A method, system, device and medium for extracting characteristics of load pattern changes

Abstract

The present invention belongs to the field of time-of-use electricity prices, and specifically relates to a method, system, device and medium for extracting characteristics of load pattern changes. First, the typical daily load curve of the user is calculated, and by comparing the difference in the total power consumption of the user before and after the implementation of the time-of-use electricity price, the price elasticity matrix is ​​fitted to restore the load when the user does not participate in the price-type demand response, thereby calculating the user load change under the time-of-use electricity price, and realizing accurate extraction of load pattern change characteristics under the action of the time-of-use electricity price. The application in the field of power systems is relatively novel and has good application effects. The user load data and the corresponding time-of-use electricity price information used in the present invention are relatively easy to obtain, so the extraction of load pattern change characteristics under the action of the time-of-use electricity price has the advantages of low cost, simple principle, good performance, and easy use.

Description

Technical Field

[0001] The present invention belongs to the field of system demand response, and in particular relates to a method, system, equipment and medium for extracting characteristics of load pattern changes. Background Art

[0002] Demand response is one of the important means to improve the flexible adjustment ability of the system. It aims to guide users to change their electricity consumption patterns by issuing electricity price signals or incentive signals, so that users can reduce or transfer loads during the peak load period of the system to achieve the purpose of peak shaving and valley filling. According to the specific types of signals released by demand response, demand response can be divided into price-based demand response and incentive-based demand response. Price-based demand response refers to the advance release of electricity price information to guide users to reduce electricity consumption when electricity prices are high and increase electricity consumption when electricity prices are low, such as peak and valley time-of-use electricity prices, peak electricity prices and real-time electricity prices; incentive-based demand response refers to signing a contract with users in advance to enable users to change their electricity consumption behavior during the period required by the system. With the continuous advancement of the marketization process, many provinces across the country have promulgated time-of-use electricity price policies, and it has become normal for users to participate in time-of-use electricity price projects. However, the degree of incentives received by users in different electricity price scenarios is different, resulting in different response depths. The diversity of user load curves and the randomness of user electricity consumption patterns have greatly increased. Scientifically analyzing the impact of time-of-use electricity price policies on users' energy consumption behavior and accurately extracting the changing characteristics of user load patterns under the influence of time-of-use electricity prices provide data support for the formulation of time-of-use electricity price policies, which is of great significance to the promotion and implementation of demand response projects.

[0003] At present, in the existing research on the impact of time-of-use electricity price policies on users' energy consumption behavior, key parameters are mostly determined by assumptions or by asking users to fill out survey reports. This method is difficult to accurately reflect the degree of influence of users on electricity prices, and cannot guarantee the accuracy and reliability of the extraction of user load pattern change characteristics. Summary of the invention

[0004] The present invention proposes a method, system, device and medium for extracting characteristics of load pattern changes to solve the problem in the prior art that key parameters are mostly determined by assumptions or by asking users to fill out survey reports, making it difficult to ensure accurate and reliable extraction of user load pattern change characteristics.

[0005] To achieve the above object, the present invention proposes the following technical solutions:

[0006] A method for extracting characteristics of load pattern changes comprises the following steps:

[0007] Step 1: Obtain user load data and time-of-use electricity price information, and calculate the user's typical daily load curve;

[0008] Step 2: Count the change ratio of the total daily electricity consumption of users before and after the implementation of the time-of-use electricity price, and fit the user price elasticity coefficient matrix according to the typical daily load curve of the user and the change ratio of the total daily electricity consumption of the user to obtain the fitting result;

[0009] Step 3: Obtain daily load data of users participating in time-of-use electricity prices, calculate the change in user load under the influence of time-of-use electricity prices based on the fitting results of the user price elasticity coefficient matrix and user load data, and extract load pattern change characteristics based on the change in user load under the influence of time-of-use electricity prices.

[0010] Preferably, in step 1, the user load data includes historical load data before and after the user participates in the time-of-use electricity price; the time-of-use electricity price information includes the peak, valley and normal period division and the time-of-use electricity price.

[0011] Preferably, in step 1, the specific process of calculating the typical daily load curve of the user is:

[0012] According to the user load data and time-of-use electricity price information, the average load value of each user per hour is calculated. According to the average load value of each user per hour, the typical load curve of the user is obtained. The result is expressed as:

[0013]

[0014] In the formula, For users The typical load curve is The value of the moment, For users In history sky The load value at the moment, The number of historical days.

[0015] Preferably, in step 2, the specific process of calculating the change ratio of the total daily electricity consumption of users before and after the implementation of the time-of-use electricity price is as follows:

[0016] Calculate the change in total daily electricity consumption, and the result is expressed as:

[0017]

[0018] In the formula, and They represent the average daily load of users before and after the implementation of time-of-use electricity prices,

[0019] The change ratio of the total daily electricity consumption of users before and after the implementation of time-of-use electricity prices is calculated, and the results are expressed as follows:

[0020]

[0021] Where α is the change ratio of the user’s daily total electricity consumption before and after the implementation of time-of-use electricity prices.

[0022] Preferably, in step 3, specifically: using the price elasticity matrix fitting results and the daily load data of users participating in the time-of-use electricity price, solve the load if the user does not participate in the time-of-use electricity price, and calculate the user load change under the influence of the daily time-of-use electricity price by subtracting it from the actual load measured by the electricity meter.

[0023] Preferably, in step 3, a k-means clustering algorithm is used to extract the characteristics of load pattern changes; in the process of extracting the characteristics of load pattern changes using the k-means clustering algorithm, the user load changes in each time period are regarded as continuous curves for clustering.

[0024] Preferably, in the process of calculating the percentage change in the total daily electricity consumption of users before and after the implementation of the time-of-use electricity price, the load data of the users for one month before and after participating in the time-of-use electricity price are obtained; the data sampling interval is 30 minutes.

[0025] A load pattern change feature extraction system includes the following modules:

[0026] The user's typical daily load curve calculation module is used to obtain user load data and time-of-use electricity price information and calculate the user's typical daily load curve;

[0027] The user price elasticity coefficient matrix fitting module is used to count the change ratio of the user's daily total electricity consumption before and after the implementation of the time-of-use electricity price, and to fit the user price elasticity coefficient matrix according to the user's typical daily load curve and the change ratio of the user's daily total electricity consumption to obtain the fitting result;

[0028] The load pattern change feature extraction module obtains the daily load data of users participating in the time-of-use electricity price, calculates the user load change under the influence of the time-of-use electricity price based on the fitting results of the user price elasticity coefficient matrix and the user load data, and extracts the load pattern change characteristics based on the user load change under the influence of the time-of-use electricity price.

[0029] A load mode change feature extraction device comprises a memory, at least one processor, a computer program stored in the memory and executable on the at least one processor, and at least one communication bus.

[0030] The memory may be used to store the computer program, and the processor implements the steps of the load pattern change feature extraction method by running or executing the computer program stored in the memory and calling the data stored in the memory.

[0031] A load pattern change feature extraction medium includes a computer program. When the computer program is executed by a processor, the steps of a load pattern change feature extraction method are implemented.

[0032] The present invention is beneficial in that:

[0033] Calculate the user's typical daily load curve, compare the difference in total user electricity consumption before and after the implementation of time-of-use electricity prices, fit the price elasticity matrix, and restore the load when the user does not participate in price-based demand response, thereby calculating the user's load change under time-of-use electricity prices, and accurately extracting the load pattern change characteristics under the action of time-of-use electricity prices. The application in the field of power systems is relatively novel and has good application effects.

[0034] The user load data and corresponding time-of-use electricity price information used in the present invention are relatively easy to obtain, so the extraction of load pattern change characteristics under the action of time-of-use electricity prices has the advantages of low cost, simple principle, good performance, and easy use. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0036] Figure 1 It is a flow chart of a method for extracting characteristics of load pattern changes under the action of time-of-use electricity price according to the present invention;

[0037] Figure 2 This is a clustering result diagram of the load change curves of users at different times in an embodiment of the present invention.

[0038] Figure 3 Schematic diagram of a load pattern change feature extraction device. DETAILED DESCRIPTION

[0039] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0040] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.

[0041] Embodiment 1:

[0042] See also Figure 1 As shown, the present invention provides a method for extracting load pattern change characteristics, comprising the following steps:

[0043] Step 1: Obtain user load data and corresponding time-of-use electricity price information, and calculate the user's typical daily load curve;

[0044] Specifically, step 1 includes:

[0045] Step 11, obtaining user load data and corresponding time-of-use electricity price information: the user load data includes historical load data before and after the user participates in the time-of-use electricity price, and the time-of-use electricity price information includes the peak, valley and normal period division and the corresponding time-of-use electricity price.

[0046] Step 12, based on the user load data and the corresponding time-of-use electricity price information, calculate the user's typical daily load curve: calculate the average load value of each user in each hour, and obtain the typical load curve of the user based on the average load value of each user in each hour. The result is expressed as:

[0047]

[0048] in: For users The typical load curve is The value of the moment, For users In history sky The load value at the moment, is the number of historical days included in the dataset.

[0049] Step 2: Count the change ratio of the total daily electricity consumption of users before and after the implementation of the time-of-use electricity price, and fit the user price elasticity coefficient matrix;

[0050] Specifically, step 2 includes:

[0051] Step 21, calculate the change ratio of the user's daily electricity consumption before and after the implementation of the time-of-use electricity price: accumulate the user's load at each time of the day to obtain the user's daily electricity consumption. Calculate the user's daily electricity consumption for a period of time before and after the time-of-use electricity price is implemented. and They represent the average daily load before and after the user participates in price-based demand response, and the difference between them is the change in the total daily electricity consumption. The result is expressed as:

[0052]

[0053] The change ratio of the total daily electricity consumption of users before and after the implementation of time-of-use electricity prices is calculated, and the results are expressed as follows:

[0054]

[0055] Step 22, fitting the user price elasticity coefficient matrix: fitting the user price elasticity coefficient matrix based on the change ratio of the user's daily total electricity consumption, the typical daily load curve and the actual electricity price information.

[0056] Step 3: Calculate the load when the user does not participate in price-based demand response and the load change of the user under the influence of time-of-use electricity price, and use k-means clustering algorithm to extract the load pattern change characteristics based on the load change in each period;

[0057] Specifically, step 3 includes:

[0058] Step 31, calculate the load when the user does not participate in the price-based demand response and the load change of the user under the influence of the time-of-use electricity price: use the price elasticity matrix fitting result and the daily load data of the user participating in the time-of-use electricity price to solve the load when the user does not participate in the price-based demand response, and calculate the load change of the user under the influence of the daily time-of-use electricity price by subtracting it from the actual load measured by the meter;

[0059] Step 32, 4 uses the k-means clustering algorithm to extract the load pattern change characteristics based on the load change in each time period: the k-means clustering algorithm is used to cluster the load change curves of users at each time of each day within a period of time to obtain the typical characteristics of user load pattern changes.

[0060] Specifically, in the process of calculating the percentage change in users' total daily electricity consumption before and after the implementation of time-of-use electricity prices, taking into account that electricity price information is updated once a month, a period of time is taken as one month.

[0061] Specifically, in the process of fitting the user price elasticity coefficient matrix, the proportion calculated in step ③ is used as a supplementary condition, and the equation for the total daily electricity consumption of the user is added to fit the user price elasticity coefficient.

[0062] Specifically, in the process of extracting the load pattern change characteristics using the k-means clustering algorithm, the user load change in each time period is regarded as a continuous curve for clustering.

[0063] Embodiment 2:

[0064] In this embodiment, a resident user in a certain area is randomly selected as the research object, and the specific process is as follows:

[0065] Step 1: Obtain user load data and corresponding time-of-use electricity price information, and calculate the user's typical daily load curve based on the user's historical load data.

[0066] The step 1 specifically comprises the following steps:

[0067] Step 11: The user load data includes the historical load data before and after the user participates in the time-of-use electricity price. The time-of-use electricity price information includes the peak, valley and normal period division and the corresponding time-of-use electricity price. Obtain the load data of residential users for one month before and after participating in the time-of-use electricity price, with a data sampling interval of 30 minutes. The corresponding peak periods are 07:00-17:00 and 23:00-24:00, the normal period is 18:00-22:00, and the valley period is 00:00-06:00. The peak, valley and normal period electricity prices are 67.20 pence / kWh, 3.99 pence / kWh, and 11.76 pence / kWh respectively.

[0068] Step 12: Calculate the average load value of the user in each hour as the typical load curve of the user. The result is expressed as:

[0069]

[0070] in: For users The typical load curve is The value of the moment, For users In history sky The load value at the moment, is the number of historical days included in the dataset.

[0071] Step 2: Calculate the difference in the total daily electricity consumption of users before and after the time-of-use electricity price, and calculate the total electricity consumption change ratio. Based on the total electricity consumption change ratio, typical daily load curve and electricity price information, fit the price elasticity coefficient matrix;

[0072] The step 2 specifically comprises the following steps:

[0073] Step 21: Accumulate the user's load at each time of the day to obtain the user's total daily electricity consumption. Calculate the user's total daily electricity consumption before and after participating in the time-of-use electricity price. and They represent the average daily load before and after the user participates in price-based demand response, and the difference between them is the change in the total daily electricity consumption. The result is expressed as:

[0074]

[0075] The change ratio of the total daily electricity consumption of users before and after the implementation of time-of-use electricity prices is calculated, and the results are expressed as follows:

[0076]

[0077] In this embodiment, The calculated result is 0.247082 kWh, The calculated result is 0.232854kWh, The calculated result is 0.014228 kWh, The calculated result is 0.057584.

[0078] Step 22: Fit the user price elasticity coefficient matrix based on the user's daily electricity consumption change ratio, typical daily load curve and actual electricity price information. Assume and Represents the users before and after participating in price-based demand response The load value at the moment. Then, the total load change result in step ③ can be used to supplement the equation as follows, thereby fitting the user price elasticity coefficient matrix:

[0079]

[0080] Step 3: According to the price elasticity coefficient matrix, calculate the load when the user does not participate in price-based demand response and the load change under the influence of time-of-use electricity prices, and use a clustering algorithm to extract the load pattern change characteristics based on the load change in each period.

[0081] The step 3 specifically comprises the following steps:

[0082] Step 31: Using the price elasticity matrix fitting results and the daily load data of users participating in the TOU electricity price, solve the load when the user does not participate in the price-based demand response, and calculate the user load change under the influence of the daily TOU electricity price by subtracting it from the actual load measured by the meter.

[0083] Step 32: Based on the load changes in each period, use the k-means clustering algorithm to extract the load pattern change characteristics

[0084] The k-means clustering algorithm is used to cluster the load change curves of users at different times of the day within a period of time to obtain the typical characteristics of the user load pattern changes. In this embodiment, the load change curves of users at different times of the day are clustered into 4 categories. The clustering results are as follows: Figure 2 As shown. It can be seen that the load pattern change characteristics of the user when affected by the time-of-use electricity price can be summarized as follows Figure 2 Four typical modes are shown.

[0085] Embodiment 3:

[0086] A load pattern change feature extraction system specifically includes a user typical daily load curve calculation module, a user price elasticity coefficient matrix fitting module and a load pattern change feature extraction module, wherein:

[0087] The user typical daily load curve calculation module is used to implement step 1 described in Example 1: obtaining user load data and corresponding time-of-use electricity price information, wherein the user load data includes historical load data before and after the user participates in the time-of-use electricity price, and the time-of-use electricity price information includes the peak, valley and normal period division and the corresponding time-of-use electricity price; calculating the user's typical daily load curve according to the user load data and the corresponding time-of-use electricity price information: calculating the average load value of each user in each hour, and obtaining the typical load curve of the user according to the average load value of each user in each hour, and the result is expressed as:

[0088]

[0089] in: For users The typical load curve is The value of the moment, For users In history sky The load value at the moment, is the number of historical days included in the dataset.

[0090] The user price elasticity coefficient matrix fitting module is used to implement step 2 described in Example 1, accumulating the user's load at each time of the day to obtain the user's daily total electricity consumption. Calculate the user's daily total electricity consumption before and after participating in the time-of-use electricity price. and They represent the average daily load before and after the user participates in price-based demand response, and the difference between them is the change in the total daily electricity consumption. The result is expressed as:

[0091]

[0092] The change ratio of the total daily electricity consumption of users before and after the implementation of time-of-use electricity prices is calculated, and the results are expressed as follows:

[0093]

[0094] The user price elasticity coefficient matrix is ​​fitted based on the change ratio of the user's daily electricity consumption, the typical daily load curve and the actual electricity price information. and Represents the users before and after participating in price-based demand response The load value at the moment. Then the total load change result can be used to supplement the equation as follows, thereby fitting the user price elasticity coefficient matrix;

[0095] The load pattern change feature extraction module is used to implement step 3 described in Example 1. It uses the price elasticity matrix fitting results and the daily load data of users participating in time-of-use electricity prices to solve the load when the user does not participate in price-based demand response, and calculates the user's load change under the influence of daily time-of-use electricity prices by subtracting it from the actual load measured by the meter; based on the load change in each time period, the k-means clustering algorithm is used to extract the load pattern change characteristics, and the k-means clustering algorithm is used to cluster the load change curves of users at each time of the day within a period of time to obtain typical characteristics of user load pattern changes.

[0096] Embodiment 4:

[0097] See also Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a method for extracting characteristics of load pattern changes; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0098] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for obtaining parking spaces described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0099] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0100] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for extracting characteristics of load pattern changes, and the processor 102 can execute the plurality of instructions to implement:

[0101] Obtain user load data and corresponding time-of-use electricity price information, the user load data includes historical load data before and after the user participates in the time-of-use electricity price, the time-of-use electricity price information includes the peak, valley and normal period division and the corresponding time-of-use electricity price; calculate the user's typical daily load curve according to the user load data and the corresponding time-of-use electricity price information: calculate the average load value of each user in each hour, and obtain the typical load curve of the user according to the average load value of each user in each hour, and the result is expressed as:

[0102]

[0103] in: For users The typical load curve is The value of the moment, For users In history sky The load value at the moment, is the number of historical days included in the dataset.

[0104] The total daily electricity consumption of the user is obtained by summing up the load at each time of the day. The total daily electricity consumption of the user before and after the time-of-use electricity price is calculated respectively. and They represent the average daily load before and after the user participates in price-based demand response, and the difference between them is the change in the total daily electricity consumption. The result is expressed as:

[0105]

[0106] The change ratio of the total daily electricity consumption of users before and after the implementation of time-of-use electricity prices is calculated, and the results are expressed as follows:

[0107]

[0108] The user price elasticity coefficient matrix is ​​fitted based on the change ratio of the user's daily electricity consumption, the typical daily load curve and the actual electricity price information. and Represents the users before and after participating in price-based demand response The load value at the moment. Then the total load change result can be used to supplement the equation as follows, thereby fitting the user price elasticity coefficient matrix;

[0109] By using the fitting results of the price elasticity matrix and the daily load data of users participating in time-of-use electricity prices, the load when the user does not participate in price-based demand response is solved, and the user load change under the influence of daily time-of-use electricity prices is calculated by subtracting it from the actual load measured by the meter; based on the load change in each time period, the k-means clustering algorithm is used to extract the load pattern change characteristics, and the k-means clustering algorithm is used to cluster the load change curves of users at each time of the day within a period of time, and the typical characteristics of user load pattern changes are obtained.

[0110] Embodiment 5:

[0111] If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0112] The advantage of the present invention is that the method for extracting the characteristics of load pattern changes under the action of time-of-use electricity prices provided by the present invention first calculates the typical daily load curve of the user, and by comparing the difference in the total electricity consumption of the user before and after the implementation of the time-of-use electricity price, fits the price elasticity matrix, and restores the load when the user does not participate in the price-type demand response, thereby calculating the user's load change under the time-of-use electricity price, and realizing accurate extraction of the characteristics of load pattern changes under the action of time-of-use electricity price. The application in the field of power systems is relatively novel and has good application effects.

[0113] The user load data and corresponding time-of-use electricity price information used in the present invention are relatively easy to obtain, so the extraction of load pattern change characteristics under the action of time-of-use electricity prices has the advantages of low cost, simple principle, good performance, and easy use.

[0114] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.

[0115] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0117] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for extracting characteristics of load pattern changes, characterized in that: The steps include: Step 1: Obtain user load data and time-of-use electricity price information, and calculate the user's typical daily load curve; Step 2: Count the change ratio of the total daily electricity consumption of users before and after the implementation of the time-of-use electricity price, and fit the user price elasticity coefficient matrix according to the typical daily load curve of the user and the change ratio of the total daily electricity consumption of the user to obtain the fitting result; Step 3, obtaining daily load data of users participating in the time-of-use electricity price, calculating the user load change under the influence of the time-of-use electricity price based on the fitting result of the user price elasticity coefficient matrix and the user load data, and extracting the load pattern change characteristics based on the user load change under the influence of the time-of-use electricity price; The typical daily load curve of the user is expressed as: In the formula, For users The typical daily load curve is The value of the moment, For users In history sky The load value at the moment, is the number of historical days; In step 2, the specific process of calculating the change ratio of the total daily electricity consumption of users before and after the implementation of the time-of-use electricity price is as follows: Step 21: Calculate the change in total daily electricity consumption. The result is expressed as: In the formula, and They represent the average daily load of users before and after the implementation of time-of-use electricity prices, The change ratio of the total daily electricity consumption of users before and after the implementation of time-of-use electricity prices is calculated, and the results are expressed as follows: In the formula, α is the change ratio of the total daily electricity consumption of users before and after the implementation of time-of-use electricity prices; Then, the supplementary equation is obtained by using the change ratio of the user's daily total electricity consumption as follows: in, and Represents the users before and after participating in price-based demand response The load value at the moment; Step 22: fitting the user price elasticity coefficient matrix based on the change ratio of the user's daily total electricity consumption before and after the implementation of the time-of-use electricity price, the typical daily load curve, the actual electricity price information and the supplementary equation; In step 3, specifically: using the price elasticity matrix fitting results and the daily load data of users participating in the time-of-use electricity price, solve the load if the user does not participate in the time-of-use electricity price, and calculate the user load change under the influence of the daily time-of-use electricity price by subtracting it from the actual load measured by the meter.

2. A method for extracting characteristics of load pattern changes according to claim 1, characterized in that: In step 1, the user load data includes historical load data before and after the user participates in the time-of-use electricity price; the time-of-use electricity price information includes the peak, valley and normal period division and the time-of-use electricity price.

3. A method for extracting characteristics of load pattern changes according to claim 1, characterized in that: In step 3, the k-means clustering algorithm is used to extract the load pattern change characteristics; In the process of extracting the load pattern change characteristics using the k-means clustering algorithm, the user load changes in each period are regarded as continuous curves for clustering.

4. A method for extracting characteristics of load pattern changes according to claim 1, characterized in that: In the process of calculating the percentage change in users' daily electricity consumption before and after the implementation of time-of-use electricity prices, the load data of users for one month before and after participating in the time-of-use electricity prices are obtained; the data sampling interval is 30 minutes.

5. A load pattern change feature extraction system for implementing the load pattern change feature extraction method according to any one of claims 1 to 4, characterized in that: Includes the following modules: The user's typical daily load curve calculation module is used to obtain user load data and time-of-use electricity price information and calculate the user's typical daily load curve; The user price elasticity coefficient matrix fitting module is used to count the change ratio of the user's daily total electricity consumption before and after the implementation of the time-of-use electricity price, and to fit the user price elasticity coefficient matrix according to the user's typical daily load curve and the change ratio of the user's daily total electricity consumption to obtain the fitting result; The load pattern change feature extraction module obtains the daily load data of users participating in the time-of-use electricity price, calculates the user load change under the influence of the time-of-use electricity price based on the fitting results of the user price elasticity coefficient matrix and the user load data, and extracts the load pattern change characteristics based on the user load change under the influence of the time-of-use electricity price.

6. A load pattern change feature extraction device, characterized in that: include: An electronic device (100), comprising a memory (101), at least one processor (102), a computer program (103) stored in the memory (101) and executable on the at least one processor (102), and at least one communication bus (104); The memory (101) can be used to store the computer program (103), and the processor (102) implements the steps of the load pattern change feature extraction method described in any one of claims 1 to 4 by running or executing the computer program stored in the memory (101) and calling the data stored in the memory (101).

7. A load pattern change feature extraction medium, characterized in that: The medium includes a computer program, and when the computer program is executed by a processor, the steps of the load pattern change feature extraction method according to any one of claims 1 to 4 are implemented.

Images