Virtual power plant load end resource optimization scheduling method, equipment and medium

Abstract

The invention relates to a virtual power plant load end resource optimization scheduling method and device and a medium, and is applied to the field of data processing, and the method comprises the steps: obtaining historical total electricity consumption corresponding to a plurality of historical periods of an energy supply range of a virtual power plant; according to the historical total electricity consumption corresponding to a plurality of historical periods of the energy supply range of the virtual power plant, estimating the first total electricity consumption required by the next period; for each region, according to the probability distribution model corresponding to the region and the first total electricity consumption, estimating the estimated electricity consumption of the maximum probability corresponding to the region; and performing power scheduling according to the estimated power consumption of the maximum probability corresponding to each region. According to the invention, after overall estimation, each region can be finely estimated based on the first total power consumption after overall estimation, overall data are considered, estimation data of each region are also considered, and the accuracy and reliability of power estimation are effectively improved.

Description

Technical Field

[0001] The present application relates to a field, and in particular to a method, device and medium for optimizing and scheduling load-side resources of a virtual power plant. Background Art

[0002] As an important direction for the deep integration of energy and information technology, virtual power plants effectively improve the system flexibility and the management level of load-side resources by power grid dispatching agencies by aggregating one or more controllable resources such as adjustable loads, energy storage, microgrids, electric vehicles, distributed power sources, etc. in different spaces, thereby promoting the supply and demand balance of the power grid.

[0003] In the related art, the energy supply range of the virtual power plant is divided into multiple regions, and the power consumption in the next cycle is estimated based on the historical data of each region, and then the total power consumption in the energy supply range of the virtual power plant is estimated, so as to facilitate the power scheduling of the next cycle according to the total power consumption. However, estimating the power consumption of a region based only on historical data may have estimation bias, making the estimation of the region inaccurate. Summary of the invention

[0004] The purpose of this application is to provide a method, device and medium for optimizing the scheduling of load-side resources of a virtual power plant, which can improve the accuracy and reliability of power estimation.

[0005] In a first aspect, a method for optimizing and scheduling load-side resources of a virtual power plant is provided, comprising: Obtain the historical total electricity consumption corresponding to each of multiple historical periods of the energy supply range of the virtual power plant; estimating a first total power consumption required for a next cycle according to the historical total power consumption corresponding to each of the multiple historical cycles of the energy supply range of the virtual power plant; Obtaining a probability distribution model of electricity consumption in each region of the energy supply range, wherein the probability distribution model is obtained by analyzing the historical electricity consumption of the region in each historical period and the historical total electricity consumption of the energy supply range in each historical period; For each region, based on the probability distribution model corresponding to the region and the first total power consumption, estimate the maximum probability power consumption corresponding to the region; Power dispatch is carried out according to the estimated power consumption with the maximum probability corresponding to each area.

[0006] Through the above technical scheme, by analyzing the total electricity consumption data of multiple historical periods, the first total electricity consumption of the next period is estimated; combined with the probability distribution model of electricity consumption in each region, the estimate is further refined, and the estimated electricity consumption with the maximum probability is allocated to each region. After the overall estimate, it is possible to make a detailed estimate of each region based on the first total electricity consumption after the overall estimate. In this scheme, not only the overall data is considered, but also the estimated data of each region, which effectively improves the accuracy and reliability of electricity estimation.

[0007] In an achievable manner, after estimating the estimated power consumption with the maximum probability corresponding to each region according to the probability distribution model corresponding to the region and the first total power consumption, the method further includes: Summarize the estimated power consumption with the maximum probability corresponding to each area to obtain the second total power consumption; Determine whether the difference between the first total power consumption and the second total power consumption is within a preset difference range; If yes, then executing the step of performing power dispatch according to the estimated power consumption with the maximum probability corresponding to each area; If not, then determining the effective historical total power consumption in the historical total power consumption corresponding to each of the multiple historical periods of the energy supply range of the virtual power plant, and determining the effective historical power consumption in each historical period of each area of ​​the energy supply range; According to the effective historical total power consumption, a new first total power consumption is estimated, Construct a new probability distribution model of electricity consumption in each region based on the effective historical electricity consumption in each historical period of each region within the energy supply range; For each region, according to the new probability distribution model corresponding to the region and the new first total power consumption, estimate the new maximum probability estimated power consumption corresponding to the region until the preset condition is met, thereby obtaining the maximum probability estimated power consumption corresponding to each region; The preset condition is that the number of iterations reaches a preset number threshold, or the difference between the first total power consumption and the second total power consumption is within a preset difference range.

[0008] Through the above technical solution, after the preliminary estimation of the power consumption of each region, the rationality of the estimation is judged by comparing the difference between the estimated total power consumption and the actual estimated target (the first total power consumption). If the difference exceeds the preset range, the iteration process is automatically triggered, and the probability distribution model is rebuilt using the selected valid historical data, and a new round of estimation is performed based on this. This process is repeated until the preset conditions are met (such as the number of iterations reaches the threshold or the difference is within an acceptable range), thereby ensuring the accuracy and adaptability of the power estimation and improving the rationality of the scheduling plan.

[0009] In an achievable manner, determining the effective historical total power consumption in the historical total power consumption corresponding to each of the multiple historical periods of the energy supply range of the virtual power plant, and determining the effective historical power consumption in each historical period of each area of ​​the energy supply range, includes: Determine a first difference in the historical total power consumption of adjacent cycles; Determine a first change time corresponding to the total power consumption according to the first difference; Determine the historical total power consumption corresponding to each period after the first change moment as the effective historical total power consumption; For each region, it is determined whether there is a first change moment. If there is a first change moment, the historical power consumption of the region in each historical period after the first change moment is determined as the effective historical power consumption.

[0010] Through the above technical solution, during the iteration process, by identifying the change moments of the historical total electricity consumption, based on the change moments, the valid historical data reflecting the changes and in line with the current situation is retained, so as to build a more accurate and stable probability distribution model and improve the accuracy of electricity estimation.

[0011] In one achievable manner, the present invention further includes: Determining whether the number of cycles after the first change moment is greater than a preset cycle number threshold; If not, then according to the first difference of the historical total power consumption of the adjacent cycles corresponding to the first change moment, correct the historical total power consumption before the first change moment, and use the corrected historical total power consumption as the supplementary effective historical total power consumption; For the area with the first change moment, the historical power consumption of the area before the first change moment is corrected according to the first difference in historical power consumption of the area in the adjacent periods corresponding to the first change moment, and the corrected historical power consumption is used as the supplementary effective historical power consumption.

[0012] Through the above technical solution, when faced with insufficient historical data or sudden changes, the continuity and stability of power estimation can be ensured by correcting historical data or adjusting the identification method of the sudden change moment, making the power estimation system more robust.

[0013] In an achievable manner, determining the first change time of the total power consumption according to the first difference includes: Determine the initial first change time of the total power consumption according to the first difference; For each region, determining a second difference in historical power consumption of the region in adjacent periods; determining a second change time of the region according to the second difference; determining whether the second change moment is the same as the first change moment; If not, the initial first change moment is adjusted according to the second change moment to obtain the first change moment.

[0014] Through the above technical scheme, when determining the mutation moment of total electricity consumption, not only the changing trend of total electricity consumption is taken into account, but also the changing situation of electricity consumption in each region is combined. By comprehensively comparing the mutation moments of the two, the first change moment is corrected, and the accurate identification of the mutation moment is achieved, which further improves the accuracy and reliability of mutation identification.

[0015] In one achievable manner, the power dispatching according to the estimated power consumption with the maximum probability corresponding to each area includes: Determine the first priority of each area based on the area information of each area; Determine the second priority for each area based on the estimated electricity consumption of each area; Determine the priority of each area based on the first and second priorities; Power is allocated according to the priority of each area.

[0016] Through the above technical scheme, this scheme establishes a power dispatch priority system that comprehensively considers multiple factors. In the power dispatch process, not only the second priority of the estimated power consumption of each region is considered, but also the first priority determined by combining regional information (such as subject type, impact index, environmental information, etc.). Through the method of comprehensive evaluation of multiple factors, the priority is determined, and then power is allocated based on the priority, making the power dispatch more reasonable.

[0017] In an achievable manner, the regional information includes: subject type, impact index, and environmental information; Based on the regional information of each area, determine the first priority of each area, including: Determine the first sub-priority for each area based on the subject type; Determine the initial second sub-priority for each region based on the impact index; According to the environmental information, the initial second sub-priority of each area is modified to obtain the second sub-priority; A weighted calculation is performed based on the first sub-priority and the second sub-priority to obtain a first priority for each area.

[0018] Through the above technical solution, when determining the first priority of a region, not only the basic factor of the subject type is taken into consideration, but also the impact index and environmental information are introduced as adjustment factors. By quantifying the impact of these factors on regional priorities and performing weighted calculations, a more accurate and detailed regional priority ranking is obtained.

[0019] In an achievable manner, after performing weighted calculation based on the first sub-priority and the second sub-priority to obtain the first priority of each area, the method further includes: After receiving the emergency demand index, modifying the first priority according to the emergency demand index and the first priority; Accordingly, determining the priority of each area according to the first priority and the second priority includes: The priority of each area is determined based on the revised first priority and second priority.

[0020] Through the above technical solution, the emergency demand index is introduced as a correction factor, which makes it possible to flexibly respond to emergencies or urgent needs. By receiving and analyzing the emergency demand index in real time, the priority ranking of each area can be quickly adjusted. This dynamic adjustment mechanism ensures that power resources can be quickly and accurately allocated to where they are most needed in an emergency, thereby improving the flexibility and response speed of power dispatch.

[0021] In a second aspect, an electronic device is provided, the electronic device comprising: one or more processors; Memory; One or more applications, wherein one or more applications are stored in a memory and configured to be executed by one or more processors, and one or more programs are configured to: perform operations corresponding to the method shown in any possible implementation of the first aspect.

[0022] In a third aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by a processor to implement a method as shown in any possible implementation of the first aspect.

[0023] According to a fourth aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method is implemented as shown in any possible implementation manner of the first aspect.

[0024] In summary, the present application includes at least one of the following beneficial technical effects: 1. By analyzing the total electricity consumption data of multiple historical periods, the first total electricity consumption of the next period is estimated; combined with the probability distribution model of electricity consumption in each region, the estimate is further refined, and the estimated electricity consumption with the highest probability is allocated to each region. After the overall estimate, each region can be estimated in detail based on the first total electricity consumption after the overall estimate. In this solution, not only the overall data but also the estimated data of each region are considered, which effectively improves the accuracy and reliability of electricity estimation; 2. After preliminarily estimating the power consumption of each region, the rationality of the estimate is determined by comparing the difference between the estimated total power consumption and the actual estimated target (the first total power consumption). If the difference exceeds the preset range, the iteration process is automatically triggered, and the probability distribution model is rebuilt using the filtered valid historical data, and a new round of estimates is made based on this. This process is repeated until the preset conditions are met (such as the number of iterations reaches the threshold or the difference is within an acceptable range), thereby ensuring the accuracy and adaptability of the power estimate and improving the rationality of the scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a structural diagram of a virtual power plant load-side resource optimization and scheduling system provided in an embodiment of the present application; Figure 2 It is a flow chart of a method for optimizing resource scheduling at the load end of a virtual power plant provided in an embodiment of the present application; Figure 3 It is a schematic diagram of a data screening process provided by an embodiment of the present application; Figure 4 It is a schematic diagram of a priority determination process provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. 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 this field without creative work are within the scope of protection of this application.

[0028] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0029] As a cutting-edge energy management concept and technical practice, the virtual power plant (VPP) goes beyond the scope of traditional physical power plants. Relying on advanced information and communication technology and intelligent software systems, it cleverly weaves distributed distributed power sources (DG), energy storage devices, adjustable loads, electric vehicles and other diversified distributed energy resources (DER) into a highly integrated virtual energy network. This network exists in a non-physical form, but it can flexibly participate in the transactions of the power market and the daily operation of the power grid like a unified entity, promoting the intelligent dispatching and refined management of electricity. By continuously monitoring the supply and demand dynamics of the power grid, the virtual power plant uses advanced algorithm models to deeply mine and analyze massive data, accurately predict the trend of power demand, and thus formulate the most optimized power supply and dispatching plan. This process not only greatly improves the comprehensive utilization efficiency of energy, but also effectively enhances the resilience and stability of the power system, providing a solid guarantee for the stable operation of the power market.

[0030] In actual operation, refer to Figure 1 The virtual power plant collects real-time operating data of various DERs; processes and analyzes these data in combination with the areas that need power supply to formulate the optimal power dispatch strategy; and sends dispatch instructions to each DER to achieve accurate dispatch and optimal configuration of electricity.

[0031] In an embodiment of the present application, a virtual power plant load-side resource optimization scheduling method is provided, which can accurately predict the next cycle of electricity within the energy supply range of the virtual power plant to facilitate accurate scheduling of electricity.

[0032] Specifically, the present application embodiment provides a method for optimizing the scheduling of load-side resources of a virtual power plant, such as Figure 2 As shown, the method provided in the embodiment of the present application can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes: S101, obtaining the historical total power consumption corresponding to each of multiple historical periods of the energy supply range of the virtual power plant; Each virtual power plant has a corresponding energy supply range and corresponding distributed energy. The energy supply range refers to the geographical area or customer group to which the virtual power plant can provide power services. The historical period is used to represent a period of time in the past divided by specific time intervals (such as days, weeks, and months). The historical total electricity consumption represents the total amount of electricity consumed by all users or devices within the energy supply range of the virtual power plant during the historical period.

[0033] Specifically, if the energy supply range of the virtual power plant needs to be determined, the energy supply range corresponding to the current virtual power plant can be determined by querying the pre-stored mapping relationship between the virtual power plant and the energy supply range.

[0034] In one possible scenario, the selection of cycles may be multiple cycles in the recent period, or multiple cycles in the same period of each year, or other periods. This embodiment of the present application does not limit this, and the user may set it according to actual needs as long as the purpose of this embodiment can be achieved.

[0035] In some embodiments, the electricity consumption data of all users within the energy supply range of the virtual power plant is obtained through the database; these data are cleaned and sorted, and abnormal values ​​and duplicate data are removed; the data are grouped and summarized according to the selected historical period, and the total electricity consumption of each period is calculated. It is understandable that other methods can also be used to achieve this, such as obtaining electricity consumption data through a third-party data service provider, or using Internet of Things technology to achieve real-time monitoring and aggregation of electricity consumption. This is not limited here, and the specific implementation method can be flexibly selected according to actual conditions and needs.

[0036] S102, estimating a first total power consumption required for a next cycle according to the historical total power consumption corresponding to each of the multiple historical cycles within the energy supply range of the virtual power plant; The first total electricity consumption required for the next cycle refers to the total electricity consumption that may be required within the energy supply scope of the virtual power plant in a certain future cycle, estimated based on historical data and prediction models.

[0037] In some embodiments, a time series analysis method (such as an ARIMA model) can be used to analyze the historical total electricity consumption corresponding to multiple historical periods, identify seasonal patterns and trends in electricity consumption changes, and obtain the first total electricity consumption required for the next period.

[0038] Specifically, when predicting the next cycle based on the time series analysis method, the entire cycle can be used for prediction, and a local combination method can also be used for prediction. For example, the cycle is divided into multiple time periods according to a preset number of divisions, and then all historical cycles are divided according to the time periods to obtain multiple sub-historical time periods. For example, each cycle is divided into 5 time periods, and the first time period of each historical cycle is used as the first data group, the second time period is used as the second data group, and so on, to obtain 5 data groups; for the data group corresponding to each sub-historical time period, a prediction is performed according to the time series analysis method to obtain the sub-total power consumption of each sub-historical time period corresponding to the next cycle, and then all sub-total power consumptions are summarized to obtain the first total power consumption.

[0039] Furthermore, after obtaining the first total electricity consumption, the first total electricity consumption is adjusted based on external factors such as the current market environment and weather conditions as adjustment parameters to obtain the first total electricity consumption required for the next cycle, thereby ensuring the accuracy and reliability of the prediction results.

[0040] Of course, other methods can also be used for prediction, which are not limited in the embodiments of the present application, and users can set them according to actual needs.

[0041] S103, obtaining a probability distribution model of power consumption in each region within the energy supply range, where the probability distribution model is obtained by analyzing the historical power consumption of the region in each historical period and the historical total power consumption of the energy supply range in each historical period; S104: for each region, based on the probability distribution model corresponding to the region and the first total power consumption, estimate the estimated power consumption with the maximum probability corresponding to the region; Each energy supply direction is divided into multiple areas. When dividing the energy supply range into regions, it can be divided based on geographical proximity, or based on grid connection conditions, or based on user types (residential electricity, commercial electricity, factory electricity).

[0042] The probability distribution model is built based on historical data and can reflect the changing patterns and trends of power consumption.

[0043] In some embodiments, this step can be implemented in a variety of ways: Method 1: Select a suitable probability distribution model (such as normal distribution, Poisson distribution or Weibull distribution, etc.), divide the historical total electricity consumption into total intervals, and the data in each total interval are similar; then for each total interval, estimate the electricity consumption, and obtain the probability distribution of each region in multiple intervals as the probability distribution model.

[0044] Method 2: Use machine learning algorithms (such as random forests, neural networks, etc.) to build a probability distribution model for power consumption. This method can automatically learn the characteristics and rules of power consumption from data without manually specifying the model form. According to the historical total power consumption data, input the training model to obtain the probabilities corresponding to multiple intervals, and use the intervals corresponding to the historical power consumption of the region to iteratively train the machine learning model; evaluate the performance of the model through methods such as cross-validation, and adjust the model parameters to improve the prediction accuracy to obtain the final model; the trained model is used as the probability distribution model of the region.

[0045] It is understandable that this step can also be implemented in other ways, such as prediction methods based on expert systems, fuzzy reasoning methods, etc., which are not limited here.

[0046] The estimated power consumption with the highest probability is the power consumption prediction value that is most likely to occur in a certain area, calculated based on the probability distribution model and the first total power consumption. This value corresponds to the highest probability density or the greatest possibility in the probability distribution.

[0047] Furthermore, when the probability distribution model is obtained by method 1, the probability distribution model corresponding to the first total power consumption can be selected to analyze the region to obtain the estimated power consumption corresponding to the maximum probability. Of course, if the current date or climate is special, the estimated power consumption can be increased or decreased accordingly after obtaining the estimated power consumption, providing accurate data support for subsequent energy management and power grid dispatching.

[0048] When the probability distribution model is obtained through method 2, advanced machine learning or deep learning algorithms are used to directly predict regional electricity consumption and obtain the estimated electricity consumption with the highest probability. This method can automatically learn complex patterns and relationships in the data and improve the accuracy and efficiency of the prediction.

[0049] S105. Perform power dispatch according to the estimated power consumption with the maximum probability corresponding to each area.

[0050] After obtaining the estimated electricity consumption, the total electricity consumption can be summarized and then electricity dispatch can be carried out. The estimated electricity consumption of each area can also be used for electricity dispatch separately, aiming to meet the electricity demand of each area while ensuring the stable operation of the power system.

[0051] It can be seen that in the embodiment of the present application, by analyzing the total electricity consumption data of multiple historical periods, the first total electricity consumption of the next period is estimated; combined with the probability distribution model of electricity consumption in each region, the estimate is further refined, and the estimated electricity consumption with the maximum probability is allocated to each region. After the overall estimate, it is possible to make a detailed estimate of each region based on the first total electricity consumption after the overall estimate, taking into account not only the overall data but also the estimated data of each region, thereby effectively improving the accuracy and reliability of the electricity estimate.

[0052] Further, see Figure 3 In order to improve the accuracy of determining the estimated power consumption, in the embodiment of the present application, for each region, according to the probability distribution model corresponding to the region and the first total power consumption, after estimating the estimated power consumption with the maximum probability corresponding to the region, the method further includes: S201, summarizing the estimated power consumption with the maximum probability corresponding to each area to obtain a second total power consumption; The estimated power consumption with the maximum probability corresponding to all areas is summed up to obtain the second total power consumption.

[0053] S202, determining whether the difference between the first total power consumption and the second total power consumption is within a preset difference range; The preset difference range is a custom setting. When it is within this range, it means that the estimation of the area is accurate. When it is not within this range, it means that there is an error in the estimation and further verification and adjustment are required.

[0054] S203: If yes, then executing the step of dispatching power according to the estimated power consumption with the maximum probability corresponding to each area; S204, if not, determining the effective historical total power consumption in the historical total power consumption corresponding to each of the multiple historical periods within the energy supply range of the virtual power plant, and determining the effective historical power consumption in each historical period of each area within the energy supply range; Effective historical total electricity consumption: refers to the historical total electricity consumption data that can truly reflect the historical electricity consumption situation under the current state.

[0055] Effective historical electricity consumption: refers to the actual electricity consumption data of each area within the energy supply range of the virtual power plant within a specific historical period that can truly reflect the current state.

[0056] Specifically, the effective historical total power consumption in the historical total power consumption corresponding to each of the multiple historical periods of the energy supply range of the virtual power plant is determined, and the effective historical power consumption in each historical period of each area of ​​the energy supply range is determined, including SA1-SA4 (not shown in the drawings), wherein: SA1. Determine the first difference of the historical total power consumption in adjacent cycles; Adjacent cycles refer to two consecutive and adjacent time periods in the time series, which are used to compare and analyze the changing trend of electricity consumption.

[0057] SA2. Determine a first change time corresponding to the total power consumption according to the first difference; The first change moment refers to the moment when the electricity consumption changes significantly based on the change of the first difference. The change needs to be continuous rather than sporadic. This moment may mark some important shift in electricity demand or supply, indicating that the state of the area may have changed.

[0058] A curve graph is drawn according to the first difference, and a change moment closest to the current moment is determined according to the curve graph as the first change moment.

[0059] If there is a change, the first change moment is obtained; If there is no change, determine whether there is a change time for each area. If there is a change time in a certain area, the most recent change time is selected as the effective change time, and the historical electricity consumption data after the change time of the area with the effective change time is used as the effective historical electricity consumption data, and the other areas remain unchanged.

[0060] SA3. Determine the historical total power consumption corresponding to each period after the first change moment as the effective historical total power consumption; SA4. For each area, determine whether there is a first change moment. If so, determine the historical power consumption of the area in each historical period after the first change moment as the effective historical power consumption.

[0061] Each region has its own electricity consumption patterns. If an area is an industrial production area, the electricity consumption may be relatively stable and will not change. Some areas are living areas and may change due to environmental influences.

[0062] For each region, determine whether there is a change moment based on the historical power consumption of the region; If it exists, further determine whether the change moment includes the first change moment, if so, determine the historical power consumption of the area in each historical period after the first change moment as the effective historical power consumption, if not, determine the historical power consumption of the area in each historical period after the most recent change as the effective historical power consumption; If it does not exist, all historical electricity consumption will be regarded as effective historical electricity consumption.

[0063] Through the above method, effective power consumption information can be determined.

[0064] It can be seen that in the embodiment of the present application, during the iteration process, by identifying the change time of the historical total power consumption, based on the change time, the valid historical data reflecting the change and conforming to the current situation is retained, so as to build a more accurate and stable probability distribution model and improve the accuracy of power estimation.

[0065] S205, estimating a new first total power consumption based on the effective historical total power consumption; S206, constructing a new probability distribution model of electricity consumption in each region according to the effective historical electricity consumption in each historical period of each region within the energy supply range; S207. For each region, according to the new probability distribution model corresponding to the region and the new first total power consumption, estimate the new maximum probability estimated power consumption corresponding to the region until a preset condition is met, thereby obtaining the maximum probability estimated power consumption corresponding to each region; The preset condition is that the number of iterations reaches a preset number threshold, or the difference between the first total power consumption and the second total power consumption is within a preset difference range.

[0066] Iterative estimation: If the number of repeated estimations reaches the preset number, the cycle is stopped and the final power consumption is used as the estimated power consumption, or the technician revises the estimated power consumption based on experience.

[0067] It can be seen that in the embodiment of the present application, after the preliminary estimation of the power consumption of each area, the rationality of the estimation is judged by comparing the difference between the estimated total power consumption and the actual estimated target (the first total power consumption). If the difference exceeds the preset range, the iteration process is automatically triggered, and the probability distribution model is rebuilt using the screened valid historical data, and a new round of estimation is performed based on this. This process is repeated until the preset conditions are met (such as the number of iterations reaches the threshold or the difference is within an acceptable range), thereby ensuring the accuracy and adaptability of the power estimation and improving the rationality of the scheduling plan.

[0068] Furthermore, if the number of cycles after the first change moment is small, the accuracy of the model may be affected. In order to further improve the accuracy, the method further includes: Determining whether the number of cycles after the first change moment is greater than a preset cycle number threshold; If not, then according to the first difference of the historical total power consumption of the adjacent cycles corresponding to the first change moment, correct the historical total power consumption before the first change moment, and use the corrected historical total power consumption as the supplementary effective historical total power consumption; For the area with the first change moment, the historical power consumption of the area before the first change moment is corrected according to the first difference in historical power consumption of the area in the adjacent periods corresponding to the first change moment, and the corrected historical power consumption is used as the supplementary effective historical power consumption.

[0069] The preset cycle quantity threshold can be set according to actual needs.

[0070] When the number of cycles after the first change moment is not greater than the preset cycle number threshold, it means that the amount of data is small. The difference in the historical total power consumption of adjacent cycles corresponding to the first change moment is calculated, and the historical total power consumption before the first change moment is corrected according to the first difference in the historical total power consumption of adjacent cycles corresponding to the first change moment. Specifically, the difference + historical total power consumption = corrected historical total power consumption is obtained to supplement the effective historical charging capacity and increase the data sample.

[0071] When there are other change moments in the area with the first change moment, data correction can be performed by combining the differences corresponding to the multiple change moments with the difference corresponding to the first change moment. In one possible situation, all data can be corrected, or a preset number of data can be corrected to supplement a sufficient number of data samples.

[0072] It can be seen that in the embodiment of the present application, when faced with insufficient historical data or sudden changes, the continuity and stability of the power estimation are ensured by correcting the historical data or adjusting the identification method of the sudden change moment, making the power estimation system more robust.

[0073] A possible implementation of the embodiment of the present application is to determine the first change time of total power consumption according to the difference, including: Determine the initial first change time of the total power consumption according to the first difference; For each region, determining a second difference in historical power consumption of the region in adjacent periods; determining a second change time of the region according to the second difference; determining whether the second change moment is the same as the first change moment; If not, the initial first change moment is adjusted according to the second change moment to obtain the first change moment.

[0074] In an embodiment of the present application, when the change moment determined based on the total power consumption is different from the change moment of the region, the most recent moment among all the second change moments can be selected as the first change moment to make the change moment more accurate.

[0075] It can be seen that in the embodiment of the present application, when determining the mutation moment of the total electricity consumption, not only the changing trend of the total electricity consumption is taken into consideration, but also the changes in electricity consumption in each region are combined. By comprehensively comparing the mutation moments of the two, the first change moment is corrected, and accurate identification of the mutation moment is achieved, further improving the accuracy and reliability of mutation identification.

[0076] Combination Figure 4When dispatching electricity, different priorities are determined for different areas to achieve priority supply and ensure the stability of power supply in important areas. Specifically, electricity dispatch is performed according to the estimated electricity consumption with the maximum probability corresponding to each area, including: SC1-SC4 (not shown in the attached figure), where: SC1. Determine the first priority of each area based on the area information of each area; Regional information includes: subject type, impact index, and environmental information; Based on the regional information of each area, determine the first priority of each area, including: Determine the first sub-priority for each area based on the subject type; Determine the initial second sub-priority for each region based on the impact index; According to the environmental information, the initial second sub-priority of each area is modified to obtain the second sub-priority; A weighted calculation is performed based on the first sub-priority and the second sub-priority to obtain a first priority for each area.

[0077] Specifically, the subject type is the main electricity consumers in the region, such as residential electricity, commercial electricity, and factory electricity.

[0078] The electronic device is preset with corresponding relationships between different subject types and different priorities, so as to facilitate determination of the first sub-priority level; The electronic device is preset with corresponding relationships between different ranges of impact indexes and different priorities, so as to facilitate determination of the initial second sub-priority level; Environmental information: represents various conditions and states in the current environment or scenario, including but not limited to temperature, humidity, light intensity, and flow of people. This information is crucial for evaluating the importance or urgency of different areas. Environmental information may have an impact on the power consumption of the area. Through environmental information, the initial second sub-priority is corrected so that the obtained second sub-priority is closer to the actual situation of the current environment and can more accurately guide subsequent resource allocation, task scheduling or decision-making. Different environmental information settings have different modification coefficients or adjustment amounts, so as to obtain the coefficient or adjustment amount corresponding to the current environmental information, correct the initial second sub-priority, and obtain the second sub-priority.

[0079] When determining the first priority of a region, not only the basic factor of the subject type is taken into consideration, but also the impact index and environmental information are introduced as adjustment factors. By quantifying the impact of these factors on regional priorities and performing weighted calculations, a more accurate and detailed regional priority ranking is obtained.

[0080] SC2, determine the second priority of each area based on the estimated power consumption of each area; The more power consumption is estimated to be, the higher the corresponding second priority is.

[0081] SC3. Determine the priority of each area based on the first priority and the second priority; A weighted calculation is performed based on each priority to obtain the priority of the area.

[0082] SC4. Allocate power according to the priority of each area.

[0083] It can be seen that in the embodiment of the present application, a power dispatch priority system that comprehensively considers multiple factors is established. In the power dispatch process, not only the second priority of the estimated power consumption of each area is considered, but also the first priority determined by the regional information (such as subject type, impact index, environmental information, etc.). The priority is determined through a multi-factor comprehensive evaluation method, and then power is allocated based on the priority, making the power dispatch more reasonable.

[0084] Furthermore, a possible implementation of the embodiment of the present application, after performing weighted calculation based on the first sub-priority and the second sub-priority to obtain the first priority of each area, further includes: After receiving the emergency demand index, modifying the first priority according to the emergency demand index and the first priority; Accordingly, the priority of each area is determined according to the first priority and the second priority, including: The priority of each area is determined based on the revised first priority and second priority.

[0085] In the embodiment of the present application, the emergency demand index indicates the urgency of a certain demand or task in the current situation, and is usually a quantitative indicator used to measure the urgency with which the demand or task needs to be processed.

[0086] After receiving the emergency demand index, if the index indicates that there is an emergency demand that needs immediate treatment or special attention, a comprehensive analysis and evaluation will be conducted based on the specific value of the emergency demand index and the first priority to adjust the first priority to better respond to the emergency demand.

[0087] In some embodiments, the operation of modifying the first priority according to the emergency demand index can be implemented in multiple ways: Optionally, a correspondence between an emergency demand index and a priority adjustment range is preset. When the emergency demand index is received, the specific range by which the priority needs to be adjusted is determined based on the correspondence; finally, the adjustment range is applied to the first priority to obtain a revised new priority.

[0088] Optionally, a dynamic priority adjustment algorithm is used, which can analyze the changes in the emergency demand index T and the first priority P of the current system in real time, automatically calculate the optimal priority adjustment plan, and update the first priority in real time, see Table 1.

[0089] Table 1 Specifically, a first index threshold T1 and a second index threshold T2 are preset, and the first index threshold T1 is smaller than the second index threshold T; a first priority threshold P1 and a second priority threshold P2 are preset, and the first priority threshold P1 is smaller than the second priority threshold P2.

[0090] When the emergency demand index is less than the first index threshold, the first priority remains unchanged; When the emergency demand index is greater than the first index threshold, the first priority is adjusted to the maximum priority; When the emergency demand index is between the first index threshold and the second index threshold, if the first priority is greater than the second priority threshold, the first priority is adjusted to the maximum priority; if the first priority is less than the first priority threshold, the priority corresponding to the current emergency demand index is determined according to the preset correspondence between the emergency demand index and the priority, and the first priority is replaced; if the first priority is between the first priority threshold and the second priority threshold, the priority corresponding to the current emergency demand index is determined according to the preset correspondence between the emergency demand index and the priority, and the priority and the first priority are weighted to obtain the priority, and the first priority is replaced. When performing weighted calculations, the weight value can be customized by the user. This approach can respond to changes in emergency needs more flexibly and intelligently.

[0091] It is understandable that other methods may be used to implement the operation of modifying the first priority according to the emergency demand index, such as decision support based on expert systems, fuzzy logic reasoning, etc., which are not limited here.

[0092] It can be seen that in the embodiment of the present application, the emergency demand index is introduced as a correction factor, which makes it possible to flexibly respond to emergencies or emergency needs. By receiving and analyzing the emergency demand index in real time, the priority ranking of each area can be quickly adjusted; this dynamic adjustment mechanism ensures that power resources can be quickly and accurately allocated to where they are most needed in an emergency, thereby improving the flexibility and response speed of power dispatch.

[0093] A possible implementation of the embodiment of the present application is to allocate power according to the priority of the region, including: Obtaining energy information corresponding to each of multiple power supply energy sources of the virtual power grid, the energy information including: power supply stability and available power; According to the priority of the region and the energy information corresponding to each of the multiple power supply energy sources, power supply energy and the power supply amount corresponding to the power supply energy are allocated to each region.

[0094] Sort the regions according to their priorities, and then traverse the sorted region list in turn. For each region, one or more energy sources are selected from multiple power supply energy sources for allocation based on its priority and energy demand. In the selection process, factors such as power generation, cost, and stability of the power supply energy are comprehensively considered, and the optimal power supply allocation plan is calculated through the optimization algorithm.

[0095] An electronic device is provided in an embodiment of the present application, such as Figure 5 As shown, Figure 5 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0096] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0097] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0098] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0099] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0100] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0101] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0102] An embodiment of the present application provides a computer program product, including a computer program, which implements the corresponding contents of the aforementioned method embodiment when the computer program is executed by a processor.

[0103] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0104] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for optimizing and scheduling load-side resources of a virtual power plant, characterized in that: include: Obtain the historical total electricity consumption corresponding to each of multiple historical periods of the energy supply range of the virtual power plant; estimating a first total power consumption required for a next cycle according to the historical total power consumption corresponding to each of the multiple historical cycles of the energy supply range of the virtual power plant; Obtaining a probability distribution model of electricity consumption in each region of the energy supply range, wherein the probability distribution model is obtained by analyzing the historical electricity consumption of the region in each historical period and the historical total electricity consumption of the energy supply range in each historical period; For each region, based on the probability distribution model corresponding to the region and the first total power consumption, estimate the maximum probability power consumption corresponding to the region; Power dispatch is carried out according to the estimated power consumption with the maximum probability corresponding to each area.

2. The method for optimizing and scheduling load-side resources of a virtual power plant according to claim 1, characterized in that: After estimating the estimated power consumption with the maximum probability corresponding to the region according to the probability distribution model corresponding to the region and the first total power consumption for each region, the method further includes: Summarize the estimated power consumption with the maximum probability corresponding to each area to obtain the second total power consumption; Determine whether the difference between the first total power consumption and the second total power consumption is within a preset difference range; If yes, then executing the step of performing power dispatch according to the estimated power consumption with the maximum probability corresponding to each area; If not, then determining the effective historical total power consumption in the historical total power consumption corresponding to each of the multiple historical periods of the energy supply range of the virtual power plant, and determining the effective historical power consumption in each historical period of each area of ​​the energy supply range; According to the effective historical total power consumption, a new first total power consumption is estimated, Construct a new probability distribution model of electricity consumption in each region based on the effective historical electricity consumption in each historical period of each region within the energy supply range; For each region, according to the new probability distribution model corresponding to the region and the new first total power consumption, estimate the new maximum probability estimated power consumption corresponding to the region until the preset condition is met, thereby obtaining the maximum probability estimated power consumption corresponding to each region; The preset condition is that the number of iterations reaches a preset number threshold, or the difference between the first total power consumption and the second total power consumption is within a preset difference range.

3. The method for optimizing and scheduling load-side resources of a virtual power plant according to claim 2, characterized in that: The determining of the effective historical total power consumption in the historical total power consumption corresponding to each of the multiple historical periods of the energy supply range of the virtual power plant, and the determining of the effective historical power consumption in each historical period of each area of ​​the energy supply range, include: Determine a first difference in the historical total power consumption of adjacent cycles; Determine a first change time corresponding to the total power consumption according to the first difference; Determine the historical total power consumption corresponding to each period after the first change moment as the effective historical total power consumption; For each region, it is determined whether there is a first change moment. If there is a first change moment, the historical power consumption of the region in each historical period after the first change moment is determined as the effective historical power consumption.

4. The method for optimizing and scheduling load-side resources of a virtual power plant according to claim 3, characterized in that: Also includes: Determining whether the number of cycles after the first change moment is greater than a preset cycle number threshold; If not, then according to the first difference of the historical total power consumption of the adjacent cycles corresponding to the first change moment, correct the historical total power consumption before the first change moment, and use the corrected historical total power consumption as the supplementary effective historical total power consumption; For the area with the first change moment, the historical power consumption of the area before the first change moment is corrected according to the first difference in historical power consumption of the area in the adjacent periods corresponding to the first change moment, and the corrected historical power consumption is used as the supplementary effective historical power consumption.

5. The method for optimizing and scheduling load-side resources of a virtual power plant according to claim 3, characterized in that: The determining the first change moment of total power consumption according to the first difference includes: Determine the initial first change time of the total power consumption according to the first difference; For each region, determining a second difference in historical power consumption of the region in adjacent periods; determining a second change time of the region according to the second difference; determining whether the second change moment is the same as the first change moment; If not, the initial first change moment is adjusted according to the second change moment to obtain the first change moment.

6. The method for optimizing and dispatching load-side resources of a virtual power plant according to any one of claims 1 to 5, characterized in that: The power dispatching according to the estimated power consumption with the maximum probability corresponding to each area includes: Determine the first priority of each area based on the area information of each area; Determine the second priority for each area based on the estimated electricity consumption of each area; Determine the priority of each area based on the first and second priorities; Power is allocated according to the priority of each area.

7. The method for optimizing and scheduling load-side resources of a virtual power plant according to claim 6, characterized in that: The regional information includes: subject type, impact index, and environmental information; Based on the regional information of each area, determine the first priority of each area, including: Determine the first sub-priority for each area based on the subject type; Determine the initial second sub-priority for each region based on the impact index; According to the environmental information, the initial second sub-priority of each area is modified to obtain the second sub-priority; A weighted calculation is performed based on the first sub-priority and the second sub-priority to obtain a first priority for each area.

8. The method for optimizing and scheduling load-side resources of a virtual power plant according to claim 7, characterized in that: After the first priority of each area is obtained by weighted calculation based on the first sub-priority and the second sub-priority, the following steps are also included: After receiving the emergency demand index, modifying the first priority according to the emergency demand index and the first priority; Accordingly, determining the priority of each area according to the first priority and the second priority includes: The priority of each area is determined based on the revised first priority and second priority.

9. An electronic device, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the steps of the virtual power plant load-side resource optimization scheduling method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded by the processor and executes the steps of the virtual power plant load-end resource optimization scheduling method according to any one of claims 1 to 8.

Images