A user side energy flexible scheduling management method and system

Abstract

The application belongs to the technical field of power dispatching. A user-side energy flexible scheduling management method and system are provided. The method comprises the following steps: acquiring first power consumption demand historical data and second power consumption demand historical data of each user in a target area; using a first prediction model to perform prediction processing on the first power consumption demand historical data to obtain a first predicted power consumption 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; 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. The aspects of the application simultaneously consider the historical power consumption law of the user and the influence of the fluctuation of the electricity price and the electricity supply and demand, and can significantly improve the accuracy and rationality of the determined energy flexible scheduling management scheme.

Description

TECHNICAL FIELD

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

[0002] By real-time monitoring, adjusting and optimizing the matching between user-side energy demand and supply, accurate control of energy flow can be realized, thereby improving the operation efficiency of the power system. The existing technology currently mainly predicts the electricity demand law of users in the region, and then determines the electricity dispatching strategy for users in the region. However, the above existing method lacks consideration of other factors, such as energy price, supply and demand situation, etc., resulting in a large difference between the predicted electricity demand and the actual electricity consumption, which is not conducive to determining a reasonable flexible dispatching scheme. SUMMARY

[0003] To solve the above technical problems, the present application provides a user-side energy flexible dispatching management method, system, electronic device, computer storage medium and computer program product.

[0004] The present application discloses a user-side energy flexible dispatching management method, which comprises the following steps:

[0005] Obtain the first electricity demand history data and the second electricity demand history data of each user in the target region; wherein only the second electricity demand history data contains power price data with a fluctuation amplitude higher than a first preset value and power supply and demand data with a fluctuation amplitude higher than a second preset value;

[0006] Use a first prediction model to predict and process the first electricity demand history data to obtain a first predicted electricity demand;

[0007] Use a second prediction model to predict and process the second electricity demand history data to obtain a first electricity demand fluctuation coefficient;

[0008] Based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, a second predicted electricity demand is calculated, and an energy flexible dispatching management scheme is determined according to the second predicted electricity demand.

[0009] In some embodiments, the first electricity demand history data and the second electricity demand history data of each user in the target region are obtained, comprising:

[0010] Through intelligent electric meters, energy management systems or user submission, real-time or periodic collection of electricity data of each user in the target region is performed, including at least electricity consumption and electricity time;

[0011] The collected power consumption data is classified according to time dimension and user attributes to form the first power consumption demand history data;

[0012] According to each power consumption time, corresponding power price data and power supply and demand data are collected, and the power price data with a fluctuation amplitude higher than a first preset value and the power supply and demand data with a fluctuation amplitude higher than a second preset value are screened out;

[0013] The power consumption data, the power price data with a fluctuation amplitude higher than the first preset value, and the power supply and demand data with a fluctuation amplitude higher than the second preset value are time-registered and integrated with the power consumption data to obtain the second power consumption demand history data.

[0014] In some embodiments, the power consumption data of each user in the target area is collected in real time or periodically through a smart meter, an energy management system or a user submission, including:

[0015] According to a preset first time length, the first power consumption data of all users in the target area is collected, and a first quantity of power consumption data from the smart meter and the energy management system and a second quantity of power consumption data from the user submission are obtained from the first power consumption data.

[0016] According to the ratio of the first quantity to the second quantity, an expansion coefficient is determined, and the second time length is obtained by multiplying the first time length by the expansion coefficient.

[0017] According to the second time length, the second power consumption data of all users in the target area is collected, and the power consumption data of each user is included in the second power consumption data.

[0018] In some embodiments, the first power consumption demand history data is processed using a first prediction model to obtain a first predicted power consumption demand, and the second power consumption demand history data is processed using a second prediction model to obtain a first power consumption demand fluctuation coefficient, including:

[0019] The first power consumption demand history data and the second power consumption demand history data are respectively extracted using a convolution network to obtain first power consumption features and second power consumption features.

[0020] The first power consumption features are input into the first prediction model to obtain the first predicted power consumption demand, wherein the first prediction model is constructed based on a deep learning model.

[0021] The second power consumption features are input into the second prediction model to obtain the first power consumption demand fluctuation coefficient, wherein the second prediction model is constructed based on a general large model.

[0022] In some embodiments, the second predicted electricity demand is calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, including:

[0023] The power grid connection data of each user in the target area is called, and a third quantity of users with power grid connection records is obtained according to the power grid connection data, and a second electricity demand fluctuation coefficient is determined according to the third quantity;

[0024] 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.

[0025] In some embodiments, the energy flexible scheduling management scheme is determined according to the second predicted electricity demand, including:

[0026] The specific scheduling target of energy scheduling is set, including but not limited to supply-demand balance and cost minimization, energy efficiency maximization;

[0027] The energy flexible scheduling management scheme is determined according to the second predicted electricity demand and the scheduling target.

[0028] The application also discloses a user-side energy flexible scheduling management system, which comprises a processor and a memory, and the processor runs computer codes stored in the memory to realize the following steps:

[0029] The first electricity demand historical data and the second electricity demand historical data of each user in the target area are obtained, wherein only the second electricity demand historical data contains power price data with a fluctuation amplitude higher than a first preset value and power supply-demand data with a fluctuation amplitude higher than a second preset value;

[0030] The first predicted electricity demand is obtained by using a first prediction model to predict the first electricity demand historical data;

[0031] The first electricity demand fluctuation coefficient is obtained by using a second prediction model to predict the second electricity demand historical data;

[0032] The 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 scheme is determined according to the second predicted electricity demand.

[0033] The application also discloses an electronic device, which comprises at least one processor, a memory and a computer program stored in the memory and capable of running on the at least one processor, and the processor executes the computer program to realize the method as described in any one of the preceding embodiments.

[0034] The application further discloses a computer storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method according to any one of the preceding.

[0035] The application further discloses a computer program product, which, when running on a terminal, enables the terminal to implement the method according to any one of the preceding.

[0036] The application has the following beneficial effects:

[0037] The application considers not only the historical power consumption rule of the user in the target area, but also the influence of the power price and the fluctuation of the power supply and demand of each user in the target area, so that the predicted power consumption demand is more accurate, and the accuracy and rationality of the energy flexible scheduling management scheme are improved. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0039] Figure 1 is a flowchart of a user-side energy flexible scheduling management method disclosed by the embodiments of the application;

[0040] Figure 2 is a schematic diagram of the relationship between the convolution network and the first prediction model and the second prediction model disclosed by the embodiments of the application;

[0041] Figure 3 is a structural schematic diagram of a user-side energy flexible scheduling management system disclosed by the embodiments of the application. DETAILED DESCRIPTION

[0042] The embodiments of the application will be described in detail by specific embodiments. Those skilled in the art can easily understand other advantages and effects of the application from the content disclosed in the specification. Obviously, the described embodiments are part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0043] In addition, the technical features involved in different embodiments of the application described below can be combined with each other as long as there is no conflict.

[0044] The prior art currently mainly predicts the electricity demand law of users in a region, and then determines the electricity scheduling strategy for users in the region. However, the above existing method lacks consideration of other factors, such as energy prices, supply and demand conditions, etc., resulting in a large difference between the predicted electricity demand and the actual electricity consumption, which is not conducive to determining a reasonable flexible scheduling scheme.

[0045] In view of the above defects of the prior art, as shown in the background art, embodiments of the present application disclose a user-side energy flexible scheduling management method, which comprises the following steps: Figure 1

[0046] Obtain first electricity demand historical data and second electricity demand historical data of each user in a target region; wherein only the second electricity demand historical data includes power price data with a fluctuation amplitude higher than a first preset value and power supply and demand data with a fluctuation amplitude higher than a second preset value;

[0047] Use a first prediction model to perform prediction processing on the first electricity demand historical data to obtain a first predicted electricity demand;

[0048] Use a second prediction model to perform prediction processing on the second electricity demand historical data to obtain a first electricity demand fluctuation coefficient;

[0049] Calculate a second predicted electricity demand based on the first predicted electricity demand and the first electricity demand fluctuation coefficient, and determine an energy flexible scheduling management scheme based on the second predicted electricity demand.

[0050] Compared with the existing processing method in the background art, the present application simultaneously collects two kinds of electricity demand historical data of each user in the target region, i.e. the first electricity demand historical data and the second electricity demand historical data. Among them, the first electricity demand historical data contains the actual electricity data of each user in the target region at different time periods, and the second electricity demand historical data includes, in addition to the actual electricity data, power price data with a fluctuation amplitude higher than a first preset value and power supply and demand data with a fluctuation amplitude higher than a second preset value corresponding to the time period.

[0051] ​Then, a preset first prediction model is used to predict the first historical electricity demand data to obtain the first predicted electricity demand; and a preset second prediction model is used to predict the second historical electricity demand data to obtain the 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 degree of influence. For example, when the electricity price increase is higher and the electricity supply is tighter, the first electricity demand fluctuation coefficient is lower, that is, the user's electricity demand shows a downward trend; when the electricity price increase is lower or the decrease is higher and the electricity supply is more abundant, the first electricity demand fluctuation coefficient is higher, that is, the electricity demand shows an upward trend. This is only an illustrative example of the basic principles and is not intended to limit the scope of protection of the present invention.

[0052] Finally, the second predicted electricity demand is calculated by multiplying the first electricity demand fluctuation coefficient by the aforementioned first predicted electricity demand. Compared with the first predicted electricity demand, the second predicted electricity demand takes into account the impact of fluctuations in electricity prices and electricity supply and demand among users in the target area. Therefore, the energy flexible dispatch management scheme determined based on the second predicted electricity demand will be more accurate and reasonable.

[0053] Therefore, in addition to considering the historical electricity consumption patterns of users within the target area, the present invention further considers the impact of fluctuations in electricity prices and electricity supply and demand on each user within the target area, making the determined predicted electricity demand more accurate, thereby significantly improving the accuracy and rationality of the determined flexible energy dispatch management scheme.

[0054] In some embodiments, obtaining the first and second historical electricity demand data of each user within the target area includes:

[0055] Collect electricity consumption data of each user in the target area in real time or periodically through smart meters, energy management systems or user submissions, including at least electricity consumption and electricity consumption time.

[0056] The collected electricity consumption data is classified according to time dimension and user attributes to form the first electricity demand historical data;

[0057] Based on the electricity consumption time, collect the corresponding electricity price data and electricity supply and demand data, and filter out the electricity price data with a fluctuation range higher than the first preset value and the electricity supply and demand data with a fluctuation range higher than the second preset value;

[0058] The power consumption data is time-matched and integrated with the power price data with a fluctuation amplitude higher than a first preset value, the power supply and demand data with a fluctuation amplitude higher than a second preset value, and the power consumption data, to obtain the second power consumption demand history data.

[0059] In the embodiments of the present application, the power consumption data of each user in the target area can be obtained in various ways or manners, and the power consumption data at least includes power consumption and power consumption time.

[0060] Smart meters: Modern smart meters can record users' power consumption data in real time, including power consumption, power consumption time, power factor, etc., and are important tools for obtaining power consumption demand history data. Energy management system: Some large enterprises or parks may be equipped with an energy management system, which can monitor and record power consumption data in real time, providing more detailed and accurate power consumption information. User submission: In some cases, users may voluntarily submit their power consumption data, especially when these data are important for developing personalized energy management solutions.

[0061] The collected power consumption data is classified according to time dimension and user attributes to form the first power consumption demand history data. The time dimension is, for example, day, week, month, and year. The power consumption data classified according to the time dimension can be used to analyze users' power consumption patterns and trends. The user attributes are, for example, residents, businesses, and industries. Since the power consumption characteristics of users with different attributes differ greatly, classifying power consumption data according to user attributes helps to analyze more accurate first predicted power consumption demand.

[0062] 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 piece of power consumption data. 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 amplitude higher than a first preset value and the power supply and demand data with a fluctuation amplitude higher than a second preset value can be selected, respectively. The first preset value and the second preset value are predetermined. The selected power price data and power supply and demand data are time-matched and then integrated with the corresponding power consumption data, to obtain the second power consumption demand history data.

[0063] In some embodiments, the power consumption data of each user in the target area is collected in real time or periodically by smart meters, energy management systems, or user submission, including:

[0064] According to a preset first time length, first power consumption data of all users in the target area is collected. From the first power consumption data, a first number of power consumption data from smart meters and energy management systems is extracted, and a second number of power consumption data from user submission is extracted.

[0065] An expansion coefficient is determined according to a ratio of the first quantity to the second quantity, and the first duration is multiplied by the expansion coefficient to obtain a second duration;

[0066] Second power consumption data of all users in the target area are collected according to the second duration, and the second power consumption data include the power consumption data of each user.

[0067] In the embodiments of the present application, the collection of the power consumption data of each user in the target area in the present application is divided into two stages. That is, first, first power consumption data of all users in the target area within a preset first duration (i.e., a first duration back to a historical time direction from a current time) are collected, and a first quantity of power consumption data whose source is an intelligent power meter and an energy management system and a second quantity of power consumption data whose source is a user-submitted mode are extracted from the first power consumption data. Then, a corresponding expansion coefficient is determined according to a ratio of the first quantity to the second quantity. The larger the ratio, the more the proportion of the power consumption data whose source is the intelligent power meter and the energy management system in the target area, and the data uploaded by the intelligent power meter and the energy management system is all preprocessed, such as correction and deduplication, and has higher credibility. Therefore, the first power consumption data also has higher credibility, and the expansion coefficient is set to be smaller at this time. The smaller the ratio, the less the proportion of the power consumption data whose source is the intelligent power meter and the energy management system in the target area. Since the data uploaded by the user-submitted mode has obvious deficiencies in data specification and data credibility, the data submitted by the user has lower credibility, and the first power consumption data also has lower credibility. Therefore, the expansion coefficient is set to be larger at this time, that is, more power consumption data is used to ensure the accuracy of the first predicted power consumption demand and the first power consumption demand fluctuation coefficient. The expansion coefficient is a value greater than 1.

[0068] Subsequently, the determined expansion coefficient is multiplied by the aforementioned first duration to obtain a corrected second duration, and the power consumption data of each user in the target area are collected according to the second duration, that is, the second power consumption data are obtained.

[0069] It should be noted that the present application does not limit the conversion formula between the ratio and the expansion coefficient.

[0070] In some embodiments, the first power consumption demand historical data are predicted using a first prediction model to obtain a first predicted power consumption demand, and the second power consumption demand historical data are predicted using a second prediction model to obtain a first power consumption demand fluctuation coefficient, including:

[0071] The first power consumption demand historical data and the second power consumption demand historical data are respectively subjected to feature extraction using a convolution network to obtain first power consumption features and second power consumption features.

[0072] inputting the first electricity consumption feature into the first prediction model to obtain the first predicted electricity demand quantity; wherein the first prediction model is constructed based on a deep learning model;

[0073] inputting the second electricity consumption feature 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.

[0074] In the embodiments of the present application, the first prediction model and the second prediction model described above are constructed to respectively predict the first predicted electricity demand quantity and the first electricity demand fluctuation coefficient. The first prediction model is constructed based on a deep learning model, which includes but is not limited to a convolutional neural network (CNN), a recurrent neural network (RNN), a transformer, etc. The second prediction model is constructed based on a general large model, which includes but is not limited to a GPT series model, BERT, T5, RoBERTa, etc.

[0075] Since the electricity consumption rule of a user is easy to grasp, a conventional deep learning model can be used to construct the first prediction model described above. However, the electricity consumption of a user is obviously more complex in terms of the influence degree of power price and power supply and demand fluctuations, so the present application uses a general large model that has been trained through large-scale data and computing resources to better capture complex data patterns and features.

[0076] In addition, as shown in FIG. 1, the present application also pre-disposes a convolutional network for the first prediction model and the second prediction model, which first extracts features from the first electricity demand historical data and the second electricity demand historical data to obtain the first electricity consumption feature and the second electricity consumption feature, and then inputs them into the first prediction model and the second prediction model for deep processing and analysis. Figure 2

[0077] In some embodiments, the calculation of the second predicted electricity demand quantity based on the first predicted electricity demand quantity and the first electricity demand fluctuation coefficient includes:

[0078] The power grid connection data of each user in the target area is retrieved, and the third quantity of users with power grid connection records is obtained according to the power grid connection data. The second electricity demand fluctuation coefficient is determined according to the third quantity;

[0079] The second predicted electricity demand quantity is calculated based on the first predicted electricity demand quantity, the first electricity demand fluctuation coefficient, and the second electricity demand fluctuation coefficient.

[0080] ​In the embodiments of the present application, the second predicted electricity demand calculated based on the first predicted electricity demand and the first electricity demand fluctuation coefficient is on the premise that all users in the target area are electricity demand sides. However, with the development of distributed power technology, more and more users can install, for example, photovoltaic power generation equipment, wind power generation equipment, etc., and these users can optionally connect the excess power generated by themselves to the power grid, that is, in addition to obtaining power from the power grid, they can also provide power to the power grid. The change of electricity demand of these users is more complex, for example, due to the high proportion of power generated by a user, although the power price rises greatly, it will not significantly affect the purchase of the planned power gap from the power grid; and when the power generated by these users decreases significantly (for example, when the photovoltaic equipment generates insufficient power due to rainy weather), the power gap purchased from the power grid will be larger. Therefore, the present application considers the users who can provide power to the power grid.

[0081] 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 selected from the power grid connection data. The more the third number of users in the target area that can connect to the power grid, the greater the probability of a large fluctuation in the actual electricity consumption in the target area, that is, the greater the uncertainty, and vice versa. Therefore, the present application sets the second electricity demand fluctuation coefficient determined according to the third number, and the second electricity demand fluctuation coefficient is positively correlated with the third number. At this point, the first predicted electricity demand and the second electricity demand fluctuation coefficient are multiplied by the first electricity demand fluctuation coefficient to calculate a more accurate second predicted electricity demand.

[0082] It should be noted that, similar to the foregoing, the present application does not limit the conversion formula between the third number and the second electricity demand fluctuation coefficient.

[0083] In some embodiments, the energy flexible scheduling management scheme is determined according to the second predicted electricity demand, comprising:

[0084] Setting specific scheduling targets for energy scheduling, including but not limited to supply-demand balance and cost minimization, energy efficiency maximization;

[0085] Determining the energy flexible scheduling management scheme according to the second predicted electricity demand and the scheduling target.

[0086] In the embodiments of the present application, when determining the energy flexible scheduling management scheme, in addition to considering meeting the electricity demand of each user in the target area, that is, ensuring the supply-demand balance, the cost minimization and energy efficiency maximization when implementing energy scheduling also need to be considered.

[0087] It should be noted that the depth model can also be preset to generate a specific energy flexibility scheduling management scheme, which will not be described here.

[0088] As shown in Figure 3 The embodiment of the application further discloses a user-side energy flexibility scheduling management system, which comprises a processor and a memory, and the processor runs computer codes stored in the memory to realize the following steps:

[0089] obtaining first power consumption demand history data and second power consumption demand history data of each user in a target area; wherein only the second power consumption demand history data comprises power price data with a fluctuation amplitude higher than a first preset value and power supply and demand data with a fluctuation amplitude higher than a second preset value;

[0090] using a first prediction model to perform prediction processing on the first power consumption demand history data to obtain a first predicted power consumption demand;

[0091] using a second prediction model to perform prediction processing on the second power consumption demand history data to obtain a first power consumption demand fluctuation coefficient;

[0092] 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 flexibility scheduling management scheme according to the second predicted power consumption demand.

[0093] The embodiment of the application 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 realize the method as described in the foregoing embodiments.

[0094] The embodiment of the application further discloses a computer storage medium, which stores a computer program, characterized in that: the computer program is executed by a processor to realize the method as described in the foregoing embodiments.

[0095] The embodiment of the application further discloses a computer program product, which, when running on a terminal, enables the terminal to execute the method as described in the foregoing embodiments.

[0096] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0097] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0098] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0099] The above description is only preferred embodiments of the present application, and not intended to limit the protection scope of the present application.

Claims

1. A user-side energy flexible scheduling management method, characterized in that, The method comprises the following steps: Obtaining first power consumption demand history data and second power consumption demand history data of each user in a target area; wherein only the second power consumption demand history data contains power price data with a fluctuation amplitude higher than a first preset value and power supply and demand data with a fluctuation amplitude higher than a second preset value; Using a first prediction model to perform prediction processing on the first power consumption demand history data to obtain a first predicted power consumption demand; Using a second prediction model to perform prediction processing on the second power consumption demand history data to obtain a first power consumption demand fluctuation coefficient; Based on the first predicted power consumption demand and the first power consumption demand fluctuation coefficient, a second predicted power consumption demand is calculated, and an energy flexible scheduling management scheme is determined according to the second predicted power consumption demand; Based on the first predicted power consumption demand and the first power consumption demand fluctuation coefficient, a second predicted power consumption demand is calculated, including: Retrieving power grid connection data of each user in the target area, and obtaining a third quantity of users with power grid connection records according to the power grid connection data, and determining a second power consumption demand fluctuation coefficient according to the third quantity; wherein the second power consumption demand fluctuation coefficient is positively correlated with the third quantity; Based on the first predicted power consumption demand, the first power consumption demand fluctuation coefficient and the second power consumption demand fluctuation coefficient, the second predicted power consumption demand is calculated. 2.The user-side energy flexible scheduling management method of claim 1, wherein: Obtaining first power consumption demand history data and second power consumption demand history data of each user in a target area, including: Collecting power consumption data of each user in the target area in real time or periodically through smart meters, energy management systems or user submission, at least including power consumption amount and power consumption time; Classifying the collected power consumption data according to time dimension and user attributes to form the first power consumption demand history data; According to each power consumption time, collecting corresponding power price data and power supply and demand data, and screening out the power price data with a fluctuation amplitude higher than a first preset value and the power supply and demand data with a fluctuation amplitude higher than a second preset value; Time registering and integrating the power consumption data, the power price data with a fluctuation amplitude higher than a first preset value and the power supply and demand data with a fluctuation amplitude higher than a second preset value with the power consumption data to obtain the second power consumption demand history data. 3.The user-side energy flexible scheduling management method of claim 2, wherein: Collecting power consumption data of each user in the target area in real time or periodically through smart meters, energy management systems or user submission, including: According to a preset first time length, collecting first power consumption data of all users in the target area, and obtaining a first quantity of power consumption data from smart meters and energy management systems and a second quantity of power consumption data from user submission from the first power consumption data; Determining an expansion coefficient according to the ratio of the first quantity to the second quantity, and multiplying the first time length by the expansion coefficient to obtain a second time length; According to the second time length, collecting second power consumption data of all users in the target area, which includes the power consumption data of each user. 4.The user-side energy flexible scheduling management method of claim 3, wherein: The first prediction model is used to perform prediction processing on the first power consumption demand historical data, to obtain a first predicted power consumption demand; The second prediction model is used to perform prediction processing on the second power consumption demand historical data, to obtain a first power consumption demand fluctuation coefficient, including: The first power consumption demand historical data and the second power consumption demand historical data are respectively subjected to feature extraction using a convolution network, to obtain first power consumption features and second power consumption features; The first power consumption features are input into the first prediction model, to obtain the first predicted power consumption demand; wherein the first prediction model is constructed based on a deep learning model; The second power consumption features are input into the second prediction model, to obtain the first power consumption demand fluctuation coefficient; wherein the second prediction model is constructed based on a general large model. 5.The user-side energy flexible scheduling management method of claim 1, wherein: An energy flexible scheduling management scheme is determined according to the second predicted power consumption demand, including: A specific scheduling target of energy scheduling is set, including but not limited to supply-demand balance, cost minimization, and energy efficiency maximization; The energy flexible scheduling management scheme is determined according to the second predicted power consumption demand and the scheduling target. 6.A user-side energy flexible scheduling management system, the system comprising a processor and a memory, characterized in that: The processor runs computer codes stored in the memory to implement the following steps: First power consumption demand historical data and second power consumption demand historical data of each user in a target region are obtained; wherein only the second power consumption demand historical data contains power price data with a fluctuation amplitude higher than a first preset value and power supply-demand data with a fluctuation amplitude higher than a second preset value; The first prediction model is used to perform prediction processing on the first power consumption demand historical data, to obtain a first predicted power consumption demand; The second prediction model is used to perform prediction processing on the second power consumption demand historical data, to obtain a first power consumption demand fluctuation coefficient; A second predicted power consumption demand is calculated based on the first predicted power consumption demand and the first power consumption demand fluctuation coefficient, and an energy flexible scheduling management scheme is determined according to the second predicted power consumption demand; A second predicted power consumption demand is calculated based on the first predicted power consumption demand and the first power consumption demand fluctuation coefficient, including: Power grid connection data of each user in the target region are retrieved, a third quantity of users with power grid connection records is obtained according to the power grid connection data, and a second power consumption demand fluctuation coefficient is determined according to the third quantity; wherein the second power consumption demand fluctuation coefficient is positively correlated with the third quantity; The second predicted power consumption demand is calculated based on the first predicted power consumption demand, the first power consumption demand fluctuation coefficient, and the second power consumption demand fluctuation coefficient.

7. 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 of any one of claims 1-5.

8. A computer storage medium storing a computer program, the computer program comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program is executed by the processor to implement the method of any one of claims 1-5.

9. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: The computer program is executed by the processor to implement the method of any one of claims 1-5.

Images