further comprises:
[0018] Based on the preset indicator evaluation strategy, each power usage mode and the corresponding indicator information are visualized in a chart to obtain the portrait information of each power usage mode.
[0019] In one embodiment, the plurality of preset index evaluation strategies include a climbing index evaluation system, a rotation index evaluation system and a peak-valley index evaluation system.
[0020] In one embodiment, the method further comprises:
[0021] Initial power data is acquired, and the initial power data is preprocessed to obtain target power data, wherein the initial power data includes one or more of user information, power consumption, and power operation standard.
[0022] In a second aspect, the present application also provides a demand response potential assessment device, comprising:
[0023] A processing module, used to process the target power data based on a plurality of preset indicator evaluation strategies respectively, and obtain indicator information corresponding to each preset indicator evaluation strategy;
[0024] A clustering processing module, used for performing clustering processing on the target power data based on the indicator information to obtain multiple target power consumption modes;
[0025] The calculation module is used to perform demand response calculation on the target power data corresponding to each target power consumption mode to obtain a demand response potential evaluation result.
[0026] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:
[0027] Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy;
[0028] Clustering the target power data based on the indicator information to obtain multiple target power consumption modes;
[0029] The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
[0030] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:
[0031] Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy;
[0032] Clustering the target power data based on the indicator information to obtain multiple target power consumption modes;
[0033] The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
[0034] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:
[0035] Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy;
[0036] Clustering the target power data based on the indicator information to obtain multiple target power consumption modes;
[0037] The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
[0038] The above-mentioned demand response potential assessment method, device, computer equipment, readable storage medium and program product process the target power data respectively through a variety of preset indicator evaluation strategies to obtain indicator information corresponding to each preset evaluation strategy; cluster the target power data based on the indicator information to obtain a variety of target power consumption modes, and reasonably classify user behaviors; and perform demand response calculations on the target power data of each target power consumption mode to obtain demand response potential assessment results, which can realize hierarchical demand response potential assessment of users and improve the accuracy of user demand response potential assessment. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0040] Figure 1 A schematic diagram of a flow chart of a demand response potential assessment method in one embodiment;
[0041] Figure 2 A schematic diagram of a flow chart of a demand response potential assessment method in one embodiment;
[0042] Figure 3 It is a structural block diagram of a demand response potential assessment device in one embodiment;
[0043] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0045] In an exemplary embodiment, Figure 1 As shown, a demand response potential evaluation method is provided. This embodiment uses the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:
[0046] Step 101: Process target power data based on a plurality of preset indicator evaluation strategies respectively to obtain indicator information corresponding to each preset indicator evaluation strategy.
[0047] Among them, different preset indicator evaluation strategies can be set based on different time scales. The preset indicator evaluation strategy can be an indicator evaluation system of different time sizes. The target power data can be composed of load powers of multiple unit time lengths. The indicator information can characterize the load changes on different time scales in the power system, and the indicator information can be the specific values corresponding to the indicators in the preset indicator evaluation strategy.
[0048] Specifically, the terminal can pre-set different preset indicator evaluation strategies according to different time division scales. The terminal can calculate the target power data according to the time scales specified by different preset indicator evaluation strategies to obtain indicator information. The indicator information can reflect the load changes on different time scales. In addition, the terminal can construct a corresponding indicator data set based on the indicator information of different preset indicator evaluation strategies, and the indicator data set may include indicators, indicator information and timestamps.
[0049] Step 102: cluster the target power data based on the indicator information to obtain multiple target power consumption patterns.
[0050] Among them, the target power consumption mode can represent the user's power consumption type.
[0051] Specifically, the terminal can perform clustering processing on the target power data through a preset clustering algorithm to obtain a clustering result. The terminal can view the distribution of power consumption characteristic indicators of the user group of the clustering result based on the indicator data set of the indicator information, reconstruct the clustering result, and obtain a variety of target power consumption modes. The terminal can also perform multiple clustering processing on the target power data through a preset clustering algorithm to obtain a clustering result. The terminal can perform a clustering processing on the target power data once through a preset clustering algorithm to obtain a first clustering result. The terminal can also perform a secondary clustering processing on the target power data corresponding to the first clustering result through a preset clustering algorithm to obtain a second clustering result, ..., the terminal can perform n clustering processing on the target power data corresponding to the n-1 clustering result through a preset clustering algorithm to obtain an nth clustering result. The terminal can view the distribution of power consumption characteristic indicators of the user group of the nth clustering result based on the indicator data set of the indicator information, reconstruct the nth clustering result, and obtain a variety of target power consumption modes. It should be understood that the number of specific clustering is related to the actual application environment and is not limited here. The preset clustering algorithms in the multiple clustering processes may be the same clustering algorithm or different clustering algorithms, and the preset clustering algorithm may be a hierarchical clustering algorithm and / or a density-based spatial clustering of applications with noise (DBSCAN). In addition, the terminal may filter out noise and interference data in the clustering process.
[0052] Step 103: Perform demand response calculation on the target power data corresponding to each target power consumption mode to obtain a demand response potential assessment result.
[0053] Specifically, for each target power consumption mode, the terminal may calculate the target power data to obtain a quantitative value of demand response potential, and smooth the quantitative value of demand response potential to obtain a demand response potential evaluation result of the target power consumption mode.
[0054] The above-mentioned demand response potential assessment method processes the target power data respectively through a variety of preset indicator evaluation strategies to obtain the indicator information corresponding to each preset evaluation strategy; clusters the target power data based on the indicator information to obtain a variety of target power consumption modes, and reasonably classifies user behaviors; and performs demand response calculations on the target power data of each target power consumption mode to obtain demand response potential assessment results, which can realize hierarchical demand response potential assessment of users and improve the accuracy of user demand response potential assessment.
[0055] In an exemplary embodiment, step 102 includes:
[0056] The target power data is globally clustered to obtain a plurality of first power usage patterns; based on a preset density space clustering algorithm, each first power usage pattern is subdivided and clustered to obtain a plurality of second power usage patterns; the second power usage pattern is processed based on the indicator information to obtain reconstruction suggestions, and based on the reconstruction suggestions, a plurality of target power usage patterns are obtained.
[0057] Among them, the multiple second power usage modes can be a branch of the first power usage mode. The multiple target modes can be a branch of the second power usage mode. The multiple first power usage modes can be three major modes: residential, commercial and industrial.
[0058] Specifically, the terminal can use the unit length as the characteristic dimension of the target power data, divide the unit length according to the time frequency of the specified time, and divide the target power data within the unit time length into multiple characteristic dimensions. The terminal can normalize the target power data of multiple characteristic dimensions to obtain the normalized target power data. The terminal can select a preset distance threshold or a number of clusters to perform global clustering on the target power data to obtain multiple first power consumption modes. The terminal performs subdivision clustering on each first power consumption mode by setting the eps (neighborhood radius) and min_samples (minimum number of samples in the neighborhood) parameters to obtain multiple second power consumption modes. The terminal can combine the indicator information to view the indicator distribution of the power consumption characteristics of the power consumption mode after clustering to obtain reconstruction suggestions. The terminal can reconstruct the second power consumption mode based on the reconstruction suggestions to obtain multiple target power consumption modes. In addition, the terminal can perform a mechanistic clustering analysis on the second power consumption mode in combination with the preset suggestion to obtain a reconstruction suggestion. The terminal can also reconstruct the second power consumption mode through the reconstruction suggestion obtained by the preset suggestion to obtain multiple target power consumption modes. The terminal can also combine the indicator information and the preset suggestion to obtain a reconstruction suggestion. It should be understood that the preset suggestions may be experience suggestions.
[0059] In addition, the terminal can reduce the dimension of the target power data by using a dimensionality reduction algorithm before performing the second clustering. For example, the terminal can perform dimensionality reduction processing by using a principal component analysis algorithm (PCA) to obtain the target power data after dimensionality reduction processing, and the terminal can use the target power data after dimensionality reduction processing for the second clustering processing. The terminal can also use the k-distance method to estimate the appropriate EPS value, or use cross-validation combined with indicators such as the silhouette coefficient to select the best parameters. The terminal can cluster the first power consumption mode again and identify and eliminate noise points using the optimized parameters.
[0060] Exemplarily, the terminal data uses the intraday time period as the feature dimension. Taking the time frequency of 5 minutes as an example, the target power data (daily load curve data) has 288 feature dimensions. The terminal can use the hierarchical clustering algorithm to perform global clustering processing on the target power data. The terminal can use the DBSCAN algorithm to perform segmented clustering processing on the target power data.
[0061] In this embodiment, the target power consumption pattern is obtained by performing multiple clustering processes on the target power data, and the effective information of the user portrait is enriched through multi-level classification and combined with indicator information, which effectively assists in the accurate assessment of the potential for responding to classified user needs. At the same time, the DBSCAN algorithm can effectively filter out noise interference, and the DBSCAN algorithm combined with hierarchical clustering can achieve accurate control of multi-level classification clustering.
[0062] In an exemplary embodiment, step 103 includes:
[0063] For each power consumption mode, the maximum value of the target power data per unit time is calculated; the difference between the maximum value and the predicted load value is calculated, and the difference greater than the preset value is determined as the demand response potential quantification value; the demand response potential quantification value is visualized based on the sliding window average value to obtain a visualization result; based on the visualization result and portrait information, the demand response potential evaluation result is determined.
[0064] The extreme value may include a maximum value and a minimum value.
[0065] Specifically, for each power consumption mode, the terminal can adjust the target power data per unit time by the 3σ principle. The terminal can calculate the maximum and minimum values of the target power data per unit time. The terminal can obtain the maximum and minimum values of the target power data per unit time by sorting or by load curve. The specific formula for the maximum and minimum values of the target power data per unit time can be:
[0066]
[0067] Among them, U adj is the maximum value of the daily load curve after adjustment by the 3σ principle, L adj is the minimum value of the daily load curve after adjustment by the 3σ principle. μ is the mean value; σ is the standard deviation.
[0068] The terminal can predict the predicted load value per unit time by using a preset load prediction model. The terminal can calculate a first difference between the maximum value and the predicted load value, and calculate a second difference between the predicted load value and the minimum value. The terminal can compare the first difference with the preset value. If the first difference is greater than the preset value, the first difference is used as the first demand response potential quantification value; otherwise, the preset value is used as the first demand response potential quantification value. The terminal can compare the second difference with the preset value. If the second difference is greater than the preset value, the second difference is used as the second demand response potential quantification value; otherwise, the preset value is used as the second demand response potential quantification value. The terminal determines the first demand response potential quantification value and the second demand response potential quantification value as the demand response potential quantification value. The expression of the demand response potential quantification value can be:
[0069]
[0070] Among them, P upper is the quantitative value of the first demand response potential, P lower is the second demand response potential quantification value, X pred is the predicted load value. For example, the preset value may be 0.
[0071] The terminal can draw a line graph of the quantitative value of the demand response potential in combination with the sliding window average value, and use a smoothing tool to smooth the line graph to obtain a visualization result. The terminal can combine the image information of the electricity consumption model and the visualization result to obtain the demand response potential evaluation result.
[0072] In this embodiment, the relationship between the predicted load value and the upper and lower bounds of the adjusted daily load curve is taken into account, and the potential value of the demand response potential evaluation result is ensured to be non-negative. The accurate demand response potential evaluation of each classified user on the day to be evaluated is completed. The accurate control of the demand response potential evaluation is achieved.
[0073] In an exemplary embodiment, the demand response potential assessment method further includes:
[0074] Based on the preset indicator evaluation strategy, each power consumption mode and the corresponding indicator information are visualized in a chart to obtain the portrait information of each power consumption mode.
[0075] Among them, the portrait information can characterize the typical characteristics of different electricity consumption patterns, the time distribution of electricity consumption behavior, the fluctuation of electricity power, etc.
[0076] Specifically, the terminal can perform chart visualization processing on each power consumption mode and the indicator information corresponding to each power consumption mode based on the preset indicator evaluation strategy. The terminal can realize icon visualization processing of the power consumption mode and the corresponding indicator information through the chart visualization tool to obtain the visualization result. The terminal can build a portrait of each power consumption mode by combining the visualization results and the indicator information. The terminal can draw a bar chart / radar chart through the chart visualization tool. For example, the terminal can display the indicator information between different preset indicator evaluation strategies through a bar chart. The terminal can choose to draw the climbing rate, the rotation load change rate, etc., and the specific indicators drawn can be set according to the preset indicator evaluation strategy.
[0077] Exemplarily, the chart visualization tool may be a plotting library (Matplotlib Plotting Library, Matplotlib) or a statistical plotting library (Seaborn Statistical Data Visualization, Seaborn), which is not specifically limited herein.
[0078] In this embodiment, each power consumption mode and the corresponding indicator information are visualized based on a preset indicator evaluation strategy to obtain portrait information of each power consumption mode, thereby improving the operating efficiency and reliability of the power grid.
[0079] In an exemplary embodiment, the plurality of preset index evaluation strategies include a climbing index evaluation system, a rotation index evaluation system, and a peak-valley index evaluation system.
[0080] Specifically, the terminal can set different indicator evaluation strategies through different time scales. The terminal can calculate the climbing rate and the total climbing time, the climbing rate and the total climbing time under the climbing indicator evaluation system. The terminal uses the climbing rate and the total climbing time, the climbing rate and the total climbing time as the indicator information under the climbing indicator evaluation system. The terminal can calculate the rotation load change and the rotation load change rate under the rotation indicator evaluation system, and use the rotation load change and the rotation load change rate as the indicator information under the rotation indicator evaluation system. The terminal can calculate the volatility, the peak load proportion (peak power grid power consumption period), the valley load proportion (low power grid power consumption period) and the peak-valley difference rate under the peak-valley indicator evaluation system, and use the volatility, the peak load proportion (peak power grid power consumption period), the valley load proportion (low power grid power consumption period) and the peak-valley difference rate as the indicator information under the peak-valley indicator evaluation system.
[0081] For example, the climbing index evaluation system is defined in the time interval The load change is greater than the set threshold is a climbing event, that is , where P e and P s They are The load power at the end and the beginning of the period. Climbing related indicators include climbing rate and total climbing time , which can be specifically divided into the climbing rate and the total climbing time, and the downhill rate and the total downhill time. The specific calculation formula of the climbing rate can be:
[0082]
[0083] Rotational rest index evaluation system: defined as the relevant index between statutory rest days and working days. Including the change of rotational rest load Load change rate with shift .in, is the average daily load of the user on working days, is the average value of the daily load on the user's rest day;
[0084] Peak-valley index evaluation system: defined as the relevant indicators related to the peak / valley period of power grid electricity consumption, including volatility (total volatility of user daily load curve, volatility of user load curve during peak power grid electricity consumption, volatility of user load curve during valley power grid electricity consumption) , Peak load ratio , valley load ratio (low power consumption period of the power grid) Peak-to-valley ratio Among them, P peak is the user load during the peak period of the power grid on that day; Pmin is the minimum load of the user on that day; P max is the maximum load of the user on that day; P volley It is the user's load during the low period of the power grid on that day.
[0085] In addition, the terminal may construct an indicator data set corresponding to the corresponding indicator information.
[0086] In an exemplary embodiment, the demand response potential assessment method further includes:
[0087] Initial power data is acquired, and the initial power data is preprocessed to obtain target power data.
[0088] The initial power data includes one or more of user information, power consumption and power operation standards. User information may include specific user categories (residential / industrial / commercial), and power consumption may include real-time data of each user. The grid operation execution standards include the division rules of peak / valley / normal periods.
[0089] Specifically, the terminal can collect the initial power data related to multiple measuring points of the site to be evaluated in real time or within a specified period of time, screen the data quality of the initial power data one by one, and process missing values and abnormal values.
[0090] The power consumption data is preprocessed at each measuring point and each day. It is necessary to screen out the daily data with too many missing values or obvious abnormal data. For the data that meet the overall data quality requirements, the power consumption is detected by the outlier detection algorithm to obtain the outliers, and the outliers are determined as missing values. The random forest algorithm can be used to fill the missing values. For example, the outlier detection algorithm can be a method such as mechanism discrimination, 3σ principle filtering, and maximum value detection of the rate of change.
[0091] The terminal can construct a daily load curve data set for massive users by transposing the processed real-time power data on a daily basis.
[0092] In an exemplary embodiment, Figure 2 As shown, the demand response potential assessment method also includes:
[0093] Step 201: The terminal may collect initial power data related to multiple measuring points of the site to be evaluated, and pre-process the initial power data to obtain multiple target power data, and construct the target power data into a user daily load curve data set.
[0094] Step 202: The terminal may define preset indicator evaluation strategies under different time scales, calculate indicator information based on the preset indicator evaluation strategies, and form an indicator set.
[0095] Step 203: The terminal implements global clustering through hierarchical clustering to obtain multiple first power usage patterns, performs subdivision clustering processing on each first power usage pattern and removes noise daily data to obtain multiple second power usage patterns, processes the second power usage patterns based on indicator information to obtain reconstruction suggestions, and obtains multiple target power usage patterns based on the reconstruction suggestions.
[0096] Step 204: Calculate the demand response potential and profile specific index values for each category of users in combination with the power consumption plan limit and different demand response states (working days / holidays), and visualize them in bar charts and radar charts respectively.
[0097] The above-mentioned demand response potential assessment method constructs an electricity consumption characteristic index evaluation system at different time scales, and combines multiple characteristic index evaluation systems with a hierarchical clustering algorithm for global clustering and a DBSCAN algorithm for screening out abnormal electricity consumption curves. It realizes the classification of reasonable user electricity consumption behaviors through mechanistic judgment, and quantifies the demand response potential of classified users. Finally, the demand response potential assessment of hierarchical and classified users is completed in a visual form.
[0098] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0099] Based on the same inventive concept, the embodiment of the present application also provides a demand response potential assessment device for implementing the demand response potential assessment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more demand response potential assessment device embodiments provided below can refer to the limitations of the demand response potential assessment method above, and will not be repeated here.
[0100] In an exemplary embodiment, Figure 3 As shown, a demand response potential assessment device 30 is provided, comprising: a processing module 31, a clustering processing module 32 and a calculation module 33, wherein:
[0101] The processing module 31 is used to process the target power data based on multiple preset indicator evaluation strategies respectively to obtain indicator information corresponding to each preset indicator evaluation strategy;
[0102] A clustering processing module 32 is used to perform clustering processing on the target power data based on the indicator information to obtain multiple target power consumption modes;
[0103] The calculation module 33 is used to perform demand response calculation on the target power data corresponding to each target power consumption mode to obtain a demand response potential evaluation result.
[0104] In one embodiment, the cluster processing module 32 is used to perform global cluster processing on the target power data to obtain multiple first power usage modes;
[0105] Based on a preset density space clustering algorithm, each first power usage mode is subdivided and clustered to obtain multiple second power usage modes;
[0106] The second power usage pattern is processed based on the indicator information to obtain reconstruction suggestions, and multiple target power usage patterns are obtained based on the reconstruction suggestions.
[0107] In one embodiment, the calculation module 33 is used to calculate the maximum value of the target power data per unit time for each power consumption mode;
[0108] Calculate the difference between the maximum value and the predicted load value, and determine the difference greater than the preset value as the demand response potential quantification value;
[0109] The quantitative value of demand response potential is visualized based on the sliding window average value to obtain a visualization result; based on the visualization result and portrait information, the demand response potential evaluation result is determined.
[0110] In one of the embodiments, the calculation module 33 is further used to perform graphical visualization processing on each power usage mode and the corresponding indicator information based on a preset indicator evaluation strategy to obtain portrait information of each power usage mode.
[0111] In one embodiment, the multiple preset indicator evaluation strategies include a climbing indicator evaluation system, a rotation indicator evaluation system, and a peak-valley indicator evaluation system.
[0112] In one embodiment, the processing module 31 is further used to obtain initial power data, pre-process the initial power data, and obtain target power data. The initial power data includes: one or more of user information, power consumption, and power operation standards.
[0113] Each module in the above-mentioned demand response potential assessment device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0114] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a demand response potential assessment method is implemented.
[0115] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0116] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0117] Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy;
[0118] Clustering the target power data based on the indicator information to obtain multiple target power consumption modes;
[0119] The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
[0120] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0121] Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy;
[0122] Clustering the target power data based on the indicator information to obtain multiple target power consumption modes;
[0123] The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
[0124] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0125] Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy;
[0126] Clustering the target power data based on the indicator information to obtain multiple target power consumption modes;
[0127] The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
[0128] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0129] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0130] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for evaluating demand response potential, characterized in that: The method comprises: Based on a plurality of preset index evaluation strategies, the target power data is processed respectively to obtain the index information corresponding to each preset index evaluation strategy; Clustering the target power data based on the indicator information to obtain multiple target power consumption modes; The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result.
2. The method according to claim 1, characterized in that The target power data is clustered based on the indicator information to obtain multiple target power consumption modes, including: Performing global clustering processing on the target power data to obtain multiple first power usage modes; Based on a preset density space clustering algorithm, each first power usage mode is subdivided and clustered to obtain multiple second power usage modes; The second power usage mode is processed based on the indicator information to obtain a reconstruction suggestion, and a plurality of target power usage modes are obtained based on the reconstruction suggestion.
3. The method according to claim 1, characterized in that: The target power data corresponding to each target power consumption mode is subjected to demand response calculation to obtain a demand response potential assessment result, including: For each power consumption mode, calculate the maximum value of the target power data per unit time; Calculating the difference between the maximum value and the predicted load value, and determining the difference greater than a preset value as a demand response potential quantification value; The demand response potential quantification value is visualized in a graph based on the sliding window average value to obtain a visualization result; based on the visualization result and the portrait information, a demand response potential evaluation result is determined.
4. The method according to claim 3, characterized in that The method further comprises: Based on the preset indicator evaluation strategy, each power usage mode and the corresponding indicator information are visualized in a chart to obtain the portrait information of each power usage mode.
5. The method according to claim 1, characterized in that: The multiple preset indicator evaluation strategies include a climbing indicator evaluation system, a rotation indicator evaluation system and a peak-valley indicator evaluation system.
6. The method according to claim 1, characterized in that The method further comprises: Initial power data is acquired, and the initial power data is preprocessed to obtain target power data, wherein the initial power data includes one or more of user information, power consumption, and power operation standard.
7. A demand response potential assessment device, characterized in that: The device comprises: A processing module, used to process the target power data based on a plurality of preset indicator evaluation strategies respectively, and obtain indicator information corresponding to each preset indicator evaluation strategy; A clustering processing module, used for performing clustering processing on the target power data based on the indicator information to obtain multiple target power consumption modes; The calculation module is used to perform demand response calculation on the target power data corresponding to each target power consumption mode to obtain a demand response potential evaluation result.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.