Method and device for evaluating user side demand response potential based on power grid

Abstract

The invention discloses a user side demand response potential evaluation method and device based on a power grid. According to the main technical scheme of the invention, the method comprises the steps: obtaining the historical power utilization data of each user on the power utilization of a user side, carrying out the processing of the historical power utilization data through a preset clustering model, and carrying out the fitting, and obtaining the historical daily load curves of different types of users; processing the historical daily load curves corresponding to the different types of users by adopting a preset power load prediction model, and outputting power load prediction data corresponding to the different types of users; and finally, for different types of users, according to the maximum value and the minimum value on a historical daily load curve and by combining the predicted power consumption load prediction data, determining the executable peak clipping potential or valley filling potential in a future time range, which is equivalent to the potential of reducing the power consumption when the power grid demand is peak or the electricity price is high. Or the potential of the increased electricity consumption when the electricity price is low is applied to evaluating the user side demand response potential based on the power grid.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method and device for evaluating user-side demand response potential based on a power grid. Background Art

[0002] In the power system, user-side demand refers to the amount of electricity consumed by users in different time periods. This demand can be rigid, such as residents' use of lighting and air conditioning at night; it can also be flexible, such as the discontinuous process in industrial production.

[0003] The user-side demand response achieved on the basis of user-side demand refers to the user voluntarily reducing or delaying part of the electricity demand according to the demand and price signals of the power grid, and adjusting the electricity consumption plan to respond to the supply and demand balance of the power grid. Correspondingly, the demand response potential achieved on the basis of user-side demand response refers to the potential for users to reduce electricity consumption when the power grid demand is peak or the electricity price is high, or the potential for users to increase electricity consumption when the electricity price is low.

[0004] The goal of utilizing both types of potential is to achieve a balance between supply and demand across the entire power system and ensure its stability. Therefore, how to effectively assess the user-side demand response potential is a technical issue that needs to be addressed urgently. Summary of the Invention

[0005] In view of this, the present application provides a method and device for evaluating the 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 potential or valley-filling potential of each category of users in the future time range, evaluate the user's demand response potential based on the power grid, and provide an effective solution for effectively measuring and evaluating the user-side demand response potential.

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

[0007] In a first aspect, the present application provides a method for evaluating user-side demand response potential based on a power grid, the method comprising:

[0008] On the user side, obtain each user's historical electricity consumption data, the historical electricity consumption data at least including the amount of electricity used, the time of use, and daily load data, the daily load data including load information at different times on different dates;

[0009] Processing the historical electricity consumption data using a preset clustering model to obtain historical daily load curves corresponding to different categories of users, wherein the different categories of users include low-load users, medium-load users, and high-load users;

[0010] The historical daily load curves corresponding to different types of users are processed using a preset power load forecasting model, and the electricity load forecasting data corresponding to different types of users is output;

[0011] For different types of users, based on the maximum and minimum values on the historical daily load curve and in combination with the electricity load forecasting data, the peak shaving potential or valley filling potential corresponding to the user in the future time range is determined;

[0012] Based on the peak shaving potential or valley filling potential corresponding to the user in the future time range, the demand response potential of the user based on the power grid is evaluated.

[0013] A second aspect of the present application provides an evaluation device for the demand response potential of the user side based on the power grid. The device includes:

[0014] An acquisition unit for acquiring the historical electricity consumption data of each user on the user side power consumption. The historical electricity consumption data at least includes electricity consumption, electricity consumption time, and daily load data, and the daily load data includes load information at different times on different dates;

[0015] A first processing unit for processing the historical electricity consumption data using a preset clustering model to obtain the historical daily load curves corresponding to different types of users. The different types of users include low-load users, medium-load users, and high-load users;

[0016] A second processing unit for processing the historical daily load curves corresponding to different types of users using a preset power load forecasting model, and outputting the electricity load forecasting data corresponding to different types of users;

[0017] A determination unit for, for different types of users, based on the maximum and minimum values on the historical daily load curve and in combination with the electricity load forecasting data, determining the peak shaving potential or valley filling potential corresponding to the user in the future time range;

[0018] An evaluation unit for evaluating the demand response potential of the user based on the power grid according to the peak shaving potential or valley filling potential corresponding to the user in the future time range.

[0019] A third aspect of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the evaluation method for the demand response potential of the user side based on the power grid as described above is implemented.

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

[0021] Wherein, the processor and the memory complete communication with each other through the bus;

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

[0023] By means of the above technical solution, the technical solution provided by this application has at least the following advantages:

[0024] This application provides a method and device for evaluating the potential of user-side demand response based on the power grid. In terms of user-side electricity consumption, this application obtains the historical electricity consumption data of each user, and the historical electricity consumption data at least includes electricity consumption, electricity consumption time, and load information at different times on different dates. First, a preset clustering model is used to process the historical electricity consumption data to obtain historical daily load curves of three types of users, namely low-load users, medium-load users, and high-load users, that is, the first processing of a large amount of historical data is realized, and user classification and historical daily load curves of various types of users are realized; secondly, the second processing is realized, and a preset power load prediction model is used to process the historical daily load curves corresponding to different types of users, and output the electricity load prediction data corresponding to different types of users; finally, for different types of users, according to the maximum and minimum values on the historical daily load curve, combined with the predicted electricity load prediction data, this is equivalent to comparing and analyzing the historical electricity consumption habits and predicted electricity consumption habits of the same type of users. Under the condition of meeting the basic needs of users, the peak shaving potential or valley filling potential that can be executed in the future time range is determined. For example, when the power grid demand is high or the electricity price is high, the potential of reducing electricity consumption of users, or the potential of increasing electricity consumption when the electricity price is low, is applied to evaluate the potential of user-side demand response based on the power grid.

[0025] Compared with the existing need to effectively evaluate the potential of user-side demand response, this application realizes the division of a large number of users into three categories through model clustering processing and model prediction processing, and for different user categories, the relationship between the maximum and minimum values on the historical daily load curve and the electricity load prediction data is compared to convert into the peak shaving potential or valley filling potential of electricity consumption in the future time range, which is applied to evaluate the potential of user-side demand response based on the power grid. Thus, the quantification realized by the peak shaving potential or valley filling potential provides an effective solution for effectively measuring and evaluating the potential of user-side demand response.

[0026] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically listed below. Brief Description of the Drawings

[0027] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered as a limitation of the present application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0028] Figure 1 It is a flowchart of an evaluation method for the demand response potential on the user side based on the power grid provided by an embodiment of the present application;

[0029] Figure 2 It is a flowchart of another evaluation method for the demand response potential on the user side based on the power grid provided by an embodiment of the present application;

[0030] Figure 3 It is a block diagram of the composition of an evaluation device for the demand response potential on the user side based on the power grid provided by an embodiment of the present application;

[0031] Figure 4 It is a block diagram of the composition of another evaluation device for the demand response potential on the user side based on the power grid provided by an embodiment of the present application. Detailed Embodiments

[0032] The exemplary embodiments of the present application will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0033] The accurate evaluation of the demand response potential is the data support for the power grid dispatching department to formulate a scientific and reasonable dispatching plan, and is of great significance to all stakeholders involved in the implementation process of demand response.

[0034] Now, restricted by various factors such as energy conservation and emission reduction goals and the rising prices of primary energy sources such as coal, the power system mainly based on thermal power generation is transitioning to a power system mainly based on renewable energy generation. The significant feature of a power system with a high proportion of renewable energy penetration is strong volatility, so more reserve capacity is required to ensure the reliability of the power system. However, the decrease in the proportion of coal in power generation means a reduction in the reserve capacity on the power generation side, making the regulation resources on the demand side more important.

[0035] Therefore, through research, the inventors believe that the demand-side resources actively participating in power grid regulation can effectively relieve the regulation pressure on the power supply side and the power grid side. For example, evaluating the demand response potential on the user side based on the power grid, that is, realizing the ability to perform "peak shaving potential" and "valley filling potential" based on the power grid, so as to achieve the balance between power supply and demand in the power system and ensure its stability.

[0036] An embodiment of the present application provides an evaluation method for the demand response potential on the user side based on the power grid, as Figure 1 shown. The embodiments of the present invention provide the following specific steps for this:

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

[0038] In the embodiment of the present application, in order to obtain the historical electricity consumption data of a large number of users, and the large number of users includes different types, such as residential, commercial, and industrial users, etc. Since there are differences in electricity consumption demands among different types of users, the demand response potentials of different types of users will also be different. In order to comprehensively evaluate the demand response potential on the user side based on the power grid as much as possible in the embodiment of the present application, special consideration is given to covering multiple types of users when obtaining historical electricity consumption data. Below, the demand characteristics and demand response characteristics of different types of users and their electricity consumption on the user side are exemplified, including but not limited to the following:

[0039] (1) Residential users

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

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

[0042] (2) Commercial users

[0043] Demand: The electricity consumption demand of commercial users is to reduce operating costs and improve power supply reliability. The electricity consumption methods include commercial lighting, air conditioning systems, elevators, commercial display equipment, etc.

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

[0045] (3) Industrial users

[0046] Demand: The electricity consumption demand of industrial users is to reduce operating costs and ensure production continuity. The electricity consumption methods usually include 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, participating in the demand response market, etc.

[0048] 102. Process the historical electricity consumption data using a pre-set clustering model to obtain the historical daily load curves corresponding to different categories of users. Different categories of users include low-load users, medium-load users, and high-load users.

[0049] The pre-set clustering model used in the embodiments of this application can be, but is not limited to, trained using multiple clustering algorithms such as K-Means, DBSCAN, and Spectral Clustering. The purpose is to analyze and process the historical electricity consumption data of each of a large number of users. In the process, first, the historical electricity consumption data of a large number of users is converted into the historical daily load curves of each user on different dates, and 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 curves of each category of users. Then, using the clustering processing of the model, redundant data, useless data are removed, fitting classification is performed, and the fitted historical daily load curves corresponding to each category of users are obtained, so as to measure the electricity consumption trend curves of each category of users at different times in daily electricity consumption.

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

[0051] 103. Process the historical daily load curves corresponding to different categories of users using a pre-set power load forecasting model, and output the electricity load forecasting data corresponding to different categories of users.

[0052] The pre-set power load forecasting model can be, but is not limited to, trained using machine learning, and meteorological data at different times on different dates can be added during the training process to improve the accuracy of the trained model applied to forecasting electricity load.

[0053] In the embodiments of this application, this step is equivalent to realizing the second processing. Specifically, a pre-set power load forecasting model is used to process based on the historical daily load curves corresponding to different categories of users to predict the electricity load forecasting data of different categories of users in the future time range.

[0054] 104. For different categories of users, determine the peak shaving potential or valley filling potential corresponding to the users in the future time range according to the maximum and minimum values on the historical daily load curve and combined with the electricity load forecasting data.

[0055] 105. Evaluate the demand response potential of users based on the power grid according to the peak shaving potential or valley filling potential corresponding to the users in the future time range.

[0056] As described in 104-105, this is equivalent to comparing and analyzing the historical and predicted electricity consumption habits of users in the same category. Under the condition of meeting the basic needs of users (such as rigid demands that do not affect the daily basic life of users' electricity consumption), determine the peak shaving potential or valley filling potential that can be implemented in the future time range.

[0057] For different categories of users, the user-side demand refers to the electricity consumption of users at different time periods. This demand can be rigid, such as the use of residential night lighting and air conditioners; it can also be flexible, such as the discontinuous process in industrial production. The user-side demand response achieved based on the user-side demand is that users voluntarily reduce or delay a part of their electricity demand according to the demand and price signals of the power grid, and adjust their electricity consumption plans to respond to the supply-demand balance of the power grid. Therefore, after meeting certain necessary demands of users, the user-side demand response is adjustable. Based on this, the embodiments of the present application use the "user-side demand response potential" to evaluate the adjustable range of the "user-side demand response".

[0058] Exemplarily, the embodiments of the present application can be characterized by, but not limited to, "peak shaving potential" and "valley filling potential". "Peak shaving potential": the ability to reduce electricity consumption during peak hours (down-regulation reserve capacity); "Valley filling potential": the ability to increase electricity consumption during off-peak hours (up-regulation reserve capacity).

[0059] Specifically, for how to obtain the "peak shaving potential" and "valley filling potential", the embodiments of the present application estimate different categories of users separately. For example, for each category of users, in the future time range corresponding to the predicted electricity load prediction data obtained in 103, the embodiments of the present application use the maximum and minimum values on the historical daily load curve corresponding to this category of users for measurement. Since the historical daily load curve obtained through the 102 model processing represents the probable electricity consumption behavior of a category of users, there will not be much difference in this future time range, and the predicted electricity load data represents the necessary demand that can be used to meet electricity consumption.

[0060] Therefore, the embodiments of the present application compare the maximum and minimum values on the historical daily load curve of this category of users with the predicted electricity load data, and it can be seen that some parts of electricity consumption are unnecessary, that is, "peak shaving", while some parts of electricity consumption are at a low valley and the electricity consumption capacity can be increased, that is, "valley filling", so as to achieve the supply-demand balance of the entire power system and ensure its stability.

[0061] As described above, the embodiment of the present application provides a method for evaluating the demand response potential on the user side based on the power grid. In the power consumption of the user side, the embodiment of the present application obtains the historical power consumption data of each user, and the historical power consumption data at least includes the power consumption, power consumption time, and load information at different times on different dates. First, a preset clustering model is used to process the historical power consumption data to obtain the historical daily load curves of three types of users, such as low-load users, medium-load users, and high-load users, that is, the first processing of a large amount of historical data is realized, and user classification and the historical daily load curves of various types of users are realized; secondly, the second processing is realized. A preset power load prediction model is used to process the historical daily load curves corresponding to different types of users, and the power load prediction data corresponding to different types of users is output; finally, for different types of users, according to the maximum and minimum values on the historical daily load curve, combined with the predicted power load prediction data, this is equivalent to comparing and analyzing the historical power consumption habits and predicted power consumption habits of the same type of users. Under the condition of meeting the basic needs of users, the peak shaving potential or valley filling potential that can be executed in the future time range is determined. For example, when the grid demand is high or the electricity price is high, the potential of reducing the power consumption of users, or the potential of increasing the power consumption when the electricity price is low, is applied to evaluate the demand response potential on the user side based on the power grid.

[0062] Compared with the existing demand for effectively evaluating the demand response potential on the user side, the embodiment of the present application realizes the division of a large number of users into three categories through model clustering processing and model prediction processing, and for different user categories, the relationship between the maximum and minimum values on the historical daily load curve and the power load prediction data is compared to convert into the peak shaving potential or valley filling potential of power consumption in the future time range, which is applied to evaluate the demand response potential on the user side based on the power grid. Therefore, the quantization achieved by the peak shaving potential or valley filling potential provides an effective solution for effectively measuring and evaluating the demand response potential on the user side.

[0063] In order to make a more detailed description of the above embodiments, the embodiment of the present application also provides another method for evaluating the demand response potential on the user side based on the power grid, as Figure 2 shown. For this, the embodiment of the present application provides the following specific steps:

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

[0065] In the embodiment of the present application, for the explanation of this step, refer to 101, which will not be elaborated here.

[0066] 202. Establish a multi - level index based on dates and different times of the day, process historical electricity consumption data, and fit to obtain the historical daily load curves corresponding to each user on different dates.

[0067] In the embodiments of this application, the historical electricity consumption data is processed by removing missing values, filling, dealing with outliers, etc. Thus, by using such pre - processing to improve the data quality, then extract date features and time features from the pre - processed historical electricity consumption data, and further, based on the association between dates and times, such as which times (i.e., moments) exist on a certain date, and then construct a multi - level index based on the date features, time features and the association between them, to obtain the historical electricity load at certain moments on a certain date, so as to fit and obtain the historical daily load curves corresponding to each user on different dates.

[0068] 203. Use a preset clustering algorithm to process the historical daily load curves corresponding to each user on different dates, and obtain the historical daily load curves of different types of users. Different types of users include low - load users, medium - load users, and high - load users.

[0069] The preset clustering algorithm can be, but is not limited to, using the Gaussian Mixture Model (GMM) clustering algorithm to process the historical daily load curves corresponding to each user on different dates, and divide users into three categories. These three categories are usually divided according to the curve features represented on the historical daily load curves,

[0070] similarities in electricity consumption behavior patterns or load demands, etc. For example, it can be, but is not limited to, divided into three categories: low - load users, medium - load users, and high - load users. The characteristics of these three types of users are respectively exemplified as follows, and can be, but are not limited to, including the following:

[0071] (1) Low - load users:

[0072] The daily load curves of these users usually show relatively low load levels, indicating that their electricity consumption demands are relatively low; they may mainly be residential users or small - scale commercial users, and their electricity consumption behaviors are relatively stable and less affected by factors such as time and season.

[0073] (2) Medium - load users:

[0074] The daily load curves of these users will show certain fluctuations during the day, but the overall load level is moderate; they may include medium - sized commercial users, light - industrial users, or certain residential communities; the electricity consumption behaviors of these users may be affected by multiple factors such as working hours, seasonal changes, and weather conditions.

[0075] (3) High - load users:

[0076] The daily load curves of such users usually show relatively high load levels and significant fluctuations; they may mainly be key infrastructure users such as large industrial users, data centers, and hospitals; the electricity consumption demands of such users are usually large, and they have relatively high requirements for power supply quality and stability.

[0077] As described above according to 202a and 203a, the embodiments of the present application adopt two-step progressive operations to improve data quality. For example, the historical electricity consumption data of each of a large number of users is analyzed and processed. In the process, first, the historical electricity consumption data of a large number of users is converted into the historical daily load curves of each user on different dates, and 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, as well as the historical daily load curves of users in each category.

[0078] Subsequently, through the clustering processing of the model, redundant data, useless data are removed, the data is fitted and classified, and the fitted historical daily load curves corresponding to users in each category are obtained, so as to measure the electricity consumption trend curves of users in each category at different moments in daily electricity consumption.

[0079] 204. For users in each category, the load data at different moments on different dates represented by the historical daily load curve is subjected to conversion processing to obtain corresponding time series data. The time series data contains combined data sorted by date, and each combined data contains different moments on the date and the power load data corresponding to different moments.

[0080] 205. Use the pre-trained XGBoost framework to process the time series data and output the electricity load prediction data in the future time range.

[0081] In the embodiments of the present application, a pre-set power load prediction model is pre-trained. During the model training process, historical power load data is used. Since the historical power load data includes daily power load and power load at different moments on each day, this historical power load data is actually a time series data. The embodiments of the present application use time series data as samples and adopt machine learning (such as the XGBoost framework) to train the model, so as to convert the training on the time series into the model training of supervised learning. And preferably, in the model training, the data dimension of the time series data can also be increased, such as adding meteorological data, so that the model will also consider meteorological factors during the prediction application, thereby improving the prediction accuracy of the model.

[0082] As shown in 202b - 203b, in the embodiments of the present application, each category of users is processed separately to obtain the predicted power consumption load data of each category of users over a future time range. In fact, this predicted power consumption load data can represent the power consumption load of this category of users for their essential demands.

[0083] 206. For different categories of users, according to the maximum and minimum values on the historical daily load curve, and in combination with the predicted power consumption load data, determine the peak shaving potential or valley filling potential corresponding to the users over the future time range.

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

[0085] A2. Correct the maximum and minimum values using the preset standard deviation principle to obtain the corrected target maximum and target minimum values corresponding to each category of users.

[0086] If it satisfies the 3σ principle, it is a statistical principle based on the normal distribution, used to identify and process outliers or mutation values in the data set.

[0087] A3. Compare the target maximum and target minimum values with the predicted power consumption load data respectively to determine the peak shaving potential or valley filling potential corresponding to the users over the future time range.

[0088] As in A1 - A3, in the embodiments of the present application, first calculate the maximum and minimum values of the daily load curve, and ensure that the maximum and minimum values satisfy the 3σ principle. The formula (1) is as follows:

[0089] U adj = min(max(X), μ + 3σ)

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

[0091] Then calculate the response potential, such as the peak shaving potential or valley filling potential, using the 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 the above formulas (1) and (2), where X is the data set of the daily load curve, and X t is the load value at time t, X predis the predicted load value, U adj is the maximum value of the daily load curve adjusted by the 3σ principle, L adj is the minimum value of the daily load curve adjusted by the 3σ principle.

[0095] 207. Evaluate the demand response potential of users based on the grid according to the peak shaving potential or valley filling potential corresponding to users in the future time range.

[0096] B1. Determine the ability of users to reduce electricity consumption during peak hours in the future time range according to the peak shaving potential; and / or,

[0097] B2. Determine the ability of users to increase electricity consumption during valley hours in the future time range according to the valley filling potential.

[0098] The embodiments of the present application consider the relationship between the predicted load value and the upper and lower bounds of the adjusted daily load curve. For each category of users, the embodiments of the present application compare the maximum and minimum values on the historical daily load curve of this category of users with the predicted electricity load data. As shown in the above formulas (1) and (2), since the predicted electricity load data is equivalent to representing the necessary demand for meeting electricity consumption, it can be seen from the formula comparison that some parts of electricity consumption are unnecessary, that is, "peak shaving", and some parts of electricity consumption are at a low valley, and the electricity consumption capacity can be increased, that is, "valley filling", so as to achieve the balance between supply and demand of the entire power system and ensure its stability.

[0099] Further, as an implementation of the above Figure 1 、 Figure 2 shown method, the embodiments of the present application provide an evaluation device for the demand response potential of the user side based on the grid. The device embodiments correspond to the foregoing method embodiments. For the convenience of reading, the device embodiments of the present application will not repeat the details of the foregoing method embodiments one by one, but it should be clear that the device in this embodiment can correspondingly implement all the contents of the foregoing method embodiments. The device is applied to evaluate the demand response potential of different categories of users in electricity consumption, specifically as Figure 3 shown, the device includes:

[0100] An acquisition unit 31, configured to acquire the historical electricity consumption data of each user on the user side power consumption, where the historical electricity consumption data at least includes electricity consumption, electricity consumption time, and daily load data, and the daily load data includes load information at different times on different dates;

[0101] A first processing unit 32, configured to process the historical electricity consumption data by using a preset clustering model to obtain historical daily load curves corresponding to different categories of users, where the different categories of users include low-load users, medium-load users, and high-load users;

[0102] A second processing unit 33, configured to process the historical daily load curves corresponding to different categories of users by using a preset power load prediction model, and output power load prediction data corresponding to different categories of users;

[0103] A determination unit 34, configured to, for different categories of users, determine the peak shaving potential or valley filling potential corresponding to the users in a future time range according to the maximum value and the minimum value on the historical daily load curve and in combination with the power load prediction data;

[0104] An evaluation unit 35, configured to evaluate the demand response potential of the users based on the power grid according to the peak shaving potential or valley filling potential corresponding to the users in a future time range.

[0105] Further, as Figure 4 shown, the first processing unit 32 includes:

[0106] A first processing module 321, configured to establish a multi-level index according to the date and different moments on the date, process the historical power consumption data, and fit to obtain the historical daily load curves corresponding to each user on different dates;

[0107] A second processing module 322, configured to process the historical daily load curves corresponding to each user on different dates by using a preset clustering algorithm to obtain the historical daily load curves of different categories of users, where the different categories of users include low-load users, medium-load users, and high-load users.

[0108] Further, as Figure 4 shown, the second processing unit 33 includes:

[0109] A third processing module 331, configured to perform conversion processing on the load data at different moments on different dates represented on the historical daily load curve to obtain corresponding time series data, where the time series data includes combined data sorted by date, and each combined data includes different moments on the date and the power load data corresponding to the different moments;

[0110] A fourth processing module 332, configured to process the time series data by using a pre-trained XGBoost framework and output power load prediction data in a future time range.

[0111] Further, as Figure 4 shown, the determination unit 34 includes:

[0112] An acquisition module 341, configured to, for each category of users, acquire the maximum value and the minimum value on the corresponding historical daily load curve;

[0113] A calibration module 342, configured to calibrate the maximum value and the minimum value according to a preset standard deviation principle to obtain a calibrated target maximum value and a calibrated target minimum value corresponding to each category of users.

[0114] A first determination module 343, configured to compare the target maximum value and the target minimum value with the electricity load prediction data respectively to determine the peak shaving potential or valley filling potential corresponding to the user in a future time range.

[0115] Further, as Figure 4 shown, the evaluation unit 35 includes:

[0116] A second determination module 351, configured to determine the ability of the user to reduce electricity consumption during peak hours in a future time range according to the peak shaving potential; and / or,

[0117] The second determination module 351 is further configured to determine the ability of the user to increase electricity consumption during valley hours in a future time range according to the valley filling potential.

[0118] The evaluation and disposal device for the user-side demand response potential based on the power grid includes a processor and a memory. The above-mentioned acquisition unit, first processing unit, second processing unit, determination unit, and evaluation unit are all stored in the memory as program units, and the corresponding functions are implemented by the processor executing the above program units stored in the memory.

[0119] The processor contains a kernel, and the kernel retrieves the corresponding program units from the memory. One or more kernels can be set. By adjusting the kernel parameters, using historical electricity consumption data, intelligent user classification is performed, and for each category of users, their peak shaving potential or valley filling potential in a future time range is determined intelligently, and the demand response potential of the user based on the power grid is evaluated, providing an effective solution for effectively measuring and evaluating the user-side demand response potential.

[0120] An embodiment of the present application provides a storage medium, on which a program is stored, and when the program is executed by a processor, the evaluation method for the user-side demand response potential based on the power grid is implemented.

[0121] An embodiment of the present application provides a processor, and the processor is used to run a program, wherein when the program runs, the evaluation method for the user-side demand response potential based on the power grid is executed.

[0122] The present application also provides a computer program product, which is suitable for executing a program initialized with the steps of the evaluation method for the user-side demand response potential based on the power grid when executed on a data processing device.

[0123] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows 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 the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

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

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

[0126] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, 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, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0127] It should also be noted that the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0128] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, system or computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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.

[0129] The above are only the embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. An evaluation method for the potential of demand response on the user side based on the power grid, characterized in that The method includes: Obtaining historical power consumption data of each user, where the historical power consumption data at least includes power consumption, power consumption time, and daily load data, and the daily load data includes load information at different times on different dates; Processing the historical power consumption data using a preset clustering model to obtain historical daily load curves corresponding to different categories of users, where the different categories of users include low-load users, medium-load users, and high-load users; Processing the historical daily load curves corresponding to different categories of users using a preset power load forecasting model, and outputting power load forecasting data corresponding to different categories of users; For different categories of users, based on the maximum and minimum values on the historical daily load curve and in combination with the power load forecasting data, determining the peak shaving potential or valley filling potential corresponding to the user in a future time range; Evaluating the demand response potential of the user based on the power grid according to the peak shaving potential or valley filling potential corresponding to the user in a future time range.

2. The method according to claim 1, wherein The processing the historical power consumption data using a preset 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 power consumption data, and fitting to obtain the historical daily load curve corresponding to each user on different dates; Processing the historical daily load curves corresponding to each user on different dates using a preset clustering algorithm to obtain historical daily load curves of different categories of users, where the different categories of users include low-load users, medium-load users, and high-load users.

3. The method according to claim 1, wherein The processing the historical daily load curves corresponding to different categories of users using a preset power load forecasting model and outputting power load forecasting data corresponding to different categories of users includes: Performing conversion processing on the load data at different times on different dates represented on the historical daily load curve to obtain corresponding time series data, where the time series data contains combined data sorted by date, and each combined data contains different times on the date and the power load data corresponding to the different times; Processing the time series data using a pre-trained XGBoost framework and outputting power load forecasting data in a future time range.

4. The method according to claim 1, wherein The determining, for different categories of users, the peak shaving potential or valley filling potential corresponding to the user in a future time range based on the maximum and minimum values on the historical daily load curve and in combination with the power load forecasting data includes: For each category of user, obtaining the maximum and minimum values on the corresponding historical daily load curve; Correcting the maximum and minimum values using a preset standard deviation principle to obtain the corrected target maximum and target minimum values corresponding to each category of user; Comparing the target maximum and target minimum values with the power load forecasting data respectively to determine the peak shaving potential or valley filling potential corresponding to the user in a future time range.

5. The method according to any one of claims 1 to 4, characterized in that The evaluating the demand response potential of the user based on the power grid according to the peak shaving potential or valley filling potential corresponding to the user in a future time range includes: Determine the user's ability to reduce power consumption during peak hours over a future time range according to the peak shaving potential; and / or, Determine the user's ability to increase power consumption during valley hours over a future time range according to the valley filling potential.

6. An evaluation device for the potential of user-side demand response based on the power grid, characterized in that The device includes: An acquisition unit, configured to acquire historical power consumption data of each user on the user side power consumption. The historical power consumption data at least includes power consumption, power consumption time, and daily load data. The daily load data includes load information at different times on different dates; A first processing unit, configured to process the historical power consumption data by using a preset clustering model to obtain historical daily load curves corresponding to different categories of users. The different categories of users include low-load users, medium-load users, and high-load users; A second processing unit, configured to process the historical daily load curves corresponding to different categories of users by using a preset power load prediction model and output power load prediction data corresponding to different categories of users; A determination unit, configured to, for different categories of users, determine the corresponding peak shaving potential or valley filling potential of the user over a future time range according to the maximum and minimum values on the historical daily load curve and in combination with the power load prediction data; An evaluation unit, configured to evaluate the user's demand response potential based on the power grid according to the corresponding peak shaving potential or valley filling potential of the user over a future time range.

7. The device according to claim 6, characterized in that, The first processing unit includes: A first processing module, configured to establish a multi-level index according to the date and different times on the date, process the historical power consumption data, and fit to obtain the historical daily load curve corresponding to each user on different dates; A second processing module, configured to process the historical daily load curves corresponding to each user on different dates by using a preset clustering algorithm to obtain historical daily load curves of different categories of users. The different categories of users include low-load users, medium-load users, and high-load users.

8. The device according to claim 6, characterized in that, The second processing unit includes: A third processing module, configured to perform conversion processing on the load data at different times on different dates represented on the historical daily load curve to obtain corresponding time series data. The time series data contains combined data sorted by date, and each combined data contains different times on the date and the power load data corresponding to the different times; A fourth processing module, configured to process the time series data by using a pre-trained XGBoost framework and output power load prediction data over a future time range.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements the method for evaluating the user-side demand response potential based on the power grid according to any one of claims 1-5.

10. An electronic device, characterized in that, The device includes at least one processor, at least one memory connected to the processor, and a bus; Wherein, the processor and the memory communicate with each other through the bus; The processor is configured to call the program instructions in the memory to execute the method for evaluating the user-side demand response potential based on the power grid according to any one of claims 1-5.

Images