A method and device for evaluating user-side demand response potential based on a power grid

Abstract

The application discloses a kind of based on power grid's user side demand response potential evaluation method and device.The main technical scheme of the application is: on the user side power consumption, obtain the historical power consumption data of each user, the historical power consumption data is handled using preset clustering model, and the historical daily load curve of different categories of users is fitted to obtain;Different categories of users corresponding historical daily load curve is handled using preset power load prediction model, and the power load prediction data corresponding to different categories of users is output;Finally, according to the maximum and minimum of historical daily load curve, in combination with the predicted power load prediction data, the peak shaving potential or valley filling potential executable in the future time range is determined, which is equivalent to the potential of the amount of electricity that can be reduced at the peak of power grid demand or high electricity price, or the potential of the amount of electricity that can be increased at low electricity price, applied to evaluate the potential of user side demand response based on power grid.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a method and apparatus for evaluating the user-side demand response potential of a power grid. Background Technology

[0002] In a power system, user-side demand refers to the amount of electricity consumed by users at different times. This demand can be rigid, such as the use of residential lighting and air conditioning at night; or it can be flexible, such as discontinuous processes in industrial production.

[0003] User-side demand response, based on user-side demand, refers to users voluntarily reducing or delaying a portion of their electricity demand and adjusting their electricity consumption plans to respond to the grid's supply and demand balance, in accordance with grid demand and price signals. Correspondingly, the demand response potential realized based on user-side demand response refers to the potential for users to reduce electricity consumption during peak grid demand or when electricity prices are high, or the potential to increase electricity consumption when electricity prices are low.

[0004] The goal of utilizing both of these potentials is to achieve a balance between supply and demand in the entire power system and ensure its stability. Therefore, how to effectively assess the demand response potential on the user side is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] In view of this, this application provides a method and apparatus for assessing user-side demand response potential based on the power grid. The main purpose is to use historical electricity consumption data to intelligently classify users and intelligently determine the peak shaving or valley filling potential of each user category in the future time range, thereby assessing the user's demand response potential based on the power grid and providing an effective solution for measuring and assessing user-side demand response potential.

[0006] To achieve the above objectives, this application mainly provides the following technical solutions:

[0007] The first aspect of this application provides a method for assessing the user-side demand response potential of a power grid, the method comprising:

[0008] On the user-side power consumption, historical power consumption data for each user is obtained. The historical power consumption data includes at least power consumption, power consumption time, and daily load data. The daily load data includes load information at different times on different dates.

[0009] The historical electricity consumption data is processed using a pre-set clustering model to obtain historical daily load curves for different categories of users, including low-load users, medium-load users, and high-load users.

[0010] The historical daily load curves corresponding to different categories of users are processed using a pre-set power load forecasting model, and the power load forecast data corresponding to different categories of users are output.

[0011] For different categories of users, based on the maximum and minimum values ​​on the historical daily load curves, and combined with the electricity load forecast data, the peak shaving potential or valley filling potential corresponding to the users in the future time range is determined.

[0012] Assess the grid-based demand response potential of the user based on the peak shaving or valley filling potential corresponding to the user in the future time frame.

[0013] A second aspect of this application provides an apparatus for assessing the user-side demand response potential of a power grid, the apparatus comprising:

[0014] The acquisition unit is used to acquire historical electricity consumption data for each user on the user side. The historical electricity consumption data includes at least electricity consumption, electricity consumption time and daily load data. The daily load data includes load information at different times on different dates.

[0015] The first processing unit is used to process the historical electricity consumption data using a pre-set clustering model to obtain historical daily load curves corresponding to different categories of users, including low-load users, medium-load users, and high-load users.

[0016] The second processing unit is used to process the historical daily load curves corresponding to different categories of users using a preset power load prediction model, and output the power load prediction data corresponding to different categories of users.

[0017] The determination unit is used to determine the peak shaving potential or valley filling potential of different types of users in the future time range based on the maximum and minimum values ​​on the historical daily load curve and the electricity load forecast data.

[0018] An assessment unit is used to assess the user's grid-based demand response potential based on the user's peak shaving or valley filling potential over a future time horizon.

[0019] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for assessing the user-side demand response potential based on the power grid.

[0020] A fourth aspect of this application provides an electronic device, the device including at least one processor, and at least one memory and bus connected to the processor;

[0021] The processor and the memory communicate with each other via the bus.

[0022] The processor is used to invoke program instructions in the memory to execute the above-described method for assessing the user-side demand response potential based on the power grid.

[0023] By employing the above-described technical solution, the technical solution provided in this application has at least the following advantages:

[0024] This application provides a method and apparatus for assessing the user-side demand response potential of a power grid. Regarding user-side electricity consumption, this application acquires historical electricity consumption data for each user. This historical electricity consumption data includes at least electricity consumption, consumption time, and load information at different times on different dates. First, a pre-set clustering model is used to process the historical electricity consumption data, obtaining historical daily load curves for three categories of users: low-load users, medium-load users, and high-load users. This achieves the first processing of a large amount of historical data, classifying users and generating historical daily load curves for each category. The second processing involves using a pre-set power load forecasting model to assess the demand response potential of different user categories. The historical daily load curves are processed to output electricity load forecast data for different categories of users. Finally, for different categories of users, based on the maximum and minimum values ​​on the historical daily load curves, and combined with the predicted electricity load forecast data, this is equivalent to comparing and analyzing the historical and predicted electricity consumption habits of the same category of users. Under the premise of meeting the basic needs of users, the potential for peak shaving or valley filling in the future time range is determined. For example, the potential for users to reduce electricity consumption when grid demand is high or electricity prices are high, or the potential for increasing electricity consumption when electricity prices are low. This is applied to evaluate the user-side demand response potential based on the grid.

[0025] Compared to existing requirements for effectively assessing user-side demand response potential, this application uses model clustering and model prediction to divide massive numbers of users into three categories. For each user category, the maximum and minimum values ​​on historical daily load curves are compared with electricity load forecast data to convert them into quantifiable peak-shaving or valley-filling potential for electricity consumption in the future time range. This quantification is then applied to assess grid-based user-side demand response potential, thus providing an effective solution for measuring and assessing user-side demand response potential.

[0026] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0027] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0028] Figure 1 A flowchart illustrating a method for assessing user-side demand response potential based on a power grid, as provided in this application embodiment;

[0029] Figure 2 A flowchart illustrating another method for assessing user-side demand response potential based on a power grid, provided in an embodiment of this application;

[0030] Figure 3 A block diagram illustrating the composition of a power grid-based user-side demand response potential assessment device provided in this application embodiment;

[0031] Figure 4 A block diagram of another power grid-based user-side demand response potential assessment device provided in this application embodiment. Detailed Implementation

[0032] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0033] Accurate assessment of demand response potential is crucial for power grid dispatching departments to formulate scientific and reasonable dispatching plans, and is of great significance to all stakeholders involved in the implementation of demand response.

[0034] Currently, constrained by factors such as energy conservation and emission reduction targets and rising prices of primary energy sources like coal, the power system, which is primarily based on thermal power generation, is transitioning to one dominated by renewable energy generation. A significant characteristic of a power system with a high proportion of renewable energy penetration is its high volatility, thus requiring more reserve capacity to ensure system reliability. However, the declining proportion of coal in power generation means reduced reserve capacity on the generation side, making demand-side regulation resources even more crucial.

[0035] Therefore, the inventors, through research, believe that demand-side resources that actively participate in grid regulation can effectively alleviate the regulation pressure on the power supply side and the grid side. For example, by assessing the user-side demand response potential based on the grid, that is, realizing the grid-based "peak shaving potential" and "valley filling potential", the power system can achieve supply and demand balance and ensure its stability.

[0036] This application provides a method for assessing the user-side demand response potential of a power grid, such as... Figure 1 As shown, the following specific steps are provided in this embodiment of the invention:

[0037] 101. On the user side, obtain the historical electricity consumption data for each user. The historical electricity consumption data includes at least the amount of electricity consumed, the time of electricity consumption, and the daily load data. The daily load data includes the load information at different times on different dates.

[0038] This application embodiment aims to acquire historical electricity consumption data from a massive number of users, including various types such as residential, commercial, and industrial users. Since different types of users have different electricity demands, their demand response potential also varies. This application embodiment aims to achieve a comprehensive assessment of user-side demand response potential based on the power grid; therefore, when acquiring historical electricity consumption data, it specifically considers covering multiple user types. Below are examples of different user types and their user-side electricity demand characteristics and demand response characteristics, including but not limited to the following:

[0039] (1) Residential users

[0040] Demand: The main electricity demand of residential users is to reduce electricity costs and increase autonomy in electricity use. Electricity consumption includes lighting, household appliances (such as refrigerators, washing machines, air conditioners, etc.), and water heaters.

[0041] Demand response: Residential users can participate in demand response by reducing non-essential electricity consumption (such as turning off unnecessary lights and lowering air conditioner temperature settings) and using smart sockets to use high-energy-consuming devices when electricity prices are low.

[0042] (2) Business users

[0043] Demand: Commercial users' electricity needs are to reduce operating costs and improve power supply reliability. Electricity usage includes commercial lighting, air conditioning systems, elevators, and commercial display equipment.

[0044] Demand Response: Commercial users can participate in demand response by adjusting business hours, optimizing the use of air conditioning and lighting systems, and participating in demand response pricing programs.

[0045] (3) Industrial users

[0046] Demand: Industrial users' electricity needs are to reduce operating costs and ensure production continuity. Electricity consumption typically includes production equipment, machining, assembly lines, heating and cooling systems, etc.

[0047] Demand response: Industrial users can participate in demand response by adjusting production plans, using backup generators, or participating in the demand response market.

[0048] 102. A pre-set clustering model is used to process historical electricity consumption data to obtain historical daily load curves for different categories of users, including low-load users, medium-load users, and high-load users.

[0049] The pre-built clustering model used in this application embodiment can be trained using, but is not limited to, multiple clustering algorithms such as K-Means, DBSCAN, and SpectralClustering. The purpose is to analyze and process the historical electricity consumption data of a massive number of users. In the processing, the historical electricity consumption data of the massive number of users is first converted into historical daily load curves for each user on different dates. Then, further clustering processing is performed to divide the massive number of users into three categories, such as low-load users, medium-load users, and high-load users, and to obtain the historical daily load curves for each category of users. Then, the clustering processing of the model is used to remove redundancy and useless data from the massive and complex data, fit the classification, and obtain the fitted historical daily load curves for each category of users, thereby measuring the electricity consumption trend curves of each category of users at different times of the day.

[0050] In this embodiment of the application, this step is equivalent to performing the first processing of a large amount of historical data to achieve user classification and historical daily load curves for various categories of users.

[0051] 103. Use a pre-set power load forecasting model to process the historical daily load curves of different types of users and output the power load forecast data of different types of users.

[0052] The pre-set power load forecasting model can be trained using machine learning, and meteorological data at different times on different dates can be added during the training process to increase the accuracy of the trained model in predicting power load.

[0053] In this embodiment of the application, this step is equivalent to performing a second processing step, which involves using a pre-set power load prediction model to process the historical daily load curves corresponding to different types of users in order to predict the power load forecast data of different types of users in the future time range.

[0054] 104. For different types of users, based on the maximum and minimum values ​​on the historical daily load curves, and in conjunction with electricity load forecast data, determine the peak shaving potential or valley filling potential of the users in the future time range.

[0055] 105. Assess the user's grid-based demand response potential based on the user's peak shaving or valley filling potential over a future time horizon.

[0056] For example, 104-105 is equivalent to comparing and analyzing the historical and predicted electricity consumption habits of users in the same category, and determining the feasible peak shaving or valley filling potential in the future time frame while meeting the basic needs of users (such as rigid demand, without affecting the users' daily basic electricity needs).

[0057] For different types of users, user-side demand refers to the amount of electricity consumed by users in different time periods. This demand can be rigid, such as the use of residential nighttime lighting and air conditioning; or it can be flexible, such as discontinuous processes in industrial production. User-side demand response, based on user-side demand, refers to users voluntarily reducing or delaying a portion of their electricity demand and adjusting their electricity consumption plans according to the grid's demand and price signals, thereby responding to the grid's supply and demand balance. Therefore, after meeting certain essential user needs, this user-side demand response is adjustable. Accordingly, this application's embodiments utilize "user-side demand response potential" to evaluate the extent to which the "user-side demand response" can be adjusted.

[0058] For example, embodiments of this application may be characterized by, but are not limited to, “peak shaving potential” and “valley filling potential”. “Peak shaving potential” refers to the ability to reduce electricity consumption during peak hours (adjusting reserve capacity downwards); “valley filling potential” refers to the ability to increase electricity consumption during off-peak hours (adjusting reserve capacity upwards).

[0059] Specifically, to obtain the "peak shaving potential" and "valley filling potential," this application embodiment estimates them separately for different categories of users. For example, for each category of users, this application embodiment uses the maximum and minimum values ​​on the historical daily load curve corresponding to that category of users within the future time range corresponding to the electricity load forecast data obtained by model 103. Since the historical daily load curve obtained based on model 102 represents the high-probability electricity consumption behavior of a category of users, there will not be much difference within this future time range. Furthermore, the predicted electricity load data represents the necessary demand that can be met.

[0060] Therefore, this application embodiment uses the maximum and minimum values ​​on the historical daily load curves of this type of user, and compares them with the predicted electricity load data, to see that some electricity consumption is unnecessary, i.e., "peak shaving", while some electricity consumption is in a trough, and electricity capacity can be increased, i.e., "valley filling", thereby achieving a balance between supply and demand in the entire power system and ensuring its stability.

[0061] The above embodiments of this application provide a method for assessing the user-side demand response potential based on the power grid. Regarding user-side electricity consumption, this application embodiment obtains historical electricity consumption data for each user. This historical electricity consumption data includes at least electricity consumption, consumption time, and load information at different times on different dates. First, a pre-set clustering model is used to process the historical electricity consumption data, obtaining historical daily load curves for three categories of users: low-load users, medium-load users, and high-load users. This achieves the first processing of a large amount of historical data, realizing user classification and historical daily load curves for various categories of users. The second processing involves using a pre-set power load forecasting model to analyze the different categories of users... The historical daily load curves of users are processed to output electricity load forecast data for different categories of users. Finally, for different categories of users, the maximum and minimum values ​​on the historical daily load curves are combined with the predicted electricity load data. This is equivalent to comparing and analyzing the historical and predicted electricity consumption habits of the same category of users. Under the premise of meeting the basic needs of users, the potential for peak shaving or valley filling in the future time range is determined. For example, the potential for users to reduce electricity consumption when the grid demand is high or the electricity price is high, or the potential for increasing electricity consumption when the electricity price is low. This is used to evaluate the user-side demand response potential based on the grid.

[0062] Compared to existing requirements for effectively assessing user-side demand response potential, the embodiments of this application, through model clustering and model prediction processing, divide massive numbers of users into three categories. For different user categories, the maximum and minimum values ​​on historical daily load curves are compared with electricity load forecast data to convert them into quantifiable peak-shaving or valley-filling potential for electricity consumption in the future time range. This is then applied to assess the grid-based user-side demand response potential, thereby providing an effective solution for measuring and assessing user-side demand response potential through the quantification achieved by peak-shaving or valley-filling potential.

[0063] To provide a more detailed explanation of the above embodiments, this application also provides another method for assessing the user-side demand response potential based on the power grid, such as... Figure 2 As shown, the following specific steps are provided in this embodiment of the application:

[0064] 201. On the user side, obtain the historical electricity consumption data for each user. The historical electricity consumption data includes at least the electricity consumption, electricity consumption time and daily load data. The daily load data includes load information at different times on different dates.

[0065] In the embodiments of this application, the explanation of this step is provided in 101, and will not be repeated here.

[0066] 202. Based on the date and different times on the date, establish a multi-level index, process the historical electricity consumption data, and fit the historical daily load curve corresponding to each user on different dates.

[0067] This application embodiment involves preprocessing historical electricity consumption data, such as removing missing values, filling in missing values, and removing outliers, to improve data quality. Then, date and time features are extracted from the preprocessed historical electricity consumption data. Furthermore, based on the correlation between date and time, such as which times (i.e., moments) exist on a certain date, a multi-level index is constructed based on the date features, time features, and the correlation between them to obtain historical electricity load at certain times on a certain date. This allows for the fitting of historical daily load curves for each user on different dates.

[0068] 203. A pre-defined clustering algorithm is used to process the historical daily load curves of each user on different dates to obtain the historical daily load curves of different categories of users, including low-load users, medium-load users, and high-load users.

[0069] The pre-defined clustering algorithm can be, but is not limited to, the Gaussian Mixture Model (GMM) clustering algorithm, which processes the historical daily load curves corresponding to each user on different dates, dividing users into three categories. These three categories are typically based on the curve characteristics represented by the historical daily load curves.

[0070] Users are categorized based on similarities in electricity consumption patterns or load demand. For example, they can be divided into three categories: low-load users, medium-load users, and high-load users. The characteristics of these three categories are listed below, and may include, but are not limited to, the following:

[0071] (1) Low-load users:

[0072] These types of users typically exhibit low daily load curves, indicating relatively low electricity demand. They are likely primarily residential or small commercial users, whose electricity consumption behavior is relatively stable and less affected by factors such as time and season.

[0073] (2) Medium-load users:

[0074] The daily load curve of this type of user will fluctuate to some extent throughout the day, but the overall load level is moderate; they may include medium-sized commercial users, light industrial users, or some residential communities; the electricity consumption behavior of this type of user may be affected by a variety of factors such as working hours, seasonal changes, and weather conditions.

[0075] (3) High-load users:

[0076] These users typically exhibit high daily load curves with significant fluctuations; they are likely to be large industrial users, data centers, hospitals, and other critical infrastructure users; these users usually have high electricity demand and require high power quality and stability.

[0077] According to 202a and 203a, the embodiments of this application adopt a two-step progressive operation to improve data quality. For example, the historical electricity consumption data of a large number of users are analyzed and processed. In the processing, the historical electricity consumption data of the large number of users is first converted into the historical daily load curve of each user on different dates. Then, further clustering processing is performed to divide the large number of users into three categories, such as low load users, medium load users and high load users, and the historical daily load curve of each category of users.

[0078] Then, by using the clustering process of the model, the massive and complex data is dereduplicated, useless data is removed, and the data is fitted and classified to obtain the fitted historical daily load curve for each category of users, so as to measure the electricity consumption trend curve of each category of users at different times of the day.

[0079] 204. For each category of user, the load data at different times on different dates represented by the historical daily load curve are transformed to obtain the corresponding time series data. The time series data contains combined data sorted by date, and each combined data contains the power load data at different times on the date.

[0080] 205. The time series data is processed using a pre-trained XGBoost framework to output electricity load forecast data for the future time range.

[0081] In this embodiment, a pre-trained power load prediction model is used. During model training, historical power load data is employed. Since historical power load data includes daily power load and power load at different times each day, it is essentially time-series data. This embodiment uses time-series data as samples and employs machine learning (such as the XGBoost framework) to train the model, thereby transforming time-series training into supervised learning model training. A preferred implementation is to increase the data dimension of the time-series data during model training, such as by adding meteorological data, so that the model also considers meteorological factors in its prediction applications, thus improving the accuracy of model predictions.

[0082] As in 202b-203b, embodiments of this application process each category of user separately to obtain electricity load forecast data for each category of user over a future time range. In fact, this electricity load forecast data can characterize the electricity load of this type of user in terms of necessary demand.

[0083] 206. For different types of users, based on the maximum and minimum values ​​on the historical daily load curves, and combined with electricity load forecast data, determine the peak shaving potential or valley filling potential of the users in the future time range.

[0084] A1. For each user category, obtain the maximum and minimum values ​​on the corresponding historical daily load curve.

[0085] A2. The maximum and minimum values ​​are corrected using the preset standard deviation principle to obtain the corrected target maximum and target minimum values ​​for each category of user.

[0086] If the 3σ principle is satisfied, it is a statistical principle based on normal distribution, used to identify and process outliers or abrupt changes in a dataset.

[0087] A3. Compare the target maximum and target minimum values ​​with the electricity load forecast data to determine the peak shaving or valley filling potential for users in the future time range.

[0088] For example, in the embodiments of this application, the maximum and minimum values ​​of the daily load curves are first calculated, and the maximum and minimum values ​​are ensured to meet the 3σ principle, using formula (1) as follows:

[0089] U adj =min(max(X),μ+3σ)

[0090] L adj =max(min(X),μ-3σ) formula (1);

[0091] The response potential, such as peak shaving potential or valley filling potential, is then calculated using formula (2) as follows;

[0092] P upper =max(U adj -X pred ,0)

[0093] P lower =max(X pred -L adj ,0) Formula (2);

[0094] In formulas (1) and (2) above, X represents the data set of the daily load curve, where X... t Let X be the load value at time t. predFor the predicted load value, U adj L represents the maximum value of the daily load curve adjusted according to the 3σ principle. adj This represents the minimum value of the daily load curve after adjustment according to the 3σ principle.

[0095] 207. Assess the user's grid-based demand response potential based on the user's peak shaving or valley filling potential over a future time horizon.

[0096] B1. Based on peak shaving potential, determine the user's ability to reduce electricity consumption during peak hours over a future timeframe; and / or,

[0097] B2. Based on the valley filling potential, determine the user's ability to increase electricity consumption during off-peak hours in the future time range.

[0098] This application embodiment takes into account the relationship between the predicted load value and the upper and lower bounds of the adjusted daily load curve. For each category of user, this application embodiment compares the maximum and minimum values ​​on the historical daily load curve of that category of user with the predicted electricity load data, as shown in formulas (1) and (2) above. Since the predicted electricity load data is equivalent to representing the necessary demand that can be met, it can be seen from the formula comparison that some electricity consumption is unnecessary, i.e., "peak shaving", while some electricity consumption is in a trough, and the electricity capacity can be increased, i.e., "valley filling", thereby achieving the supply and demand balance of the entire power system and ensuring its stability.

[0099] Furthermore, as a response to the above Figure 1 , Figure 2 To implement the method shown, this application provides an assessment device for user-side demand response potential based on the power grid. This device embodiment corresponds to the aforementioned method embodiment. For ease of reading, this device embodiment will not repeat the details of the aforementioned method embodiment, but it should be understood that the device in this embodiment can implement all the contents of the aforementioned method embodiment. This device is used to assess the demand response potential of different categories of users in terms of electricity consumption, specifically as follows... Figure 3 As shown, the device includes:

[0100] The acquisition unit 31 is used to acquire historical electricity consumption data of each user on the user side. The historical electricity consumption data includes at least electricity consumption, electricity consumption time and daily load data. The daily load data includes load information at different times on different dates.

[0101] The first processing unit 32 is used to process the historical electricity consumption data using a preset clustering model to obtain historical daily load curves corresponding to different categories of users, including low-load users, medium-load users and high-load users.

[0102] The second processing unit 33 is used to process the historical daily load curves corresponding to different categories of users using a preset power load prediction model, and output the power load prediction data corresponding to different categories of users.

[0103] The determination unit 34 is used to determine the peak shaving potential or valley filling potential of the user in the future time range based on the maximum and minimum values ​​on the historical daily load curve and the electricity load forecast data for different types of users.

[0104] Evaluation unit 35 is used to evaluate the user's grid-based demand response potential based on the user's peak shaving or valley filling potential over a future time horizon.

[0105] Furthermore, such as Figure 4 As shown, the first processing unit 32 includes:

[0106] The first processing module 321 is used to establish a multi-level index based on the date and different times on the date, process the historical electricity consumption data, and fit the historical daily load curve corresponding to each user on different dates.

[0107] The second processing module 322 is used to process the historical daily load curves of each user on different dates using a preset clustering algorithm to obtain the historical daily load curves of different categories of users, including low-load users, medium-load users and high-load users.

[0108] Furthermore, such as Figure 4 As shown, the second processing unit 33 includes:

[0109] The third processing module 331 is used to convert and process the load data at different times on different dates represented by the historical daily load curve to obtain the corresponding time series data. The time series data includes combined data sorted by date, and each combined data includes different times on the date and the corresponding power load data at the different times.

[0110] The fourth processing module 332 is used to process the time series data using a pre-trained XGBoost framework and output electricity load prediction data for the future time range.

[0111] Furthermore, such as Figure 4 As shown, the determining unit 34 includes:

[0112] The acquisition module 341 is used to acquire the maximum and minimum values ​​on the corresponding historical daily load curve for each category of user;

[0113] The correction module 342 is used to correct the maximum value and the minimum value using a preset standard deviation principle to obtain the corrected target maximum value and target minimum value for each category of user.

[0114] The first determining module 343 is used to compare the target maximum value and the target minimum value with the electricity load forecast data respectively, so as to determine the peak shaving potential or valley filling potential of the user in the future time range.

[0115] Furthermore, such as Figure 4 As shown, the evaluation unit 35 includes:

[0116] The second determining module 351 is configured to determine, based on the peak shaving potential, the user's ability to reduce electricity consumption during peak hours over a future timeframe; and / or,

[0117] The second determining module 351 is further configured to determine, based on the valley filling potential, the user's ability to increase electricity consumption during off-peak hours in the future time range.

[0118] The power grid-based user-side demand response potential assessment and handling device includes a processor and a memory. The aforementioned acquisition unit, first processing unit, second processing unit, determination unit, and assessment unit are all stored as program units in the memory. The processor executes the aforementioned program units stored in the memory to achieve the corresponding functions.

[0119] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and by adjusting kernel parameters, historical electricity consumption data can be used to intelligently classify users and determine the peak-shaving or valley-filling potential of each user category over a future timeframe. This provides an effective solution for measuring and assessing user-side demand response potential based on the power grid.

[0120] This application provides a storage medium storing a program that, when executed by a processor, implements the method for assessing the user-side demand response potential based on the power grid.

[0121] This application provides a processor for running a program, wherein the program executes the power grid-based user-side demand response potential assessment method during runtime.

[0122] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform the steps of an initialization method for assessing the potential of user-side demand response based on a power grid.

[0123] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0124] In a typical configuration, the device includes one or more processors (CPUs), memory, and a bus. The device may also include input / output interfaces, network interfaces, etc.

[0125] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM, and memory includes at least one memory chip. Memory is an example of computer-readable media.

[0126] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0127] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0128] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0129] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for assessing the user-side demand response potential of a power grid, characterized in that, The method includes: Obtain historical electricity consumption data for each user. The historical electricity consumption data includes at least electricity consumption, electricity consumption time, and daily load data. The daily load data includes load information at different times on different dates. The historical electricity consumption data is processed using a pre-set clustering model to obtain historical daily load curves for different categories of users, including low-load users, medium-load users, and high-load users. The step of processing the historical electricity consumption data using a pre-set clustering model to obtain historical daily load curves corresponding to different categories of users includes: establishing a multi-level index based on the date and different times on the date; processing the historical electricity consumption data; fitting the historical daily load curve corresponding to each user on different dates; and processing the historical daily load curve corresponding to each user on different dates using a pre-set clustering algorithm to obtain historical daily load curves for different categories of users, including low-load users, medium-load users, and high-load users. A pre-set power load forecasting model is used to process the historical daily load curves corresponding to different categories of users, and output power load forecasting data corresponding to different categories of users. This includes: transforming the load data at different times on different dates represented by the historical daily load curves to obtain corresponding time series data. The time series data contains combined data sorted by date, and each combined data contains power load data at different times on the date and at the corresponding times. The pre-trained XGBoost framework is used to process the time series data and output power load forecasting data for the future time range. For different categories of users, based on the maximum and minimum values ​​on the historical daily load curves, and combined with the electricity load forecast data, the peak shaving potential or valley filling potential corresponding to the users in the future time range is determined. Assess the grid-based demand response potential of the user based on the peak shaving or valley filling potential corresponding to the user in the future time frame.

2. The method according to claim 1, characterized in that, For different categories of users, based on the maximum and minimum values ​​on the historical daily load curves, and in conjunction with the electricity load forecast data, the peak-shaving potential or valley-filling potential corresponding to the users in the future time range is determined, including: For each user category, obtain the maximum and minimum values ​​on the corresponding historical daily load curve; The maximum and minimum values ​​are corrected using a preset standard deviation principle to obtain the corrected target maximum and target minimum values ​​for each user category. The target maximum value and the target minimum value are compared with the electricity load forecast data to determine the peak shaving potential or valley filling potential of the user in the future time range.

3. The method according to claim 1 or 2, characterized in that, The assessment of the user's grid-based demand response potential based on the user's corresponding peak shaving or valley filling potential over a future time horizon includes: Based on the peak shaving potential, determine the user's ability to reduce electricity consumption during peak hours over a future timeframe; and / or, Based on the valley filling potential, determine the user's ability to increase electricity consumption during off-peak hours in the future time frame.

4. A device for assessing the user-side demand response potential of a power grid, characterized in that, The device includes: The acquisition unit is used to acquire historical electricity consumption data for each user on the user side. The historical electricity consumption data includes at least electricity consumption, electricity consumption time and daily load data. The daily load data includes load information at different times on different dates. The first processing unit is used to process the historical electricity consumption data using a pre-set clustering model to obtain historical daily load curves corresponding to different categories of users, including low-load users, medium-load users, and high-load users. The first processing unit includes: a first processing module, configured to establish a multi-level index based on the date and different times on the date, process the historical electricity consumption data, and fit the historical daily load curve corresponding to each user on different dates; and a second processing module, configured to process the historical daily load curve corresponding to each user on different dates using a preset clustering algorithm to obtain the historical daily load curves of different categories of users, including low-load users, medium-load users, and high-load users. The second processing unit is used to process the historical daily load curves corresponding to different categories of users using a preset power load prediction model, and output the power load prediction data corresponding to different categories of users. The second processing unit includes: a third processing module, used to transform and process the load data at different times on different dates represented by the historical daily load curve to obtain corresponding time series data, wherein the time series data includes combined data sorted by date, and each combined data includes different times on the date and the corresponding power load data at the different times; and a fourth processing module, used to process the time series data using a pre-trained XGBoost framework to output power load prediction data for the future time range. The determination unit is used to determine the peak shaving potential or valley filling potential of different types of users in the future time range based on the maximum and minimum values ​​on the historical daily load curve and the electricity load forecast data. An assessment unit is used to assess the user's grid-based demand response potential based on the user's peak shaving or valley filling potential over a future time horizon.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the power grid-based user-side demand response potential assessment method as described in any one of claims 1-3.

6. An electronic device, characterized in that, The device includes at least one processor, and at least one memory and bus connected to the processor; The processor and the memory communicate with each other via the bus. The processor is used to invoke program instructions in the memory to execute the power grid-based user-side demand response potential assessment method as described in any one of claims 1-3.

Images