User side energy flexible scheduling management method and system

Abstract

The invention belongs to the technical field of power dispatching. The invention provides a user side energy flexible scheduling management method and system. The method comprises the following steps: acquiring first electricity demand historical data and second electricity demand historical data of each user in a target area; performing prediction processing on the first electricity demand historical data by using a first prediction model to obtain a first predicted electricity demand; using a second prediction model to perform prediction processing on the second power consumption demand historical data to obtain a first power consumption demand fluctuation coefficient; and calculating a second predicted power consumption demand based on the first predicted power consumption demand and the first power consumption demand fluctuation coefficient, and determining an energy flexible scheduling management scheme according to the second predicted power consumption demand. According to the method, the historical electricity utilization rule of the user and the influence on fluctuation of the electricity price and the electricity supply and demand condition are considered at the same time, and the accuracy and rationality of the determined energy flexible scheduling management scheme can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power dispatching, and in particular to a user-side energy flexible dispatching management method and system. Background Art

[0002] By real-time monitoring, adjusting and optimizing the match between user-side energy demand and supply, precise control of energy flow can be achieved, thereby improving the operating efficiency of the power system. The existing technology currently mainly predicts the electricity demand patterns of users in the region and then determines the electricity dispatch strategy for users in the region. However, the above existing methods lack consideration of other factors, such as energy prices, supply and demand conditions, etc., resulting in a large discrepancy between the predicted electricity demand and the actual electricity consumption, which is not conducive to determining a reasonable flexible dispatch plan. Summary of the invention

[0003] In this regard, the present invention provides a user-side energy flexible scheduling management method, system, electronic device, computer storage medium and computer program product to solve the above-mentioned technical problems.

[0004] The present invention discloses a user-side energy flexible scheduling management method, the method comprising the following steps: Acquire first electricity demand historical data and second electricity demand historical data of each user in the target area; wherein only the second electricity demand historical data contains electricity price data with a fluctuation range higher than the first preset value and electricity supply and demand data with a fluctuation range higher than the second preset value; Using a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand; Using a second prediction model to perform prediction processing on the second electricity demand historical data to obtain a first electricity demand fluctuation coefficient; A second predicted electricity demand is calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, and an energy flexible scheduling management plan is determined according to the second predicted electricity demand.

[0005] In some embodiments, the obtaining of the first power demand historical data and the second power demand historical data of each user in the target area includes: Collect electricity consumption data of each user in the target area in real time or regularly through smart meters, energy management systems or user submission, including at least electricity consumption and electricity consumption time; Classifying the collected electricity consumption data according to time dimension and user attributes to form the first electricity demand historical data; Collect corresponding electricity price data and electricity supply and demand data according to each of the electricity usage times, and filter out the electricity price data with a fluctuation range higher than a first preset value and the electricity supply and demand data with a fluctuation range higher than a second preset value; The electricity consumption data is time-aligned and integrated with the electricity price data whose fluctuation range is higher than the first preset value, and the electricity supply and demand data whose fluctuation range is higher than the second preset value, to obtain the second electricity demand historical data.

[0006] In some embodiments, the real-time or periodic collection of electricity consumption data of each user in the target area by means of a smart meter, an energy management system or user submission includes: Collect first electricity usage data of all users in the target area according to a preset first time period, and extract from the first electricity usage data a first quantity of electricity usage data whose data sources are smart meters and energy management systems, and a second quantity of electricity usage data whose data sources are submitted by users; Determine an expansion coefficient according to a ratio of the first number to the second number, and multiply the first duration by the expansion coefficient to obtain a second duration; The second power usage data of all users in the target area are collected according to the second time period, and the second power usage data include the power usage data of each user.

[0007] In some embodiments, using a first prediction model to perform prediction processing on the first power demand history data to obtain a first predicted power demand; using a second prediction model to perform prediction processing on the second power demand history data to obtain a first power demand fluctuation coefficient includes: Using a convolutional network to perform feature extraction on the first power demand historical data and the second power demand historical data respectively, to obtain a first power usage feature and a second power usage feature; Inputting the first electricity consumption feature into the first prediction model to obtain the first predicted electricity demand; wherein the first prediction model is constructed based on a deep learning model; The second electricity consumption characteristic is input into the second prediction model to obtain the first electricity demand fluctuation coefficient; wherein the second prediction model is constructed based on a general large model.

[0008] In some embodiments, the calculating the second predicted electricity demand based on the first predicted electricity demand and the first electricity demand fluctuation coefficient includes: Retrieving power grid connection data of each user in the target area, extracting a third number of users with power grid connection records based on the power grid connection data, and determining a second power demand fluctuation coefficient based on the third number; The second predicted electricity demand is calculated based on the first predicted electricity demand, the first electricity demand fluctuation coefficient and the second electricity demand fluctuation coefficient.

[0009] In some embodiments, determining an energy flexible scheduling management scheme according to the second predicted electricity demand includes: Setting specific scheduling objectives for energy scheduling, including but not limited to supply and demand balance, cost minimization, and energy efficiency maximization; The energy flexible scheduling management plan is determined based on the second predicted electricity demand and the scheduling target.

[0010] The present invention also discloses a user-side energy flexible scheduling management system, the system comprising a processor and a memory, the processor runs a computer code stored in the memory to implement the following steps: Acquire first electricity demand historical data and second electricity demand historical data of each user in the target area; wherein only the second electricity demand historical data contains electricity price data with a fluctuation range higher than the first preset value and electricity supply and demand data with a fluctuation range higher than the second preset value; Using a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand; Using a second prediction model to perform prediction processing on the second electricity demand historical data to obtain a first electricity demand fluctuation coefficient; A second predicted electricity demand is calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, and an energy flexible scheduling management plan is determined according to the second predicted electricity demand.

[0011] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.

[0012] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0013] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.

[0014] The beneficial effects of the present invention are: In addition to considering the historical electricity consumption patterns of users in the target area, aspects of the present invention further consider the impact of each user in the target area on fluctuations in electricity prices and electricity supply and demand, so that the determined predicted electricity demand is more accurate, thereby significantly improving the accuracy and rationality of the determined energy flexible scheduling management plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 It is a flow chart of a user-side energy flexible scheduling management method disclosed in an embodiment of the present invention; Figure 2 It is a schematic diagram of the relationship between the convolutional network disclosed in the embodiment of the present invention and the first prediction model and the second prediction model; Figure 3 It is a structural diagram of a user-side energy flexible scheduling management system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0018] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0019] The existing technology currently mainly predicts the electricity demand patterns of users in the region and then determines the power dispatch strategy for users in the region. However, the above existing methods lack consideration of other factors, such as energy prices, supply and demand conditions, etc., resulting in a large discrepancy between the predicted electricity demand and the actual electricity consumption, which is not conducive to determining a reasonable flexible dispatch plan.

[0020] In view of the above-mentioned defects of the prior art, Figure 1 As shown, an embodiment of the present invention discloses a user-side energy flexible scheduling management method, the method comprising the following steps: Acquire first electricity demand historical data and second electricity demand historical data of each user in the target area; wherein only the second electricity demand historical data contains electricity price data with a fluctuation range higher than the first preset value and electricity supply and demand data with a fluctuation range higher than the second preset value; Using a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand; Using a second prediction model to perform prediction processing on the second electricity demand historical data to obtain a first electricity demand fluctuation coefficient; A second predicted electricity demand is calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, and an energy flexible scheduling management plan is determined according to the second predicted electricity demand.

[0021] Compared with the existing processing methods in the background technology, the present invention simultaneously collects two types of electricity demand history data of each user in the target area, namely, the first electricity demand history data and the second electricity demand history data. Among them, the first electricity demand history data contains the actual electricity consumption data of each user in the target area at different time periods, and the second electricity demand history data, in addition to the above-mentioned actual electricity consumption data, also includes electricity price data with a fluctuation range higher than the first preset value in the corresponding time period, and electricity supply and demand data with a fluctuation range higher than the second preset value.

[0022] Then, the first electricity demand historical data is predicted and processed using a preset first prediction model to obtain a first predicted electricity demand; and the second electricity demand historical data is predicted and processed using a preset second prediction model to obtain a first electricity demand fluctuation coefficient. The first electricity demand fluctuation coefficient characterizes the degree to which the electricity consumption of each user in the region is affected by fluctuations in electricity prices and electricity supply and demand. The higher the first electricity demand fluctuation coefficient, the higher the corresponding degree of influence. For example, the higher the increase in electricity prices and the tighter the electricity supply, the lower the first electricity demand fluctuation coefficient, that is, the user's electricity demand shows a downward trend; the lower the increase in electricity prices or the higher the decrease in electricity prices and the more sufficient the electricity supply, the higher the first electricity demand fluctuation coefficient, that is, the electricity demand shows an upward trend. This is only an example of the basic principles, and is not intended to limit the scope of protection of the present invention.

[0023] Finally, the second predicted electricity demand is calculated based on the first electricity demand fluctuation coefficient multiplied by the aforementioned first predicted electricity demand. Compared with the aforementioned first predicted electricity demand, the second predicted electricity demand takes into account the impact of fluctuations in electricity prices and electricity supply and demand conditions of each user in the target area, so that the energy flexible scheduling management plan determined based on the second predicted electricity demand will be more accurate and reasonable.

[0024] Therefore, in addition to considering the historical electricity consumption patterns of users in the target area, aspects of the present invention further consider the impact of each user in the target area on fluctuations in electricity prices and electricity supply and demand, so that the determined predicted electricity demand is more accurate, thereby significantly improving the accuracy and rationality of the determined energy flexible scheduling management plan.

[0025] In some embodiments, the obtaining of the first power demand historical data and the second power demand historical data of each user in the target area includes: Collect electricity consumption data of each user in the target area in real time or regularly through smart meters, energy management systems or user submission, including at least electricity consumption and electricity consumption time; Classifying the collected electricity consumption data according to time dimension and user attributes to form the first electricity demand historical data; Collect corresponding electricity price data and electricity supply and demand data according to each of the electricity usage times, and filter out the electricity price data with a fluctuation range higher than a first preset value and the electricity supply and demand data with a fluctuation range higher than a second preset value; The electricity consumption data is time-aligned and integrated with the electricity price data whose fluctuation range is higher than the first preset value, and the electricity supply and demand data whose fluctuation range is higher than the second preset value, to obtain the second electricity demand historical data.

[0026] In the embodiment of the present invention, the power consumption data of each user in the target area can be obtained through the following multiple ways or methods, and the power consumption data at least includes the power consumption and the power consumption time.

[0027] Smart meters: Modern smart meters can record users' electricity consumption data in real time, including electricity consumption, electricity consumption time, power factor, etc., and are an important tool for obtaining historical data on electricity demand. Energy management system: Some large enterprises or parks may be equipped with energy management systems, which can monitor and record electricity consumption data in real time and provide more detailed and accurate electricity consumption information. User submission: In some cases, users may actively submit their electricity consumption data, especially when these data are important for formulating personalized energy management plans.

[0028] The collected electricity consumption data is classified according to the time dimension and user attributes to form the first electricity demand history data. The time dimension is, for example, day, week, month, year, and the electricity consumption data classified according to the time dimension can be used to analyze the user's electricity consumption pattern and trend. User attributes are, for example, residential, commercial, industrial, etc. Since the electricity consumption characteristics of users with different attributes are quite different, classifying the electricity consumption data according to user attributes is helpful to analyze a more accurate first predicted electricity demand.

[0029] At the same time, the corresponding power price data and power supply and demand data are collected according to the power consumption time in each power consumption data, and the power price fluctuation curve and the power supply and demand fluctuation curve (the horizontal axis is time, and the vertical axis is the difference between demand and supply) can be drawn respectively. According to the two curves, the power price data with a fluctuation range higher than the first preset value and the power supply and demand data with a fluctuation range higher than the second preset value can be screened respectively. The first preset value and the second preset value are pre-determined. The above-mentioned power price data, power supply and demand data obtained by screening are first time-aligned with the corresponding power consumption data, and then integrated, so as to obtain the second power demand historical data.

[0030] In some embodiments, the real-time or periodic collection of electricity consumption data of each user in the target area by means of a smart meter, an energy management system or user submission includes: Collect first electricity usage data of all users in the target area according to a preset first time period, and extract from the first electricity usage data a first quantity of electricity usage data whose data sources are smart meters and energy management systems, and a second quantity of electricity usage data whose data sources are submitted by users; Determine an expansion coefficient according to a ratio of the first number to the second number, and multiply the first duration by the expansion coefficient to obtain a second duration; The second power usage data of all users in the target area are collected according to the second time period, and the second power usage data include the power usage data of each user.

[0031] In an embodiment of the present invention, the collection of electricity consumption data of each user in the target area of ​​the present invention is divided into two stages. That is, first collect the first electricity consumption data of all users in the target area within a preset first time period (i.e., trace back the first time period in the historical time direction based on the current time), and extract the first number of electricity consumption data whose data source is the smart meter and energy management system and the second number of electricity consumption data whose data source is the user submission from the first electricity consumption data. Then determine the corresponding expansion coefficient based on the ratio of the first number to the second number, wherein the larger the ratio is, the more the proportion of electricity consumption data in the target area is from the smart meter and energy management system, and the data uploaded by the smart meter and energy management system are all pre-processed by correction, deduplication, etc., and their credibility is higher, and the credibility of the first electricity consumption data is correspondingly higher, and the smaller the expansion coefficient is set at this time. The smaller the ratio is, the smaller the proportion of electricity consumption data in the target area is from smart meters and energy management systems. Since the data uploaded by the user submission method is obviously insufficient in data standardization and data credibility, the credibility of the data submitted by the user is lower, and the credibility of the first electricity consumption data is also correspondingly lower. At this time, the larger the expansion coefficient is set, the more electricity consumption data is used to ensure the accuracy of the first predicted electricity demand and the first electricity demand fluctuation coefficient. The expansion coefficient is a value greater than 1.

[0032] Subsequently, the determined expansion coefficient is multiplied by the aforementioned first duration to obtain a corrected second duration, and the electricity consumption data of each user in the target area is collected according to the second duration, thereby obtaining the aforementioned second electricity consumption data.

[0033] It should be noted that the present invention does not limit the conversion formula between the above ratio and the expansion coefficient.

[0034] In some embodiments, using a first prediction model to perform prediction processing on the first power demand history data to obtain a first predicted power demand; using a second prediction model to perform prediction processing on the second power demand history data to obtain a first power demand fluctuation coefficient includes: Using a convolutional network to perform feature extraction on the first power demand historical data and the second power demand historical data respectively, to obtain a first power usage feature and a second power usage feature; Inputting the first electricity consumption feature into the first prediction model to obtain the first predicted electricity demand; wherein the first prediction model is constructed based on a deep learning model; The second electricity consumption characteristic is input into the second prediction model to obtain the first electricity demand fluctuation coefficient; wherein the second prediction model is constructed based on a general large model.

[0035] In an embodiment of the present invention, the present invention constructs the above-mentioned first prediction model and second prediction model, which are respectively used to predict the first predicted electricity demand and the first electricity demand fluctuation coefficient. Among them, the first prediction model is constructed based on a deep learning model, and the deep learning model includes but is not limited to a convolutional neural network CNN, a recurrent neural network RNN, a transformer Transformer, etc.; the second prediction model is constructed based on a general large model, and the general large model includes but is not limited to a GPT series model, BERT, T5, RoBERTa, etc.

[0036] Since the user's electricity consumption pattern is easy to grasp, a conventional deep learning model can be used to construct the above-mentioned first prediction model; however, the degree to which the user's electricity consumption is affected by fluctuations in electricity prices and electricity supply and demand is obviously more complex, so the present invention uses a general large model that has been trained with large-scale data and computing resources and can better capture complex data patterns and features.

[0037] In addition, if Figure 2 As shown, the present invention also pre-deploys a convolutional network for the above-mentioned first prediction model and the second prediction model. The convolutional network first extracts features from the first electricity demand historical data and the second electricity demand historical data, thereby obtaining the first electricity usage feature and the second electricity usage feature, and then inputs them into the first prediction model and the second prediction model respectively for in-depth processing and analysis.

[0038] In some embodiments, the calculating the second predicted electricity demand based on the first predicted electricity demand and the first electricity demand fluctuation coefficient includes: Retrieving power grid connection data of each user in the target area, extracting a third number of users with power grid connection records based on the power grid connection data, and determining a second power demand fluctuation coefficient based on the third number; The second predicted electricity demand is calculated based on the first predicted electricity demand, the first electricity demand fluctuation coefficient and the second electricity demand fluctuation coefficient.

[0039] In an embodiment of the present invention, the second predicted electricity demand calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient is based on the premise that all users in the target area are electricity demanders. However, with the development of distributed power technology, more and more users can deploy photovoltaic power generation equipment, wind power generation equipment, etc., and these users can connect their own excess electricity to the power grid as appropriate, that is, in addition to obtaining electricity from the power grid, they may also provide electricity to the power grid. The changes in the electricity demand of these users are more complicated. For example, due to the high proportion of electricity generated by a certain user, although the increase in electricity prices is large, it will not significantly affect the purchase of the predetermined electricity gap from the power grid; and, when the electricity generated by these users themselves drops significantly (for example, when the photovoltaic equipment generates insufficient electricity on rainy days), the electricity gap purchased from the power grid will become larger. Therefore, the present invention takes into account such users who can provide electricity to the power grid.

[0040] Specifically, the power grid connection data of each user in the target area is retrieved, and the third number of users with power grid connection records is screened out. The greater the third number of users who can connect to the power grid in the target area, the greater the probability of a large fluctuation in actual power consumption in the target area, that is, the greater the uncertainty, and vice versa. In this regard, the present invention is configured to determine a second power demand fluctuation coefficient based on the third number, and the second power demand fluctuation coefficient is positively correlated with the third number. At this point, the first predicted power demand and the second power demand fluctuation coefficient obtained above are multiplied together with the first power demand fluctuation coefficient, and a more accurate second predicted power demand is calculated.

[0041] It should be noted that, similar to the above, the present invention does not limit the conversion formula between the above third quantity and the second electricity demand fluctuation coefficient.

[0042] In some embodiments, determining an energy flexible scheduling management scheme according to the second predicted electricity demand includes: Setting specific scheduling objectives for energy scheduling, including but not limited to supply and demand balance, cost minimization, and energy efficiency maximization; The energy flexible scheduling management plan is determined based on the second predicted electricity demand and the scheduling target.

[0043] In the embodiment of the present invention, when determining the energy flexible scheduling management plan, in addition to considering meeting the electricity demand of each user in the target area, that is, ensuring the balance between supply and demand, it is also necessary to consider minimizing the cost and maximizing the energy efficiency when implementing energy scheduling.

[0044] It should be noted that a deep model can also be preset to generate a specific energy flexible scheduling management solution, which will not be elaborated here.

[0045] like Figure 3 As shown, an embodiment of the present invention further discloses a user-side energy flexible scheduling management system, the system comprising a processor and a memory, the processor runs a computer code stored in the memory to implement the following steps: Acquire first electricity demand historical data and second electricity demand historical data of each user in the target area; wherein only the second electricity demand historical data contains electricity price data with a fluctuation range higher than the first preset value and electricity supply and demand data with a fluctuation range higher than the second preset value; Using a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand; Using a second prediction model to perform prediction processing on the second electricity demand historical data to obtain a first electricity demand fluctuation coefficient; A second predicted electricity demand is calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, and an energy flexible scheduling management plan is determined according to the second predicted electricity demand.

[0046] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method described in the above embodiment.

[0047] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and is characterized in that: the computer program is executed by a processor to implement the method described in the above embodiment.

[0048] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0049] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A user-side energy flexible scheduling management method, characterized in that , the method comprises the following steps: Acquire first electricity demand historical data and second electricity demand historical data of each user in the target area; wherein only the second electricity demand historical data contains electricity price data with a fluctuation range higher than the first preset value and electricity supply and demand data with a fluctuation range higher than the second preset value; Using a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand; Using a second prediction model to perform prediction processing on the second electricity demand historical data to obtain a first electricity demand fluctuation coefficient; A second predicted electricity demand is calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, and an energy flexible scheduling management plan is determined according to the second predicted electricity demand.

2. A user-side energy flexible scheduling management method according to claim 1, characterized in that: Acquiring the first power demand historical data and the second power demand historical data of each user in the target area, including: Collect electricity consumption data of each user in the target area in real time or regularly through smart meters, energy management systems or user submission, including at least electricity consumption and electricity consumption time; Classifying the collected electricity consumption data according to time dimension and user attributes to form the first electricity demand historical data; Collect corresponding electricity price data and electricity supply and demand data according to each of the electricity usage times, and filter out the electricity price data with a fluctuation range higher than a first preset value and the electricity supply and demand data with a fluctuation range higher than a second preset value; The electricity consumption data is time-aligned and integrated with the electricity price data whose fluctuation range is higher than the first preset value, and the electricity supply and demand data whose fluctuation range is higher than the second preset value, to obtain the second electricity demand historical data.

3. A user-side energy flexible scheduling management method according to claim 2, characterized in that: Through smart meters, energy management systems or user submission, the electricity consumption data of each user in the target area is collected in real time or regularly, including: Collect first electricity usage data of all users in the target area according to a preset first time period, and extract from the first electricity usage data a first quantity of electricity usage data whose data sources are smart meters and energy management systems, and a second quantity of electricity usage data whose data sources are submitted by users; Determine an expansion coefficient according to a ratio of the first number to the second number, and multiply the first duration by the expansion coefficient to obtain a second duration; The second power usage data of all users in the target area are collected according to the second time period, and the second power usage data include the power usage data of each user.

4. A user-side energy flexible scheduling management method according to claim 3, characterized in that: Using a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand; Using the second prediction model to perform prediction processing on the second power demand historical data to obtain the first power demand fluctuation coefficient includes: Using a convolutional network to perform feature extraction on the first power demand historical data and the second power demand historical data respectively, to obtain a first power usage feature and a second power usage feature; Inputting the first electricity consumption feature into the first prediction model to obtain the first predicted electricity demand; wherein the first prediction model is constructed based on a deep learning model; The second electricity consumption characteristic is input into the second prediction model to obtain the first electricity demand fluctuation coefficient; wherein the second prediction model is constructed based on a general large model.

5. A user-side energy flexible scheduling management method according to claim 4, characterized in that: Calculating a second predicted electricity demand based on the first predicted electricity demand and the first electricity demand fluctuation coefficient includes: Retrieving power grid connection data of each user in the target area, extracting a third number of users with power grid connection records based on the power grid connection data, and determining a second power demand fluctuation coefficient based on the third number; The second predicted electricity demand is calculated based on the first predicted electricity demand, the first electricity demand fluctuation coefficient and the second electricity demand fluctuation coefficient.

6. A user-side energy flexible scheduling management method according to claim 5, characterized in that: Determining an energy flexible scheduling management plan according to the second predicted electricity demand includes: Setting specific scheduling objectives for energy scheduling, including but not limited to supply and demand balance, cost minimization, and energy efficiency maximization; The energy flexible scheduling management plan is determined based on the second predicted electricity demand and the scheduling target.

7. A user-side energy flexible scheduling management system, the system comprising a processor and a memory, characterized in that: The processor runs the computer code stored in the memory to implement the following steps: Acquire first electricity demand historical data and second electricity demand historical data of each user in the target area; wherein only the second electricity demand historical data contains electricity price data with a fluctuation range higher than the first preset value and electricity supply and demand data with a fluctuation range higher than the second preset value; Using a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand; Using a second prediction model to perform prediction processing on the second electricity demand historical data to obtain a first electricity demand fluctuation coefficient; A second predicted electricity demand is calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, and an energy flexible scheduling management plan is determined according to the second predicted electricity demand.

8. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images