Virtual power plant demand response potential assessment method and system, terminal and storage medium

Abstract

The invention relates to the technical field of virtual power plant evaluation methods, and particularly provides a virtual power plant demand response potential evaluation method and system, a terminal and a storage medium, and the method comprises the steps: obtaining historical power load data in a preset time period; carrying out dimension reduction calculation on the historical electrical load data according to a pre-selected load characteristic index; performing clustering analysis based on the dimension reduction data to obtain N groups of dimension reduction load data corresponding to the maximum clustering number N, performing dimension raising on the N groups of dimension reduction load data, and obtaining a corresponding clustering center curve based on the N groups of dimension-raised load data, the clustering center being a typical daily load curve; and carrying out demand response potential analysis on the N groups of load data after dimension raising by using an elastic coefficient method to respectively obtain response potential values of a peak period and a valley period, and subtracting the response potential value of the peak period from the typical daily load curve or adding the response potential value of the valley period to obtain an adjusted response potential value curve. The method has the advantage of reducing dependence on complex data.

Description

Technical Field

[0001] The present invention belongs to the technical field of virtual power plant evaluation methods, and specifically relates to a method, system, terminal and storage medium for evaluating the demand response potential of a virtual power plant. Background Art

[0002] Virtual power plants aggregate various types of power resources such as generators, energy storage facilities and controllable loads through advanced communication and network technologies, forming a virtual entity to participate in grid management and the power market. As an effective technical means, virtual power plants can solve the grid peak load and consumption problems caused by the large-scale access of renewable energy, and have good development prospects. In the future, with the development of distributed energy such as renewable energy, flexible loads, and energy storage, and the advancement of information and communication technology, the application prospects of virtual power plants will be broader.

[0003] However, the current demand response potential assessment methods still have many technical bottlenecks, which limit their effectiveness in practical applications. First, the complexity of the data required by the existing virtual power plant model is one of the primary problems. Most of the current demand response potential assessments rely on a variety of complex input data, including electricity price information, policy incentive mechanisms, and user electricity load data. Although these data can theoretically provide support for the accurate assessment of demand response, in actual operation, it is difficult to obtain these data. In particular, due to differences in electricity policies and market mechanisms in different regions, the availability and accuracy of relevant data are difficult to guarantee, which further increases the difficulty of demand response assessment of virtual power plants. In addition, the volatility, seasonality and diversity of user-side loads also make the acquisition and processing of electricity load data more complicated, thereby increasing the system calculation amount and the complexity of the evaluation process. Secondly, the adaptability of existing evaluation models is insufficient. Most of the existing demand response assessment methods rely on specific load models or demand response assessment models. Although these models can reflect users' electricity habits and load changes to a certain extent, their adaptability is still limited. These models usually require a large amount of prior data and assumptions to calculate, which makes it difficult to respond flexibly when dealing with complex and dynamically changing electricity consumption environments. For example, many models can only handle specific load types or load changes in specific time periods, and cannot fully consider the user's response potential under different load characteristics. The limitations of this model directly lead to deviations in the demand response potential assessment results, making it difficult to provide accurate basis for actual scheduling decisions. Third, the model evaluation process is complex and computationally intensive. In order to achieve a more accurate demand response potential assessment, existing methods often require complex calculation processes, including load forecasting, cluster analysis, response potential estimation and other steps. These steps not only require high algorithm accuracy, but also require a large amount of computing resources to support, resulting in an increase in system operating costs. At the same time, due to the volatility of user electricity load data, existing models often require multiple iterations and adjustments during calculations to improve the convergence and accuracy of the model, further increasing the system's computational burden. Summary of the invention

[0004] In view of the problems in the prior art that the data required for the virtual power plant model is relatively complex, the existing evaluation model is insufficiently adaptable, and the amount of calculation required in the model evaluation process is large, the present invention provides a virtual power plant demand response potential evaluation method, system, terminal and storage medium to solve the above technical problems.

[0005] In a first aspect, the present invention provides a method for evaluating the demand response potential of a virtual power plant, comprising: Obtain historical power load data within a preset time period; Performing dimension reduction calculation on the historical power load data according to the pre-selected load characteristic index to obtain dimension reduction data; Perform cluster analysis based on the reduced-dimensionality data to obtain N groups of reduced-dimensionality load data corresponding to the maximum cluster number N, upgrade the N groups of reduced-dimensionality load data, and obtain corresponding cluster center curves based on the N groups of upgraded-dimensional load data, wherein the cluster center is a typical daily load curve; The elastic coefficient method is used to analyze the demand response potential of N groups of load curves after dimensionality upgrade, and the response potential values ​​of peak period and valley period are obtained respectively. The response potential value of peak period is subtracted from the typical daily load curve, or the response potential value of valley period is added to obtain the adjusted response potential value curve.

[0006] Furthermore, obtaining historical power load data within a preset time period includes: Get the historical power load data for a preset number of days n consecutive hours.

[0007] Furthermore, the historical power load data is subjected to dimensionality reduction calculation according to the pre-selected load characteristic index to obtain dimensionality reduction data, including: Calculate the average daily load

[0008] =

[0009] Among them, P is the load value of the i-th time period; Calculate daily load factor

[0010] =

[0011] in, is the maximum load value of the day; Calculate the peak-to-valley ratio

[0012] =

[0013] in, is the minimum load value of the day; Calculate peak load factor

[0014] =

[0015] in, is the sum of the loads during the peak period, is the number of hours during the peak period; Calculate the average load factor

[0016] =

[0017] in, is the sum of the loads during normal periods, is the number of hours during the normal period; Calculate the valley load factor

[0018] =

[0019] in, is the sum of the loads during the valley period, The number of hours during the valley period.

[0020] Furthermore, cluster analysis is performed based on the reduced dimension data to obtain N groups of reduced dimension load data corresponding to the maximum cluster number N, and the N groups of reduced dimension load data are upgraded, and the corresponding cluster center curve is obtained based on the N groups of upgraded dimension load data, and the cluster center is a typical daily load curve, including: Import the dimension-reduced data into Matlab for cluster analysis to obtain the maximum number of clusters N and N groups of dimension-reduced load data corresponding to the maximum number of clusters N; Upgrading the dimension of each set of reduced-dimensional load data to obtain each set of upgraded-dimensional load data; A cluster center curve is obtained in each group of load data after dimensionality upgrade, wherein the cluster center is a typical daily load curve.

[0021] Furthermore, the elastic coefficient method is used to analyze the demand response potential of N groups of load curves after dimensionality upgrade, and the response potential values ​​of peak time and valley time are obtained respectively, including: Get the Tiandi Electricity load in each period , calculate the first The average power load in each period

[0022] ; based on Calculate the Elasticity coefficient of time period

[0023] ; based on and Calculate the Load factor for each period

[0024] ; based on and Calculate the response potential value during the peak period Response potential value during the valley period

[0025]

[0026]

[0027] in, and represent the peak period and valley period respectively. For each The maximum load factor of the time period, The first time in the day from 0:00 to 24:00 time periods, each time period is 1 hour long, and n is the total number of days of user load data.

[0028] Furthermore, it also includes: before performing dimensionality reduction calculation on the historical power load data according to the pre-selected load characteristic index to obtain the dimensionality reduction data, preprocessing the historical power load data includes: deleting abnormal values ​​in the historical power load data.

[0029] In a second aspect, the present invention provides a virtual power plant demand response potential assessment system, comprising: A data acquisition module is used to acquire historical power load data within a preset time period; A dimension reduction calculation module, used to perform dimension reduction calculation on the historical power load data according to a pre-selected load characteristic index to obtain dimension reduction data; A cluster analysis module is used to perform cluster analysis based on the reduced-dimensionality data, obtain N groups of reduced-dimensionality load data corresponding to the maximum cluster number N, upgrade the N groups of reduced-dimensionality load data, and obtain the corresponding cluster center curve based on the N groups of upgraded-dimensional load data, wherein the cluster center is a typical daily load curve; The demand response potential analysis module is used to perform demand response potential analysis on N groups of up-dimensional load curves using the elastic coefficient method, and obtain the response potential values ​​for peak and valley periods respectively. The typical daily load curve is subtracted from the response potential value for the peak period or added to the response potential value for the valley period to obtain the adjusted response potential value curve.

[0030] Furthermore, the cluster analysis module includes: The cluster analysis unit is used to import the dimension reduction data into Matlab for cluster analysis, and obtain the maximum cluster number N and N groups of dimension reduction load data corresponding to the maximum cluster number N; A dimension-increasing unit, comprising: performing dimension-increasing on each set of reduced-dimensional load data to obtain each set of dimension-increasing load data; The typical daily load curve generating unit is used to obtain the cluster center curve in each group of load data after dimensionality upgrade, and the cluster center is the typical daily load curve.

[0031] In a third aspect, a terminal is provided, including: processor, memory, wherein: The memory is used to store computer programs. The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.

[0032] According to a fourth aspect, a computer storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the methods described in the above aspects.

[0033] The beneficial effect of the present invention is that the virtual power plant demand response potential evaluation method, system, terminal and storage medium provided by the present invention, firstly, by simplifying data acquisition, the dependence on complex data (such as electricity price information, electricity policy, etc.) is reduced, and the demand response potential evaluation is performed only by relying on the user's historical electricity load data, which greatly reduces the difficulty of data collection and the system calculation cost, and improves the operability of the evaluation. Secondly, the K-medoids clustering method is used to replace the traditional K-means clustering, avoiding the deviation problem of the K-means method using the mean as the cluster center. By using the actual point closest to the cluster center as the cluster center, the clustering result is more in line with the user's actual electricity consumption, thereby improving the accuracy of the evaluation. In addition, the present invention can accurately evaluate the user's demand response potential in different time periods through cluster analysis and elasticity coefficient method, especially in the load regulation of peak and valley periods, helping the power system to achieve more accurate peak shaving and valley filling, and improving the optimal configuration capability of power resources. In general, the present invention not only improves the accuracy and efficiency of demand response potential evaluation, but also provides strong technical support for the intelligent dispatching of new power systems such as virtual power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0036] Figure 2 It is a schematic diagram of determining the optimal number of classifications according to a method of an embodiment of the present invention.

[0037] Figure 3 is a schematic block diagram of a system according to an embodiment of the present invention.

[0038] Figure 4 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0041] The virtual power plant demand response potential assessment method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the virtual power plant demand response potential assessment system runs in the computer device.

[0042] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution entity may be a virtual power plant demand response potential assessment system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0043] To facilitate understanding of the present invention, the virtual power plant demand response potential evaluation method provided by the present invention is further described below based on the principle of the virtual power plant demand response potential evaluation method of the present invention and in combination with the process of evaluating the demand response potential of the virtual power plant in the embodiment.

[0044] Specifically, Figure 1 As shown, the virtual power plant demand response potential assessment method includes: S1. Obtain historical power load data within a preset time period.

[0045] Get the historical power load data for a preset number of days n consecutive hours.

[0046] Specifically, the electricity load data of a certain user from 0:00 to 24:00 every day for 115 days from April to August 2017 (a total of 24 time periods) are collected and the user's original daily load curve is drawn (the horizontal axis is the time period, the vertical axis is the electricity load, and the data is 115×24 dimensions). The purpose of this curve is to more clearly see the approximate changes in the user's most original electricity consumption data over time from April to August 2017 before data preprocessing, clustering and other steps.

[0047] In one possible implementation, it further includes: before performing dimensionality reduction calculation on the historical power load data according to the pre-selected load characteristic index to obtain the dimensionality reduction data, preprocessing the historical power load data includes: deleting abnormal values ​​in the historical power load data.

[0048] Specifically, after removing the outliers in the original data of S1, the number of days the user used electricity changed from 115 to 111, and a total of 4 days of abnormal data were removed (111×24 dimensions).

[0049] S2. Performing dimension reduction calculation on the historical power load data according to the pre-selected load characteristic index to obtain dimension reduction data.

[0050] Calculate the average daily load

[0051] =

[0052] Among them, P is the load value of the i-th time period; Calculate daily load factor

[0053] =

[0054] in, is the maximum load value of the day; Calculate the peak-to-valley ratio

[0055] =

[0056] in, is the minimum load value of the day; Calculate peak load factor

[0057] =

[0058] in, is the sum of the loads during the peak period, is the number of hours during the peak period; Calculate the average load factor

[0059] =

[0060] in, is the sum of the loads during normal periods, is the number of hours during the normal period; Calculate the valley load factor

[0061] =

[0062] in, is the sum of the loads during the valley period, The number of hours during the valley period.

[0063] Specifically, the pre-selected load characteristic indicators can be daily average load, daily load rate, peak-to-valley difference rate, peak load rate, flat load rate and valley load rate, through which the user's electricity consumption information and characteristics in one day can be better extracted. The calculation of each indicator is related to the load of each period of the day. For example, the daily average load is the average of the load of each period of the 24 periods of the day; the peak-to-valley difference rate is the difference between the maximum load and the minimum load of the day divided by the maximum load. The purpose of this step is to replace the original data of 24 dimensions per day with 6-dimensional indicators to achieve the purpose of dimensionality reduction.

[0064] The above six indicators are used to replace the original power load of each hour period from 0:00 to 24:00 every day in step S1, so that the original data is reduced from 24 dimensions to 6 dimensions. The purpose of this step is to achieve information dimensionality reduction through indicator extraction, and replace the 24-dimensional single load data with 6-dimensional indicator data, so that the data contains more power information and features, so that the subsequent clustering is more accurate and effective (111×6 dimensions).

[0065] S3. Perform cluster analysis based on the reduced-dimensionality data to obtain N groups of reduced-dimensionality load curves corresponding to the maximum cluster number N, increase the dimensions of the N groups of reduced-dimensionality load curves, and obtain corresponding cluster center curves based on the N groups of increased-dimensional load curves, where the cluster center is a typical daily load curve.

[0066] Import the dimension-reduced data into Matlab for cluster analysis to obtain the maximum number of clusters N and N groups of dimension-reduced load data corresponding to the maximum number of clusters N; Upgrading the dimension of each set of reduced-dimensional load data to obtain each set of upgraded-dimensional load data; A cluster center curve is obtained in each group of load data after dimensionality upgrade, wherein the cluster center is a typical daily load curve.

[0067] Specifically, before using the software MATLAB to perform clustering operations, a silhouette coefficient test can be performed to determine the optimal number of categories. The process of the silhouette coefficient is to compare the effects of different clustering situations of the original data. For example, when the data is divided into 1 category, the silhouette coefficient is a; when it is divided into 2 categories, the silhouette coefficient is b... Find a situation where the silhouette coefficient is closest to 1, which is the best clustering effect.

[0068] The results of the silhouette coefficient test are as follows Figure 2 As shown in the figure, it can be seen that the maximum number of categories was originally set to 10. When the number of categories is 3, the silhouette coefficient is closest to 1, and the effect is best, so the data is clustered into 3 categories.

[0069] Specifically, the software Matlab can be used to perform clustering operations. In the specific operation, the 6-dimensional data (111×6 dimensions) obtained in step S2 needs to be input so that clustering can be performed based on the index data containing rich and effective information such as the daily average load and the daily load rate.

[0070] For example, using specific codes: The first step is to input data, where each row is a sample and each column is a feature.

[0071] The second step is to enter the maximum number of clusters for this group of data as 10.

[0072] The third step is to set the number of iterations to 500.

[0073] The fourth step is to execute the clustering algorithm.

[0074] The fifth step is to output the maximum number of clusters; the cluster center and the cluster to which each row of data is divided.

[0075] Since clustering analysis is based on the 6-dimensional data indicators after dimensionality reduction, the output classification data is still indicator data. When drawing, it is also necessary to draw a 24-dimensional load curve with time as the horizontal axis. Therefore, each data needs to be restored to 24-dimensional data one by one. The role of dimensionality reduction is only to make clustering more scientific and accurate. At this time, the original daily load curve is divided into 3 categories after dimensionality reduction, silhouette coefficient test, and clustering. The first category has 71 days (71×24 dimensions), the second category has 25 days (25×24 dimensions), and the third category has 15 days (15×24 dimensions).

[0076] The most representative curve of each of the three categories, that is, the cluster center of the category, is the typical daily load curve of the category. Since the principle of k-mediods clustering is to use the actual point closest to the cluster center as the cluster center, the cluster center of each category is the actual data closest to the cluster center of the category generated by the code.

[0077] Since the output cluster center is also the indicator data, it is necessary to restore the indicator data to 24-dimensional data one by one. Since there are 3 categories in total, there are 3 typical daily load curves, each of which is 1×24 dimensions (the horizontal axis is the time period and the vertical axis is the load amount). The purpose of drawing this curve is to classify the original 111 days of messy electricity consumption information and extract the 3 most representative electricity consumption patterns of the user in 111 days.

[0078] S4. Use the elasticity coefficient method to analyze the demand response potential of N groups of upgraded load curves, and obtain the response potential values ​​of the peak period and the valley period respectively. Subtract the response potential value of the peak period from the typical daily load curve or add the response potential value of the valley period to obtain the adjusted response potential value curve.

[0079] Get the Tiandi Electricity load in each period , calculate the first The average power load in each period

[0080] ; based on Calculate the Elasticity coefficient of time period

[0081] ; based on and Calculate the Load factor for each period

[0082] ; based on and Calculate the response potential value during the peak period Response potential value during the valley period

[0083]

[0084]

[0085] in, and They represent the peak period and valley period respectively. For each The maximum load factor of the time period, The first time in the day from 0:00 to 24:00 time periods, each time period is 1 hour long, and n is the total number of days of user load data.

[0086] Specifically, when calculating the demand response potential of the first category, is 71. When calculating the demand response potential of the second category, is 25. When calculating the demand response potential of the third category, is 15.

[0087] Specifically, when conducting a demand response potential analysis, a demand response potential curve can be drawn (the horizontal axis is the time period, and the vertical axis is the load amount). Each demand response potential curve has two curves, one of which is the typical daily load curve in S3 for comparison, and the other is the adjusted ideal daily load curve obtained by adding or subtracting the obtained response potential value on the basis of the typical daily load curve. In this way, it can be clearly and intuitively seen in which period of time the user has the greatest demand response potential. After analysis, it is concluded that the enterprise shows a high response potential from 9:00-12:00 and 19:00-22:00, and a low response potential from 0:00-9:00. Enterprises can concentrate relevant demand response policies in this time period to achieve a better response effect and realize the balance of power resource regulation by shaving peaks and filling valleys.

[0088] In some embodiments, the virtual power plant demand response potential assessment system may include multiple functional modules composed of computer program segments. The computer program of each program segment in the virtual power plant demand response potential assessment system may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Functionality for evaluating the demand response potential of virtual power plants.

[0089] In this embodiment, the virtual power plant demand response potential assessment system can be divided into multiple functional modules according to the functions it performs, such as Figure 3 As shown. The functional modules of the system 200 may include: a data acquisition module 210, a dimensionality reduction calculation module 220, a clustering analysis module 230, and a demand response potential analysis module 240. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0090] A data acquisition module is used to acquire historical power load data within a preset time period; A dimension reduction calculation module, used to perform dimension reduction calculation on the historical power load data according to a pre-selected load characteristic index to obtain dimension reduction data; A cluster analysis module is used to perform cluster analysis based on the reduced-dimensionality data, obtain N groups of reduced-dimensionality load data corresponding to the maximum cluster number N, upgrade the N groups of reduced-dimensionality load data, and obtain the corresponding cluster center curve based on the N groups of upgraded-dimensional load data, wherein the cluster center is a typical daily load curve; The demand response potential analysis module is used to perform demand response potential analysis on N groups of up-dimensional load curves using the elastic coefficient method, and obtain the response potential values ​​for peak and valley periods respectively. The typical daily load curve is subtracted from the response potential value for the peak period or added to the response potential value for the valley period to obtain the adjusted response potential value curve.

[0091] Optionally, as an embodiment of the present invention, the cluster analysis module includes: The cluster analysis unit is used to import the dimension reduction data into Matlab for cluster analysis, and obtain the maximum cluster number N and N groups of dimension reduction load data corresponding to the maximum cluster number N; A dimension-increasing unit, comprising: performing dimension-increasing on each set of reduced-dimensional load data to obtain each set of dimension-increasing load data; The typical daily load curve generating unit is used to obtain the cluster center curve in each group of load data after dimensionality upgrade, and the cluster center is the typical daily load curve.

[0092] Figure 4 A schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the method for evaluating the demand response potential of a virtual power plant provided in an embodiment of the present invention.

[0093] The terminal 300 may include: a processor 310, a memory 320 and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0094] The memory 320 can be used to store the execution instructions of the processor 310, and the memory 320 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 can perform some or all of the steps in the following method embodiments.

[0095] The processor 310 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 310 can only include a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0096] The communication unit 330 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0097] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0098] Therefore, by fusing data from multiple sensors, the system can combine the advantages of inertial measurement unit and lidar point cloud data to locate the vehicle. IMU can provide high-frequency motion information, while lidar provides accurate spatial data of the environment. By combining the two, the positioning accuracy of the vehicle in complex environments can be effectively improved when the GNSS signal is weak or interfered.

[0099] The virtual power plant demand response potential evaluation method, system, terminal and storage medium provided by the present invention, firstly, by simplifying data acquisition, reducing the dependence on complex data (such as electricity price information, electricity policy, etc.), relying only on the user's historical electricity load data to evaluate the demand response potential, greatly reducing the difficulty of data collection and the system calculation cost, and improving the operability of the evaluation. Secondly, the K-medoids clustering method is used to replace the traditional K-means clustering, avoiding the deviation problem of the K-means method using the mean as the cluster center. By using the actual point closest to the cluster center as the cluster center, the clustering result is more in line with the user's actual electricity consumption, thereby improving the accuracy of the evaluation. In addition, the present invention can accurately evaluate the user's demand response potential in different time periods through cluster analysis and elasticity coefficient method, especially in the load regulation of peak and valley periods, helping the power system to achieve more accurate peak shaving and valley filling, and improving the optimal configuration capability of power resources. In general, the present invention not only improves the accuracy and efficiency of demand response potential evaluation, but also provides strong technical support for the intelligent dispatching of new power systems such as virtual power plants. The technical effects that can be achieved by this embodiment can be found in the above description and will not be repeated here.

[0100] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0101] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0102] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0103] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0105] Although the present invention has been described in detail by referring to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all of these shall be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for evaluating the demand response potential of a virtual power plant, characterized in that: include: Obtain historical power load data within a preset time period; Performing dimension reduction calculation on the historical power load data according to the pre-selected load characteristic index to obtain dimension reduction data; Perform cluster analysis based on the reduced-dimensionality data to obtain N groups of reduced-dimensionality load data corresponding to the maximum cluster number N, upgrade the N groups of reduced-dimensionality load data, and obtain corresponding cluster center curves based on the N groups of upgraded-dimensional load data, wherein the cluster center is a typical daily load curve; The elastic coefficient method is used to analyze the demand response potential of N groups of upgraded load data, and the response potential values ​​of the peak period and the valley period are obtained respectively. The typical daily load curve is subtracted from the response potential value of the peak period or added to the response potential value of the valley period to obtain the adjusted response potential value curve.

2. The method according to claim 1, characterized in that Obtaining historical power load data within a preset time period includes: Get the historical power load data for a preset number of days n consecutive hours.

3. The method according to claim 1, characterized in that According to the pre-selected load characteristic index, the historical power load data is subjected to dimensionality reduction calculation to obtain dimensionality reduction data, including: Calculate the average daily load = Among them, P is the load value of the i-th time period; Calculate daily load factor = in, is the maximum load value of the day; Calculate the peak-to-valley ratio = in, is the minimum load value of the day; Calculate peak load factor = in, is the sum of the loads during the peak period, is the number of hours during the peak period; Calculate the average load factor = in, is the sum of the loads during normal periods, is the number of hours during the normal period; Calculate the valley load factor = in, is the sum of the loads during the valley period, The number of hours during the valley period.

4. The method according to claim 1, characterized in that Based on the reduced-dimensional data, cluster analysis is performed to obtain N groups of reduced-dimensional load data corresponding to the maximum cluster number N, and the N groups of reduced-dimensional load data are upgraded, and based on the N groups of upgraded-dimensional load data, the corresponding cluster center curve is obtained, and the cluster center is a typical daily load curve, including: Import the dimension-reduced data into Matlab for cluster analysis to obtain the maximum number of clusters N and N groups of dimension-reduced load data corresponding to the maximum number of clusters N; Upgrading the dimension of each set of reduced-dimensional load data to obtain each set of upgraded-dimensional load data; A cluster center curve is obtained in each group of load data after dimensionality upgrade, wherein the cluster center is a typical daily load curve.

5. The method according to claim 1, characterized in that The elastic coefficient method is used to analyze the demand response potential of N groups of load curves after dimensional upgrading, and the response potential values ​​of peak time and valley time are obtained respectively, including: Get the Tiandi Electricity load in each period , calculate the first The average power load in each period ； based on Calculate the Elasticity coefficient of time period ； based on and Calculate the Load factor for each period ； based on and Calculate the response potential value during the peak period Response potential value during the valley period in, and They represent the peak period and valley period respectively. For each The maximum load factor of the time period, The first time in the day from 0:00 to 24:00 time periods, each time period is 1 hour long, and n is the total number of days of user load data.

6. The method according to claim 1, characterized in that Also includes: Before performing dimension reduction calculation on the historical power load data according to the pre-selected load characteristic index to obtain the dimension reduction data, the historical power load data is preprocessed, including: deleting abnormal values ​​in the historical power load data.

7. A virtual power plant demand response potential assessment system, characterized in that: include: A data acquisition module is used to acquire historical power load data within a preset time period; A dimension reduction calculation module, used to perform dimension reduction calculation on the historical power load data according to a pre-selected load characteristic index to obtain dimension reduction data; A cluster analysis module is used to perform cluster analysis based on the reduced-dimensionality data, obtain N groups of reduced-dimensionality load data corresponding to the maximum cluster number N, upgrade the N groups of reduced-dimensionality load data, and obtain the corresponding cluster center curve based on the N groups of upgraded-dimensional load data, wherein the cluster center is a typical daily load curve; The demand response potential analysis module is used to perform demand response potential analysis on N groups of up-dimensional load curves using the elastic coefficient method, and obtain the response potential values ​​for peak and valley periods respectively. The typical daily load curve is subtracted from the response potential value for the peak period or added to the response potential value for the valley period to obtain the adjusted response potential value curve.

8. The system according to claim 1, characterized in that The cluster analysis module includes: The cluster analysis unit is used to import the dimension reduction data into Matlab for cluster analysis, and obtain the maximum cluster number N and N groups of dimension reduction load data corresponding to the maximum cluster number N; A dimension-increasing unit, comprising: performing dimension-increasing on each set of reduced-dimensional load data to obtain each set of dimension-increasing load data; The typical daily load curve generating unit is used to obtain the cluster center curve in each group of load data after dimensionality upgrade, and the cluster center is the typical daily load curve.

9. A terminal, characterized in that: include: A memory for storing a virtual power plant demand response potential assessment program; A processor is used to implement the steps of the virtual power plant demand response potential assessment method as described in claims 1-6 when executing the virtual power plant demand response potential assessment program.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a virtual power plant demand response potential assessment program, which, when executed by a processor, implements the steps of the virtual power plant demand response potential assessment method as described in claims 1-6.

Images