Optimal configuration method and device based on virtual power plant resources and computer equipment

Abstract

The invention relates to an optimal configuration method, device and equipment based on virtual power plant resources. The method comprises the following steps: acquiring resource parameters of each virtual power plant resource, historical load data associated with each virtual power plant resource, external load data and user behavior data, and constructing a resource characteristic model for each virtual power plant resource according to the resource parameters, the historical load data, the external load data and the user behavior data, according to historical load data, external load data and user behavior data, load prediction is carried out according to the historical load data, the external load data and the user behavior data to obtain a load prediction result, adjustable capability indexes are determined according to the load prediction result and the resource characteristic model, and weighted fusion is carried out according to the adjustable capability indexes and the index weights of the adjustable capability indexes to obtain a resource evaluation result. And performing optimal configuration on each virtual power plant resource according to a preset configuration demand and the resource evaluation result corresponding to each virtual power plant resource. The method can improve the resource utilization rate and reduce the energy consumption.

Description

Technical Field

[0001] The present application relates to the field of smart grid technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for optimizing configuration of virtual power plant resources. Background Art

[0002] With the development of smart grid technology and the gradual realization of automation, informatization and intelligence of power systems, virtual power plants have emerged to solve the problems of supply and demand imbalance, low system operation efficiency, and energy waste in power systems. By integrating and managing distributed energy resources and participating in demand response and energy trading, virtual power plants can provide auxiliary services to the power grid, such as frequency regulation, peak and valley load regulation, etc., thereby improving the flexibility and responsiveness of the entire power system.

[0003] However, the different types of resources involved in traditional virtual power plants are usually distributed in different geographical locations. If it is necessary to integrate multiple different types of distributed energy resources, such as solar energy, wind energy, energy storage equipment, etc., it is necessary to manage, schedule and integrate multiple different types in different geographical locations. Due to the diversity and dispersion of resource types, the overall external characteristics of virtual power plants may be very complex, with strong uncertainty and dynamic change characteristics. Therefore, when allocating resources, it is necessary to consider multiple factors, such as the output characteristics, load characteristics, and response speed of resources. There are still problems such as cumbersome resource allocation process and low configuration processing efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product based on virtual power plant resources that can improve the efficiency of resource configuration processing of different types in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for optimizing configuration of virtual power plant resources, comprising:

[0006] Acquire different types of virtual power plant resources and resource parameters of each of the virtual power plant resources, and acquire historical load data, external load data, and user behavior data associated with each of the virtual power plant resources;

[0007] For each of the virtual power plant resources, construct a resource characteristic model corresponding to the virtual power plant resource according to resource parameters of the virtual power plant resource, and historical load data, external load data, and user behavior data associated with the virtual power plant resource;

[0008] Perform load forecasting based on historical load data, external load data, and user behavior data associated with the virtual power plant resources to obtain load forecasting results corresponding to the virtual power plant resources;

[0009] Determine the adjustable capacity index corresponding to the virtual power plant resource according to the load forecast result corresponding to the virtual power plant resource and the resource characteristic model, and perform weighted fusion according to the adjustable capacity index corresponding to the virtual power plant resource and the index weight corresponding to each of the adjustable capacity indicators to obtain a resource evaluation result corresponding to the virtual power plant resource;

[0010] According to the resource evaluation results corresponding to each of the virtual power plant resources and the preset configuration requirements, each of the virtual power plant resources is optimally configured.

[0011] In a second aspect, the present application also provides an optimization configuration device based on virtual power plant resources, comprising:

[0012] A virtual power plant resource acquisition module, used to acquire different types of virtual power plant resources and resource parameters of each of the virtual power plant resources, and to acquire historical load data, external load data and user behavior data associated with each of the virtual power plant resources;

[0013] A resource characteristic model building module, for building a resource characteristic model corresponding to each virtual power plant resource according to resource parameters of the virtual power plant resource, and historical load data, external load data and user behavior data associated with the virtual power plant resource;

[0014] A load forecasting module, configured to perform load forecasting based on historical load data, external load data, and user behavior data associated with the virtual power plant resources, and obtain load forecasting results corresponding to the virtual power plant resources;

[0015] A resource evaluation result obtaining module, used to determine the adjustable capacity index corresponding to the virtual power plant resource according to the load forecast result corresponding to the virtual power plant resource and the resource characteristic model, and to perform weighted fusion according to the adjustable capacity index corresponding to the virtual power plant resource and the index weight corresponding to each of the adjustable capacity indexes, so as to obtain the resource evaluation result corresponding to the virtual power plant resource;

[0016] The resource optimization configuration module is used to optimize the configuration of each virtual power plant resource according to the resource evaluation results corresponding to each virtual power plant resource and the preset configuration requirements.

[0017] In a third aspect, the present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned optimization configuration method based on virtual power plant resources are implemented.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method for optimizing configuration of virtual power plant resources when executed by a processor.

[0019] In a fifth aspect, the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned optimization configuration method based on virtual power plant resources are implemented.

[0020] In the above-mentioned optimization configuration method, device, computer equipment, computer-readable storage medium and computer program product based on virtual power plant resources, by obtaining different types of virtual power plant resources, resource parameters of each virtual power plant resource, and historical load data, external load data and user behavior data associated with each virtual power plant resource, it is possible to construct a resource characteristic model corresponding to the virtual power plant resource for each virtual power plant resource according to the resource parameters of the virtual power plant resource, and the historical load data, external load data and user behavior data associated with the virtual power plant resource. Furthermore, load forecasting is performed based on historical load data, external load data, and user behavior data associated with virtual power plant resources to obtain load forecasting results corresponding to virtual power plant resources, and based on the load forecasting results and resource characteristic models corresponding to the virtual power plant resources, adjustable capacity indicators corresponding to the virtual power plant resources are determined, and weighted fusion is performed based on the adjustable capacity indicators corresponding to the virtual power plant resources and the indicator weights corresponding to each adjustable capacity indicator to obtain resource evaluation results corresponding to the virtual power plant resources, so as to optimize the configuration of each virtual power plant resource based on the resource evaluation results corresponding to each virtual power plant resource and preset configuration requirements, so that various virtual power plant resources can be more effectively mined and utilized through precise resource characteristic analysis and adjustable capacity evaluation, so as to improve resource utilization and reduce energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0022] FIG1 is a diagram of an application environment of an optimization configuration method based on virtual power plant resources in one embodiment;

[0023] Figure 2 It is a flowchart of an optimization configuration method based on virtual power plant resources in one embodiment;

[0024] Figure 3 A schematic diagram of a process for constructing a resource characteristic model corresponding to virtual power plant resources in one embodiment;

[0025] Figure 4 A schematic diagram of a process for determining an adjustable capacity indicator corresponding to a virtual power plant resource in one embodiment;

[0026] Figure 5 A schematic diagram of a process for optimizing the configuration of resources of each virtual power plant in one embodiment;

[0027] Figure 6 It is a flow chart of an optimization configuration method based on virtual power plant resources in another embodiment;

[0028] Figure 7 It is a structural block diagram of an optimization configuration device based on virtual power plant resources in one embodiment;

[0029] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0031] The optimization configuration method based on virtual power plant resources provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the terminal device 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal device 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices, portable wearable devices, and aircraft, etc. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, and projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, and head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, or a server cluster composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal device 102 and the server 104 may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0032] Among them, the terminal device 102 and the server 104 can be used alone to execute the optimization configuration method based on virtual power plant resources provided in the embodiment of the present application, and the terminal device 102 and the server 104 can also cooperate to execute the optimization configuration method based on virtual power plant resources provided in the embodiment of the present application. For example, taking the terminal device 102 and the server 104 cooperating to execute the optimization configuration method based on virtual power plant resources provided in the embodiment of the present application as an example, when the server 104 receives the resource configuration request fed back by the terminal device 102, by obtaining different types of virtual power plant resources, resource parameters of each virtual power plant resource, and historical load data, external load data and user behavior data associated with each virtual power plant resource, it can construct a resource characteristic model corresponding to the virtual power plant resource for each virtual power plant resource according to the resource parameters of the virtual power plant resource, and the historical load data, external load data and user behavior data associated with the virtual power plant resource. Furthermore, the server 104 performs load forecasting based on historical load data, external load data, and user behavior data associated with the virtual power plant resources to obtain load forecasting results corresponding to the virtual power plant resources, thereby determining the adjustable capacity indicators corresponding to the virtual power plant resources based on the load forecasting results and resource characteristic models corresponding to the virtual power plant resources, and performing weighted fusion based on the adjustable capacity indicators corresponding to the virtual power plant resources and the indicator weights corresponding to each adjustable capacity indicator to obtain resource evaluation results corresponding to the virtual power plant resources. Finally, based on the resource evaluation results corresponding to each virtual power plant resource and preset configuration requirements, each virtual power plant resource can be optimized and configured, and the corresponding resource configuration results can be fed back to the terminal device 102.

[0033] In an exemplary embodiment, Figure 2 As shown, a method for optimizing configuration based on virtual power plant resources is provided, and the method is applied to the server 104 in FIG. 1 as an example for explanation, including the following steps S202 to S210. Among them:

[0034] Step S202, obtaining different types of virtual power plant resources and resource parameters of each virtual power plant resource, and obtaining historical load data, external load data and user behavior data associated with each virtual power plant resource.

[0035] Specifically, when the server receives a resource configuration request, it responds to the resource configuration request and obtains multiple different types of virtual power plant resources that can be configured, as well as resource parameters of each virtual power plant resource.

[0036] Among them, the types of virtual power plant resources include air conditioning load, energy storage equipment, charging piles, distributed photovoltaics and controllable loads. Specifically: 1) The resource parameters of air conditioning load include power range, response time, and adjustable capacity. Among them, the power of the air conditioner depends on its model and cooling / heating capacity, usually ranging from 1-5 kilowatts, while the response time indicates the time it takes for the air conditioner to respond to changes in grid demand, ranging from a few seconds to a few minutes, and the adjustable capacity means that the air conditioner can adjust its power consumption by adjusting the temperature setting or turning it on / off. 2) The resource parameters of energy storage equipment include energy storage capacity, charging and discharging efficiency, cycle life, and response speed. Among them, energy storage capacity indicates the total energy storage capacity of the energy storage device, usually measured in kilowatt-hours (kWh), and charging and discharging efficiency indicates the energy conversion efficiency of the energy storage device during charging and discharging. The cycle life indicates the number of times the energy storage device can be charged and discharged, affecting its long-term reliability, and the response speed indicates the speed at which the energy storage device responds to changes in grid demand. 3) The resource parameters of charging piles include charging power, charging efficiency, and usage mode. Among them, charging power refers to the maximum power that the charging pile can provide, which affects the charging speed, usually ranging from a few kilowatts to tens of kilowatts. Charging efficiency refers to the conversion efficiency of electric energy from the power grid to electric vehicles, and usage mode refers to the frequency of use of the charging pile and the impact of charging time on the power grid load. 4) The resource parameters of distributed photovoltaics include installed capacity, efficiency, and sunshine conditions. Among them, installed capacity refers to the total power generation capacity of each distributed photovoltaic, usually measured in kilowatts (kW), efficiency refers to the efficiency of photovoltaic panels converting solar energy into electrical energy, and sunshine conditions refer to photovoltaic power generation affected by the intensity and duration of sunshine, which is intermittent and uncertain. 5) The resource parameters of controllable loads (such as industrial loads) include load size, flexibility, and scheduling capability. Among them, load size refers to the scale of the load. For example, the scale of industrial loads is usually large and can provide significant adjustment capabilities. Flexibility can be understood as the adjustability of the load, which depends on the characteristics of the production process and equipment, and scheduling capability refers to the ability of the load to be scheduled according to the needs of the power grid, which may affect production efficiency.

[0037] Furthermore, the server needs to obtain historical load data, external load data and user behavior data associated with each virtual power plant resource. Among them, historical load data represents the historical usage data of different types of virtual power plant resources, including power consumption, power curve, and response time, etc., external load data represents the external factors that affect the load, such as weather forecasts, holiday arrangements, and economic activities, etc., and user behavior data represents the power consumption data related to the user, such as the user's power consumption history data, response habits and preferences, etc.

[0038] In an exemplary embodiment, user behavior data includes: 1) Electricity usage history data: the user's past electricity usage records, including daily, weekly or monthly electricity usage and electricity usage time. 2) Time pattern: the user's electricity usage habits in different time periods of the day, such as electricity usage patterns in the morning, daytime, evening and late night. 3) Seasonal pattern: changes in user electricity usage behavior in different seasons (spring, summer, autumn and winter). 4) Holiday pattern: changes in user electricity usage behavior during holidays, such as the Spring Festival, National Day, etc. 5) Temperature sensitivity: the response of user electricity usage behavior to temperature changes, such as increased use of air conditioners in summer and increased use of heating equipment in winter. 6) Price sensitivity: the user's response to changes in electricity prices, such as increasing electricity consumption or participating in demand response when electricity prices are lower.

[0039] Among them, the role of user behavior data in load forecasting includes: 1) Improving forecast accuracy: By understanding the user's electricity usage habits, the accuracy of load forecasting can be improved, thereby better performing resource scheduling and grid management. 2) Promoting energy efficiency: By analyzing user behavior patterns, energy-saving potential can be discovered, and users can be encouraged to adopt more efficient electricity usage methods, thereby improving overall energy efficiency. 3) Personalized services: Using user behavior data, users can be provided with more personalized services and suggestions, such as customized energy-saving suggestions and demand response plans.

[0040] In an exemplary embodiment, the user behavior data such as the user's response habits, preferences, and trustworthiness are identified based on the user's historical records of participation in demand response and ancillary services. Demand response refers to the behavior of electricity users to actively adjust their electricity consumption patterns based on electricity market price signals or incentives. The purpose of demand response is to balance the supply and demand of the power grid through user-side adjustments, improve the operating efficiency and reliability of the power grid, and bring economic benefits to users. Specifically, demand response can target the following needs: 1) Peak and valley load regulation: reduce electricity consumption during peak electricity demand periods, or increase electricity consumption during valley periods to balance the load on the power grid. 2) Emergency load reduction: When an emergency occurs in the power grid (such as equipment failure or extreme weather), users reduce electricity consumption at the request of the power grid operator.

[0041] Ancillary services refer to the various services required by the power system to maintain stable, safe and efficient operation in addition to the basic power supply, including: 1) Frequency regulation: Help maintain the grid frequency within a stable range by quickly increasing or decreasing power generation or power load. 2) Peak and valley load regulation: Balance the peak and valley loads of the grid through demand response or other means to reduce dependence on expensive peak-load power generation resources. 3) Spinning reserve: Power plants or users retain a portion of unused power generation or power consumption capacity for rapid call-up in the event of an emergency in the grid. 4) Reactive power support: Provide reactive power to maintain grid voltage stability. 5) Black start: Restart the grid through specific generators or facilities after a complete power outage.

[0042] Specifically, the user's response habits refer to the user's tendency to adjust his or her electricity consumption behavior when faced with changes in grid demand or price signals, including: 1) Response speed: the speed at which the user adjusts his or her electricity consumption behavior after receiving a demand response signal, that is, users who respond quickly can quickly reduce or increase electricity consumption when the grid needs it. 2) Response frequency: the frequency with which the user participates in demand response, that is, the number of times the user participates in demand response within a certain period of time. 3) Response amplitude: the degree to which the user adjusts electricity consumption in a demand response event. The user's preference refers to the user's choice tendency in electricity consumption and demand response, including:

[0043] 1) Price sensitivity: The user's sensitivity to changes in electricity prices. Price-sensitive users may be more willing to reduce electricity consumption when electricity prices are high. 2) Comfort preference: The user's preference for comfort such as indoor temperature and lighting affects the user's response to demand response. 3) Equipment usage habits: The user's usage habits for specific equipment (such as air conditioners and water heaters) also affect the user's response to demand response. 4) Energy-saving awareness: The user's energy-saving awareness and environmental awareness can encourage users to participate in demand response more actively.

[0044] Among them, reliability refers to the reliability of users to abide by their commitments in demand response events and adjust their electricity consumption as agreed, including: 1) Historical fulfillment records: the records of users to abide by their commitments in past demand response events, such as whether they have reduced their electricity consumption on time and in quantity each time. 2) Stability: the consistency and predictability of users' response behavior, that is, whether users always show similar response behaviors in similar situations. 3) Communication reliability: the reliability of the communication channel through which users receive demand response signals, such as whether they can always receive signals in a timely manner. The reliability of ancillary services refers to the reliability and stability of ancillary service providers (such as power plants, energy storage facilities, and demand response aggregators) when providing services, including: 1) Service availability: the availability of ancillary services when needed, that is, whether service providers can always provide the required services. 2) Performance stability: whether the performance of ancillary services is stable, such as whether frequency regulation services can continuously and stably provide the required regulation. 3) Response time: the response time of ancillary services, that is, the time from when the service provider receives the demand signal to when it starts to provide services.

[0045] Step S204, for each virtual power plant resource, a resource characteristic model corresponding to the virtual power plant resource is constructed according to the resource parameters of the virtual power plant resource, and the historical load data, external load data and user behavior data associated with the virtual power plant resource.

[0046] Specifically, for each virtual power plant resource, the resource prediction target corresponding to the virtual power plant resource is determined based on the resource parameters of the virtual power plant resource, and the initial machine learning model is trained based on the historical load data, external load data and user behavior data associated with the virtual power plant resource. When it is determined that the prediction result obtained by the initial machine learning model for the resource prediction target meets the model training end condition, the initial machine learning model that meets the training end condition is determined as the resource characteristic model corresponding to the virtual power plant resource.

[0047] The resource characteristic model is used for the physical and operational characteristics of resources, including: 1) Efficiency: the efficiency of resource conversion or power usage. 2) Capacity: the maximum output or input capacity of resources. 3) Response time: the time from when a resource receives an instruction to when it starts responding.

[0048] Furthermore, the resource prediction target specifically includes: one or more of the resource reduction potential, cost-effectiveness ratio and response speed. Specifically, the process of predictive analysis for resource prediction targets includes: 1) Analysis of resource reduction potential, and the analysis process includes: A) Data collection: Collect historical usage data of resources, including power consumption, usage frequency, equipment capacity, etc. B) Model establishment: Establish a resource usage model to analyze the potential reduction of resources under different conditions. C) Scenario analysis: Evaluate the resource reduction potential by simulating different demand response scenarios, such as price incentives and emergency load reduction events. D) User participation evaluation: Analyze the user's willingness to participate in demand response and historical response behavior. The analysis results of resource reduction potential include: A) Maximum reduction: The maximum power consumption that a resource can reduce within a specific time. B) Reduction duration: The length of time that a resource can continue to reduce. C) Reduction cost: The cost required to achieve reduction, including incentive cost and operating cost. 2) Analysis of cost-effectiveness ratio, and the analysis process includes: A) Cost data collection: Collect cost data for resource operation and maintenance, including initial investment, operating cost, maintenance cost, etc. B) Benefit evaluation: evaluate the benefits of resources participating in virtual power plants, such as energy cost savings, incentives obtained, improved system stability, etc. C) Cost-benefit model: establish a cost-benefit analysis model to calculate the ratio of total cost to total benefit of resources. Sensitivity analysis: analyze the sensitivity of costs and benefits to changes in key parameters, such as electricity price fluctuations, changes in equipment efficiency, etc. Among them, the analysis results of cost-benefit ratio include: A) Cost-benefit ratio: the benefits brought by each unit cost of resources. B) Payback period: the length of time it takes for resource investment to be recovered. C) Cost sensitivity: the sensitivity of resource benefits to cost changes. 3) Analysis of response speed: the analysis process includes: A) Real-time data monitoring: real-time monitoring of the operating status of resources and their ability to respond to changes in grid demand. B) Delay time measurement: measure the time delay from receiving the dispatch instruction to the actual response of the resource. C) Performance testing: evaluate the response performance of resources through simulation tests, such as fast start, fast stop, etc. D) User behavior analysis: analyze the impact of users on resource response speed, such as the response time of users to demand response. Among them, the analysis results of response speed include: A) Response time: the actual time from receiving the instruction to starting the response of the resource. B) Response consistency: The consistency and reliability of a resource’s response. C) Responsiveness: How quickly a resource can reach its maximum reduction or increase in power usage.

[0049] Step S206, performing load forecasting based on historical load data, external load data, and user behavior data associated with the virtual power plant resources, and obtaining load forecasting results corresponding to the virtual power plant resources.

[0050] Specifically, for each virtual power plant resource, power consumption pattern analysis and load trend analysis are performed on the historical load data associated with the virtual power plant resource to obtain the historical power consumption pattern and load change trend corresponding to the virtual power plant resource, and external demand analysis and personalized power consumption analysis are performed on the external load data and user behavior data associated with the virtual power plant resources to obtain external demand analysis results and personalized power consumption analysis results. Therefore, load forecasting can be performed based on the historical power consumption pattern, load change trend, external demand analysis results and personalized power consumption analysis results corresponding to the virtual power plant resources to obtain load forecasting results corresponding to the virtual power plant resources.

[0051] Furthermore, in the process of load forecasting, historical load data, external load data, and user behavior data jointly affect the accuracy and reliability of the forecast results. Their respective roles are:

[0052] 1) Historical data: A) Trend analysis: Historical data shows past electricity consumption patterns and load change trends, which helps to identify long-term trends, such as annual or seasonal growth. B) Periodicity identification: By analyzing historical data, you can identify periodic patterns of load, such as the difference between weekdays and weekends, or peak electricity consumption at different times of the day. C) Anomaly detection: Historical data can be used to identify abnormal events, such as sudden increases or decreases in load caused by emergencies, which can improve the accuracy of the prediction model. 2) External load data: A) Weather conditions: Weather factors such as temperature, humidity, wind speed, and sunshine have a significant impact on load, such as the load on heating and cooling demand. B) Holidays and weekdays: The electricity consumption patterns on holidays and weekdays are usually different from those on weekdays. Identifying holidays can more accurately predict load. C) Policies and regulations: Policy factors such as changes in electricity prices and energy-saving regulations can also affect users' electricity consumption behavior. 3) User behavior data: A) Personalized electricity consumption: The electricity consumption habits and preferences of different users usually affect the electricity consumption patterns of the corresponding users, such as some users may use more electricity at night. B) Equipment usage: The power usage pattern of specific equipment used by users (such as air conditioners, water heaters, electric vehicle chargers, etc.) has a direct impact on the load.

[0053] In an exemplary embodiment, when performing power consumption pattern analysis and load trend analysis on historical load data associated with virtual power plant resources, the following analysis methods may be used:

[0054] 1) Time series analysis method: predict future load by analyzing the time series characteristics of historical load data, such as trend, seasonality and periodicity. The specific process includes: A) Data stabilization: perform differential or transformation processing on non-stationary time series data. B) Model selection: select a time series model suitable for the data characteristics, such as ARIMA (i.e., differential integrated moving average autoregressive model), seasonal ARIMA (i.e., seasonal differential integrated moving average autoregressive model), etc. C) Parameter estimation: estimate model parameters, such as autoregressive terms, moving average terms, seasonal parameters, etc. D) Model verification: verify the model through historical data and adjust the model parameters to improve the prediction accuracy. 2) Regression analysis method: use the relationship between historical load data and other influencing factors (such as temperature, economic indicators) to establish a regression model for prediction. The specific process includes: A) Variable selection: determine the main factors affecting the load. B) Model establishment: construct a multivariate linear regression or nonlinear regression model. C) Parameter estimation: estimate the regression model parameters through historical data. D) Model verification: use methods such as cross-validation to verify the prediction ability of the model. 3) Machine learning methods: Use machine learning algorithms, such as random forests, support vector machines, neural networks, etc., to learn patterns in historical data and make predictions. The specific process includes: A) Data preprocessing: Including feature selection, data standardization, etc. B) Model training: Use historical data to train machine learning models. C) Model tuning: Optimize model performance by adjusting model parameters and structure. D) Model verification: Verify the prediction accuracy of the model through the test set. 4) Ensemble methods: Combine multiple forecasting methods and improve the accuracy and stability of forecasts through ensemble learning techniques. The specific process includes: A) Method selection: Select multiple forecasting methods, such as time series analysis, regression analysis, machine learning, etc. B) Model training: Train the model of each method separately. C) Ensemble strategy: Determine the ensemble strategy, such as voting, weighted average, stacking, etc. D) Model verification: Verify the performance of the ensemble model through historical data.

[0055] Specifically, by using analysis methods such as time series analysis, regression analysis, machine learning, and integration methods, the historical load data associated with the virtual power plant resources are analyzed for power consumption patterns and load trend analysis, and the historical power consumption patterns and load change trends corresponding to the virtual power plant resources can be obtained. Similarly, time series analysis, regression analysis, machine learning, and integration methods can also be used to analyze the external load data and user behavior data associated with the virtual power plant resources, respectively, to perform external demand analysis and personalized power consumption analysis, and obtain external demand analysis results and personalized power consumption analysis results. Among them, by integrating the historical power consumption patterns, load change trends, external demand analysis results, and personalized power consumption analysis results corresponding to the virtual power plant resources, a comprehensive load forecast can be conducted from multiple aspects, and the load forecast results corresponding to the virtual power plant resources can be accurately obtained.

[0056] Step S208, based on the load forecast results and resource characteristic model corresponding to the virtual power plant resources, determine the adjustable capacity indicators corresponding to the virtual power plant resources, and perform weighted fusion based on the adjustable capacity indicators corresponding to the virtual power plant resources and the indicator weights corresponding to each adjustable capacity indicator to obtain the resource evaluation results corresponding to the virtual power plant resources.

[0057] The adjustable capacity indicators corresponding to the virtual power plant resources include: the upward adjustment margin, downward adjustment margin, response rate, maximum adjustable power, and maximum adjustment step of the virtual power plant resources.

[0058] 1) Upward adjustment margin: refers to the additional power that the virtual power plant resources can provide in the current state to support the grid's ability to increase power supply during peak demand. Its functions include: A) Grid support: During peak power demand, upward adjustment margin can help meet additional power demand and prevent grid overload. B) Frequency regulation: By providing additional power, resources can help maintain the frequency stability of the grid. C) Emergency response: When an emergency occurs in the grid (such as a generator failure), upward adjustment margin can be used as an emergency resource to respond quickly. 2) Downward adjustment margin: refers to the power that the virtual power plant resources can reduce in the current state to support the grid's ability to reduce power supply during low demand. Its functions include: A) Load management: During low power demand, downward adjustment margin can help reduce the power supply pressure of the grid and optimize resource use. B) Energy conservation: By reducing unnecessary power output, downward adjustment margin helps save energy and reduce operating costs. C) Demand response: Users can respond to the needs of the grid by reducing electricity consumption, participate in demand response programs, and receive economic incentives. 3) Maximum adjustable power: indicates the maximum power that the virtual power plant resources can adjust in the current state, which is usually determined by the upward adjustment margin and the upward adjustment margin, specifically taking the smaller value of the upward adjustment margin and the upward adjustment margin. 4) Response rate: indicates the speed at which the virtual power plant resources adjust the power during the resource configuration process, which is specifically determined based on the power change and the time change. 5) Maximum adjustment step: indicates the maximum power change that the virtual power plant resources can adjust in a single adjustment operation, which is used to reflect the granularity and flexibility of resource adjustment. Its functions include: A) Fine adjustment: A smaller maximum adjustment step means that the resources can perform more fine power adjustment, which helps to more accurately meet the adjustment needs of the power grid. B) Response speed: A larger adjustment step can quickly change the output of the resources and improve the response speed, which is particularly important for rapidly changing power grid conditions. C) Operational flexibility: Different maximum adjustment steps affect the operational flexibility of the resources, and a smaller step usually means higher operational flexibility. Among them, the adjustment step represents the minimum power unit for a single adjustment of the virtual power plant resources.

[0059] Specifically, the server obtains the resource capacity and current load corresponding to the virtual power plant resources, and through the resource characteristic model, determines the upward margin and downward margin corresponding to the virtual power plant resources according to the load forecast results, resource capacity and current load corresponding to the virtual power plant resources, and further determines the maximum adjustable power corresponding to the virtual power plant resources based on the upward margin and downward margin corresponding to the virtual power plant resources.

[0060] Among them, the server specifically determines the power change and time change corresponding to the virtual power plant resources based on the load forecast results corresponding to the virtual power plant resources, and determines the response rate corresponding to the virtual power plant resources based on the power change and time change corresponding to the virtual power plant resources.

[0061] Furthermore, since external evaluation factors need to be considered when obtaining the resource evaluation results corresponding to the virtual power plant resources, it is also necessary to obtain the external evaluation indicators corresponding to the virtual power plant resources and the evaluation weights corresponding to each external evaluation indicator. Therefore, the server specifically obtains the indicator weights corresponding to each adjustable capacity indicator, and performs weighted fusion based on the adjustable capacity indicators corresponding to the virtual power plant resources, the indicator weights corresponding to each adjustable capacity indicator, the external evaluation indicators, and the evaluation weights corresponding to each external evaluation indicator to obtain the resource evaluation results corresponding to the virtual power plant resources.

[0062] Specifically, the external evaluation indicators include the cost of resources participating in demand response, resource reliability, user willingness, response speed, and environmental impact, while the adjustable capacity indicators include: the upward adjustment margin, downward adjustment margin, response rate, maximum adjustable power, and maximum adjustment step of virtual power plant resources. Specifically, the evaluation weights corresponding to the cost of resources participating in demand response, resource reliability, user willingness, response speed, and environmental impact are determined, and the indicator weights corresponding to the upward adjustment margin, downward adjustment margin, response rate, maximum adjustable power, and maximum adjustment step are determined. Therefore, according to the adjustable capacity indicators (specifically including the upward adjustment margin, downward adjustment margin, response rate, maximum adjustable power, and maximum adjustment step of virtual power plant resources), the indicator weights corresponding to the adjustable capacity indicators, the external evaluation indicators (specifically including the cost of resources participating in demand response, resource reliability, user willingness, response speed, and environmental impact), and the evaluation weights corresponding to the external evaluation indicators, weighted fusion is performed to obtain the resource evaluation results corresponding to the virtual power plant resources.

[0063] Step S210 , optimizing the configuration of each virtual power plant resource according to the resource evaluation result corresponding to each virtual power plant resource and the preset configuration requirements.

[0064] Specifically, an optimization configuration target is determined according to preset configuration requirements, such as an adjustable capacity indicator, including one or more of the upward margin, downward margin, response rate, maximum adjustable power, and maximum adjustment step of virtual power plant resources; and an external evaluation indicator, including one or more of the cost of resource participation in demand response, resource reliability, user willingness, response speed, and environmental impact. According to the resource evaluation results corresponding to each virtual power plant resource, each virtual power plant resource is sorted to obtain a virtual power plant resource sequence, so as to determine at least one target virtual power plant resource from the virtual power plant resource sequence based on the optimization configuration target, so that resource scheduling and optimization configuration can be performed on the at least one determined target virtual power plant resource.

[0065] Among them, the process of optimizing the allocation of resources for each virtual power plant usually involves clarifying configuration goals, collecting and analyzing resource and grid data, building optimization models, evaluating resource characteristics, formulating and simulating resource allocation strategies, implementing resource scheduling, real-time monitoring and performance evaluation, and continuous optimization based on feedback to ensure that resource allocation not only meets current needs but also has the flexibility to adapt to future changes, thereby improving the economic benefits and operating efficiency of the power system.

[0066] Furthermore, the process of optimizing the configuration of each virtual power plant resource includes:

[0067] 1) Clarify the optimization objectives, including: A) Define the objectives: Clarify the objectives of the optimization configuration, such as minimizing costs, maximizing benefits, and improving grid stability. B) Determine constraints: Identify and define the constraints that need to be considered in the optimization process, such as technical limitations of resources, market rules, user preferences, etc. 2) Data collection and analysis, including: A) Resource data: Collect performance data, historical response data, cost data, etc. of the selected resources. B) Grid data: Collect grid operation data, including load forecasts, grid stability indicators, etc. C) Market data: Analyze real-time prices, demand response signals, policy changes, etc. in the power market. 3) Establish an optimization model, including: A) Select an optimization algorithm: Select an appropriate optimization algorithm according to the nature of the problem, such as linear programming, integer programming, genetic algorithm, etc. B) Model construction: Construct a mathematical model, including objective functions and constraints, to reflect the optimization objectives and practical limitations. 4) Resource characteristic analysis, including: A) Adjustable capacity evaluation: Evaluate the adjustable capacity of each resource, including the margin for upward and downward adjustment. B) Response characteristic analysis: Analyze the response speed, response time and other characteristics of the resource. 5) Formulate configuration strategies, including: A) Resource allocation: According to the optimization model and resource characteristics, formulate resource allocation strategies to determine which resources participate in specific demand response or ancillary services. B) Dispatch plan: Formulate a detailed resource dispatch plan, including resource start-up time, adjustment amount, etc. 6) Simulation and optimization, including: A) Scenario simulation: Simulate different power grid operation scenarios to evaluate the effect of resource allocation strategies. B) Sensitivity analysis: Analyze the impact of key parameter changes on optimization results, such as electricity price fluctuations, load changes, etc. C) Adjustment strategy: Adjust resource allocation strategies based on simulation results and sensitivity analysis to improve optimization effects. 7) Implementation and monitoring, including: A) Resource dispatch implementation: Implement resource dispatch according to the optimization configuration strategy. B) Real-time monitoring: Real-time monitoring of resource operation status and power grid operation to ensure effective implementation of resource allocation strategies. 8) Performance evaluation, including: A) Effect evaluation: Evaluate the actual effect of resource allocation strategies, including cost savings, benefit improvement, and improved power grid stability. B) User satisfaction: Collect user feedback and evaluate user satisfaction with resource allocation strategies. 9) Feedback and adjustment, including: A) Collecting feedback: Collecting operational data and user feedback during resource allocation. B) Strategy adjustment: Adjusting resource allocation strategies based on feedback information to adapt to changing market conditions and user needs. 10) Continuous optimization, including: A) Regular evaluation: Regularly evaluate the effectiveness of resource allocation strategies and identify opportunities for improvement. B) Model update: Update optimization models and configuration strategies based on new data and market changes.

[0068] In the above-mentioned optimization configuration method based on virtual power plant resources, by obtaining different types of virtual power plant resources, the resource parameters of each virtual power plant resource, and the historical load data, external load data and user behavior data associated with each virtual power plant resource, it is possible to construct a resource characteristic model corresponding to the virtual power plant resources for each virtual power plant resource according to the resource parameters of the virtual power plant resources, and the historical load data, external load data and user behavior data associated with the virtual power plant resources. Furthermore, load forecasting is performed based on historical load data, external load data, and user behavior data associated with virtual power plant resources to obtain load forecasting results corresponding to virtual power plant resources, and based on the load forecasting results and resource characteristic models corresponding to the virtual power plant resources, adjustable capacity indicators corresponding to the virtual power plant resources are determined, and weighted fusion is performed based on the adjustable capacity indicators corresponding to the virtual power plant resources and the indicator weights corresponding to each adjustable capacity indicator to obtain resource evaluation results corresponding to the virtual power plant resources, so as to optimize the configuration of each virtual power plant resource based on the resource evaluation results corresponding to each virtual power plant resource and preset configuration requirements, so that various virtual power plant resources can be more effectively mined and utilized through precise resource characteristic analysis and adjustable capacity evaluation, so as to improve resource utilization and reduce energy consumption.

[0069] In an exemplary embodiment, Figure 3 As shown, the step of constructing a resource characteristic model corresponding to a virtual power plant resource, that is, for each virtual power plant resource, according to the resource parameters of the virtual power plant resource, and the historical load data, external load data and user behavior data associated with the virtual power plant resource, the step of constructing a resource characteristic model corresponding to the virtual power plant resource specifically includes the following steps S302 to S312. Among them:

[0070] Step S302: determining a resource prediction target corresponding to the virtual power plant resources according to the resource parameters of the virtual power plant resources.

[0071] Specifically, based on the resource parameters of the virtual power plant resources, such as the power range, response time, and adjustable capacity corresponding to the air-conditioning load, the energy storage capacity, charging and discharging efficiency, cycle life, and response speed corresponding to the energy storage equipment, the charging power, charging efficiency and usage mode corresponding to the charging pile, the installed capacity, efficiency and sunshine conditions corresponding to the distributed photovoltaics, and the load size, flexibility and scheduling capability corresponding to the controllable load, the resource prediction targets corresponding to the virtual power plant resources are determined.

[0072] Among them, the resource prediction objectives specifically include: one or more of resource reduction potential, cost-effectiveness ratio and response speed. Specifically, based on the resource parameters of the virtual power plant resources, the model needs to clarify the problems that need to be solved, such as predicting the resource reduction potential, response speed or cost-effectiveness ratio, and determining the type and amount of data required to achieve these goals.

[0073] Step S304, performing data cleaning and feature extraction on the historical load data, external load data and user behavior data associated with the virtual power plant resources to obtain resource load features corresponding to the virtual power plant resources.

[0074] Specifically, after obtaining the historical load data, external load data and user behavior data associated with the virtual power plant resources, data cleaning is performed on the historical load data, external load data and user behavior data associated with the virtual power plant resources, such as processing missing values, outliers and noise data to ensure data quality, and feature extraction is performed on the historical load data, external load data and user behavior data after data cleaning to obtain resource load characteristics corresponding to the virtual power plant resources, including time characteristics (hours, weeks, seasons), weather characteristics (temperature, humidity), and user behavior characteristics (usage patterns, response history), etc.

[0075] Step S306: construct a model training set and a model test set according to the load characteristics of each resource.

[0076] Specifically, each resource load feature is divided into training samples or test samples, so that a model training set and a model test set can be constructed based on each resource load feature. The model training set is used for model training, while the model test set is used for model evaluation.

[0077] After obtaining the load characteristics of each resource, it is necessary to select the original model, that is, to select a suitable model according to the nature of the problem. The original models specifically include: 1) Linear regression model, which is suitable for predicting problems that are linearly related to the input features. 2) Decision trees and random forests, which are suitable for classification and regression problems and can handle nonlinear relationships. 3) Neural networks, which are suitable for complex nonlinear problems and have strong feature learning capabilities. 4) Time series models, which are suitable for predicting time series data, such as load forecasting.

[0078] Step S308: Perform model training on the initial machine learning model according to the model training set to obtain a trained resource characteristic model.

[0079] Specifically, the initial machine learning model is trained according to the model training set. Specifically, the model parameters, such as the learning rate, the depth of the tree, the number of layers of the neural network, etc., can be adjusted through methods such as cross-validation to optimize the model performance. That is, the model is trained by using the model training set so that the model can learn the patterns and relationships in the data, thereby obtaining a trained resource characteristic model.

[0080] Step S310: perform model performance evaluation on the trained resource characteristic model according to the model test set to obtain a performance evaluation result.

[0081] Specifically, the model performance of the trained resource feature model is evaluated based on the model test set. Specifically, the performance of the model can be evaluated by setting performance indicators, such as mean square error (MSE), mean absolute error (MAE), accuracy, and recall. Performance evaluation results are obtained to ensure the generalization ability of the model. At the same time, the errors of model prediction are analyzed to identify the limiting factors of model performance.

[0082] Step S312: If the prediction result obtained by the trained resource characteristic model for the resource prediction target is determined based on the performance evaluation result and the model training end condition is met, the trained resource characteristic model is determined as the resource characteristic model corresponding to the virtual power plant resources.

[0083] Specifically, if, based on the performance evaluation results, it is determined that the prediction results obtained by the trained resource characteristic model for the resource prediction target meet the model training end conditions, such as the model training loss determined based on the prediction results and the actual results, when the training loss threshold is reached, the trained resource characteristic model will be determined as the resource characteristic model corresponding to the virtual power plant resources.

[0084] In an exemplary embodiment, after obtaining the resource characteristic model, the model can be further optimized, including: 1) feature selection, that is, further optimizing the features, including adding new features or deleting irrelevant features. 2) model fusion, that is, using ensemble learning methods such as random forest, gradient boosting machine (GBM), and neural network integration to improve the stability and accuracy of the model. 3) hyperparameter adjustment: continue to adjust the hyperparameters of the model to further improve the model performance.

[0085] Among them, for the trained resource characteristic model, it also includes: 1) Model deployment, that is, by deploying the trained model to the production environment, it can be used for real-time or regular resource characteristic prediction. 2) Performance monitoring of the deployed resource characteristic model, that is, by continuously monitoring the performance of the model, ensuring that the model maintains accuracy and reliability in actual applications, and regularly updating the model based on new data and feedback to adapt to environmental changes and data drift.

[0086] In this embodiment, the resource prediction target corresponding to the virtual power plant resources is determined according to the resource parameters of the virtual power plant resources, and the historical load data, external load data and user behavior data associated with the virtual power plant resources are cleaned and feature extracted to obtain the resource load characteristics corresponding to the virtual power plant resources, so as to construct a model training set and a model test set according to each resource load characteristic. Further, according to the model training set, the initial machine learning model is trained to obtain a trained resource characteristic model, and according to the model test set, the model performance of the trained resource characteristic model is evaluated to obtain a performance evaluation result. If, according to the performance evaluation result, it is determined that the prediction result obtained by the trained resource characteristic model for the resource prediction target meets the model training end condition, the trained resource characteristic model is determined as the resource characteristic model corresponding to the virtual power plant resources, so that accurate resource characteristic analysis can be achieved based on the resource characteristic model, so that the adjustable capacity index corresponding to the virtual power plant resources can be accurately determined based on the load prediction result and the resource characteristic model in the future, so as to further improve the adjustable capacity of the resources and the flexibility of the power grid.

[0087] In an exemplary embodiment, Figure 4 As shown, the step of determining the adjustable capacity index corresponding to the virtual power plant resources, that is, the step of determining the adjustable capacity index corresponding to the virtual power plant resources according to the load forecast results and resource characteristic model corresponding to the virtual power plant resources, specifically includes the following steps S402 to S406. Among them:

[0088] Step S402, obtain the resource capacity and current load corresponding to the virtual power plant resources, and determine the upward adjustment margin and downward adjustment margin corresponding to the virtual power plant resources through the resource characteristic model according to the load forecast results, resource capacity and current load corresponding to the virtual power plant resources.

[0089] Among them, the adjustable capacity indicators corresponding to the virtual power plant resources specifically include: the upward adjustment margin, downward adjustment margin, response rate, maximum adjustable power, and maximum adjustment step of the virtual power plant resources.

[0090] Specifically, by obtaining the resource capacity and current load corresponding to the virtual power plant resources, the resource characteristic model is used to calculate the upward margin and downward margin based on the load forecast results, resource capacity and current load corresponding to the virtual power plant resources.

[0091] For example, the upward adjustment margin UR corresponding to the virtual power plant resources may be determined by the following formula (1):

[0092] UR = C - (Pr - Pc); Formula (1)

[0093] Among them, UR represents the upward adjustment margin, C represents the resource capacity corresponding to the virtual power plant resources, Pr represents the load forecast result corresponding to the virtual power plant resources, and Pc represents the current load corresponding to the virtual power plant resources.

[0094] Similarly, the downward adjustment margin DR corresponding to the virtual power plant resources can be determined by the following formula (2):

[0095] DR = Pc - Pr; Formula (2)

[0096] Among them, DR represents the downward adjustment margin, Pr represents the load forecast result corresponding to the virtual power plant resources, and Pc represents the current load corresponding to the virtual power plant resources.

[0097] Step S404: determining the maximum adjustable power corresponding to the virtual power plant resources according to the upward adjustment margin and the downward adjustment margin corresponding to the virtual power plant resources.

[0098] Specifically, after determining the upward margin and downward margin corresponding to the virtual power plant resources based on the load forecast results, resource capacity and current load corresponding to the virtual power plant resources, the maximum adjustable power corresponding to the virtual power plant resources is further determined based on the upward margin and downward margin corresponding to the virtual power plant resources. Specifically, a smaller value is determined from the upward margin and downward margin corresponding to the virtual power plant resources as the maximum adjustable power corresponding to the virtual power plant resources.

[0099] Exemplarily, the following formula (3) is used to determine the maximum adjustable power MP corresponding to the virtual power plant resources:

[0100] MP= min(UR, DR); formula (2)

[0101] Among them, MP represents the maximum adjustable power, UR represents the upward adjustment margin, DR represents the downward adjustment margin, and min (UR, DR) means taking the smaller value of the upward adjustment margin and the downward adjustment margin.

[0102] Step S406, based on the load forecast results corresponding to the virtual power plant resources, determine the power change and time change corresponding to the virtual power plant resources, and based on the power change and time change corresponding to the virtual power plant resources, determine the response rate corresponding to the virtual power plant resources.

[0103] Specifically, according to the load forecast results corresponding to the virtual power plant resources, after determining the power change and time change corresponding to the virtual power plant resources, the ratio between the power change and the time change is further calculated to obtain the response rate corresponding to the virtual power plant resources.

[0104] For example, the response rate RR corresponding to the virtual power plant resources is determined by using the following formula (4):

[0105] ;Formula (4)

[0106] Among them, RR represents the response rate corresponding to the virtual power plant resources, represents the power change corresponding to the virtual power plant resources, Indicates the time variation corresponding to the virtual power plant resources.

[0107] In an exemplary embodiment, the maximum adjustment step refers to the maximum power change that the virtual power plant resource can adjust in a single adjustment operation. A smaller maximum adjustment step means that the resource can perform more refined power adjustment, which helps to more accurately meet the regulation needs of the power grid, while a larger adjustment step can quickly change the output of the resource and improve the response speed. Specifically, the maximum adjustment step corresponding to the virtual power plant resource can be determined based on the physical characteristics of the virtual power plant resource. Exemplarily, the minimum adjustment unit of the air conditioner may be 0.5°C, that is, when the virtual power plant resource is an air conditioning load, the corresponding maximum adjustment step is 0.5°C.

[0108] In this embodiment, by obtaining the resource capacity and current load corresponding to the virtual power plant resources, the upward adjustment margin and downward adjustment margin corresponding to the virtual power plant resources are determined according to the load forecast results, resource capacity and current load corresponding to the virtual power plant resources through the resource characteristic model, and the maximum adjustable power corresponding to the virtual power plant resources is determined according to the upward adjustment margin and downward adjustment margin corresponding to the virtual power plant resources. Further, according to the load forecast results corresponding to the virtual power plant resources, the power change and time change corresponding to the virtual power plant resources are determined, and according to the power change and time change corresponding to the virtual power plant resources, the response rate corresponding to the virtual power plant resources is determined, thereby achieving.

[0109] In an exemplary embodiment, Figure 5 As shown, the step of optimizing the configuration of each virtual power plant resource, that is, the step of optimizing the configuration of each virtual power plant resource according to the resource evaluation results corresponding to each virtual power plant resource and the preset configuration requirements, specifically includes the following steps S502 to S506. Among them:

[0110] Step S502: determining an optimized configuration target according to preset configuration requirements.

[0111] Specifically, preset configuration requirements are obtained, including project requirements or market conditions, where project requirements may include reducing load during peak hours, providing frequency regulation services, etc., while market conditions include the current status of the electricity market, such as electricity prices, demand forecasts, policies and regulations, etc., and the optimal configuration target is determined based on the preset configuration requirements.

[0112] Specifically, the optimization configuration target can be determined according to the preset configuration requirements. For example, according to project requirements or market conditions, the adjustable capacity indicators can be determined, including one or more of the upward margin, downward margin, response rate, maximum adjustable power, and maximum adjustment step of the virtual power plant resources as the optimization configuration target. For example, external evaluation indicators can be determined, including one or more of the cost of resource participation in demand response, resource reliability, user willingness, response speed, and environmental impact as the optimization configuration target.

[0113] Step S502 , sorting the virtual power plant resources according to the resource evaluation results corresponding to the virtual power plant resources to obtain a virtual power plant resource sequence.

[0114] Specifically, based on the resource evaluation results corresponding to each virtual power plant resource, such as the specific score value corresponding to each virtual power plant resource, and according to the size of the score value, each virtual power plant resource is sorted, for example, from large to small score values ​​are used to sort each virtual power plant resource, to obtain a virtual power plant resource sequence, that is, a plurality of different types of virtual power plant resources in the virtual power plant resource sequence arranged from large to small score values.

[0115] Step S506, according to the optimization configuration target, at least one target virtual power plant resource is determined from the virtual power plant resource sequence, and resource scheduling and optimization configuration are performed on the determined at least one target virtual power plant resource.

[0116] Specifically, according to the optimization configuration target, at least one target virtual power plant resource is determined from the virtual power plant resource sequence, such as air-conditioning load, energy storage equipment, charging piles, distributed photovoltaic and controllable load virtual power plant resources, and at least one target virtual power plant resource, such as air-conditioning load, is determined as the target virtual power plant resource.

[0117] Furthermore, the process of optimizing the allocation of target virtual power plant resources includes: clarifying the allocation goals, collecting and analyzing resource and grid data, building optimization models, evaluating resource characteristics, formulating and simulating resource allocation strategies, implementing resource scheduling, real-time monitoring and performance evaluation, and continuous optimization based on feedback to ensure that resource allocation not only meets current needs but also has the flexibility to adapt to future changes, thereby improving the economic benefits and operating efficiency of the power system.

[0118] In an exemplary embodiment, the process of screening out the virtual power plant resources (i.e., target virtual power plant resources) that are most suitable for participating in specific demand response or ancillary services based on preset configuration requirements, such as project requirements or market conditions, includes: first, clarifying the goals and market conditions of demand response, and determining the criteria for resource selection, such as performance, cost-effectiveness, and reliability. Secondly, collecting and analyzing resource data, including historical performance and user preferences, establishing a resource library, and applying a comprehensive scoring system to score and rank resources. Third, through preliminary screening and in-depth analysis, simulate the performance of resources in different scenarios, and optimize the resource combination to maximize benefits and reliability. Finally, formulate a resource scheduling plan, implement resource scheduling, and make adjustments based on real-time monitoring and performance feedback to ensure the effectiveness and adaptability of resource configuration. The following is the specific screening process:

[0119] 1) Clarify project requirements and market conditions, including: A) Define the goals of demand response: Determine the specific goals of demand response, such as reducing load during peak hours, providing frequency regulation services, etc. B) Market conditions analysis: Analyze the current situation of the electricity market, including electricity prices, demand forecasts, policies and regulations, etc. 2) Determine the criteria for resource selection, including: A) Performance indicators: Determine the performance indicators that resources must meet, such as minimum adjustable capacity, response time, etc. B) Cost-effectiveness: Evaluate the cost-effectiveness of resource participation in demand response, including direct costs and potential benefits. C) Reliability requirements: Set standards for resource reliability to ensure that resources can provide the required services at critical moments. 3) Collect resource data, including: A) Resource characteristic data: Collect historical performance data, adjustable capacity, response history, etc. of resources. B) User data: Understand users' electricity usage habits, preferences, acceptable incentive mechanisms, etc. 4) Establish a resource library, including: A) Resource classification: Classify resources by type (such as industrial load, commercial load, residential load, etc.) and characteristics. B) Resource registration: Create a resource library to record detailed information and performance indicators of each resource. 5) Resource evaluation and scoring, including: A) Comprehensive scoring: Scoring resources according to the previously established scoring system. B) Resource ranking: Ranking resources according to the scoring results, giving priority to resources with high scores. 6) Resource screening, including: A) Preliminary screening: Screening out resources that meet basic requirements based on project requirements and resource scores. B) In-depth analysis: Conducting a more in-depth analysis of the preliminarily screened resources, considering their performance under specific conditions. 7) Simulation and optimization, including: A) Scenario simulation: Simulating the performance of resources under different demand response scenarios and evaluating their adaptability. B) Resource combination optimization: Considering the combination of different resources to maximize cost-effectiveness and risk diversification. 8) Formulating resource scheduling plans, including: A) Scheduling strategies: Formulating resource scheduling strategies to clarify the scheduling priorities and operation procedures of resources under different circumstances. B) Communication and control: Ensuring that resources can receive scheduling instructions and have the necessary communication and control capabilities. 9) Implementation and monitoring, including: A) Resource scheduling implementation: Implementing resource scheduling according to the scheduling plan. B) Performance monitoring: Real-time monitoring of resource performance to ensure that it meets project requirements. 10) Feedback and adjustment, including: A) Performance feedback: Collect performance data and user feedback of resources in actual operation. B) Strategy adjustment: Adjust resource selection criteria, scoring system and scheduling strategy based on feedback. 11) Continuous improvement, including: A) Regular evaluation: Regularly evaluate the effect of resource selection and scheduling, and identify opportunities for improvement. B) Update resource library: Update resource library and related strategies as market conditions and project requirements change.

[0120] In this embodiment, an optimization configuration target is determined according to preset configuration requirements, and each virtual power plant resource is sorted according to a resource evaluation result corresponding to each virtual power plant resource to obtain a virtual power plant resource sequence, so that at least one target virtual power plant resource can be determined from the virtual power plant resource sequence according to the optimization configuration target, so that resource scheduling and optimization configuration can be performed on the at least one target virtual power plant resource determined, thereby achieving the reduction of unnecessary energy waste and the reduction of the operating cost of the power system through optimizing resource allocation, and improving energy utilization efficiency and reducing energy consumption through accurate load forecasting and resource scheduling.

[0121] In an exemplary embodiment, Figure 6 As shown, a method for optimizing configuration based on virtual power plant resources is provided, and the method is applied to the server 104 in FIG. 1 as an example for explanation, and specifically includes the following steps S601 to S614. Among them:

[0122] Step S601, obtaining different types of virtual power plant resources and resource parameters of each virtual power plant resource, and obtaining historical load data, external load data and user behavior data associated with each virtual power plant resource.

[0123] Step S602 : for each virtual power plant resource, determine a resource prediction target corresponding to the virtual power plant resource according to the resource parameters of the virtual power plant resource.

[0124] Step S603, performing data cleaning and feature extraction on the historical load data, external load data and user behavior data associated with the virtual power plant resources to obtain resource load features corresponding to the virtual power plant resources.

[0125] Step S604: construct a model training set and a model test set according to the characteristics of each resource load, perform model training on the initial machine learning model according to the model training set to obtain a trained resource characteristic model, and perform model performance evaluation on the trained resource characteristic model according to the model test set to obtain a performance evaluation result.

[0126] Step S605, if the prediction result obtained by the trained resource characteristic model for the resource prediction target is determined based on the performance evaluation result, and the model training end condition is met, the trained resource characteristic model is determined as the resource characteristic model corresponding to the virtual power plant resources.

[0127] Step S606, for each virtual power plant resource, perform power consumption pattern analysis and load trend analysis on the historical load data associated with the virtual power plant resource to obtain the historical power consumption pattern and load change trend corresponding to the virtual power plant resource.

[0128] Step S607, performing external demand analysis and personalized power consumption analysis on the external load data and user behavior data associated with the virtual power plant resources, respectively, to obtain external demand analysis results and personalized power consumption analysis results.

[0129] Step S608, performing load forecasting according to the historical power consumption patterns, load change trends, external demand analysis results and personalized power consumption analysis results corresponding to the virtual power plant resources, and obtaining load forecasting results corresponding to the virtual power plant resources.

[0130] Step S609, obtain the resource capacity and current load corresponding to the virtual power plant resources, and determine the upward adjustment margin and downward adjustment margin corresponding to the virtual power plant resources through the resource characteristic model according to the load forecast results, resource capacity and current load corresponding to the virtual power plant resources.

[0131] Step S610: determining the maximum adjustable power corresponding to the virtual power plant resources according to the upward adjustment margin and the downward adjustment margin corresponding to the virtual power plant resources.

[0132] Step S611, based on the load forecast results corresponding to the virtual power plant resources, determine the power change and time change corresponding to the virtual power plant resources, and based on the power change and time change corresponding to the virtual power plant resources, determine the response rate corresponding to the virtual power plant resources.

[0133] Step S612, obtain the external evaluation indicators corresponding to the virtual power plant resources and the evaluation weights corresponding to each external evaluation indicator, and perform weighted fusion according to the adjustable capacity indicators corresponding to the virtual power plant resources, the indicator weights corresponding to each adjustable capacity indicator, the external evaluation indicators, and the evaluation weights corresponding to each external evaluation indicator to obtain the resource evaluation results corresponding to the virtual power plant resources.

[0134] Step S613: sorting the virtual power plant resources according to the resource evaluation results corresponding to the virtual power plant resources to obtain a virtual power plant resource sequence.

[0135] Step S614, determining the optimization configuration target according to the preset configuration requirements, and determining at least one target virtual power plant resource from the virtual power plant resource sequence according to the optimization configuration target, so as to perform resource scheduling and optimization configuration for the determined at least one target virtual power plant resource.

[0136] In an exemplary embodiment, after performing resource scheduling and optimal configuration on at least one target virtual power plant resource, the method further includes:

[0137] 1) Decision support: Provide a graphical display interface to intuitively display the statistical analysis of resources, load forecast results, adjustable capacity assessment results and optimization configuration plans, provide data-driven decision support, and improve the scientificity and accuracy of decision-making. 2) Execution and monitoring: According to the optimization configuration plan, execute resource scheduling and control instructions, monitor the resource operation status and response effect in real time, so as to achieve accurate load forecasting and resource scheduling, improve energy utilization efficiency, and reduce energy consumption. 3) Feedback and adjustment: Collect feedback and actual effect data during the resource participation process, and continuously optimize and adjust the resource evaluation model and configuration strategy to reduce unnecessary energy waste and reduce the operating cost of the power system.

[0138] In the above-mentioned optimization configuration method based on virtual power plant resources, by obtaining different types of virtual power plant resources, the resource parameters of each virtual power plant resource, and the historical load data, external load data and user behavior data associated with each virtual power plant resource, it is possible to construct a resource characteristic model corresponding to the virtual power plant resources for each virtual power plant resource according to the resource parameters of the virtual power plant resources, and the historical load data, external load data and user behavior data associated with the virtual power plant resources. Furthermore, load forecasting is performed based on historical load data, external load data, and user behavior data associated with virtual power plant resources to obtain load forecasting results corresponding to virtual power plant resources, and based on the load forecasting results and resource characteristic models corresponding to the virtual power plant resources, adjustable capacity indicators corresponding to the virtual power plant resources are determined, and weighted fusion is performed based on the adjustable capacity indicators corresponding to the virtual power plant resources and the indicator weights corresponding to each adjustable capacity indicator to obtain resource evaluation results corresponding to the virtual power plant resources, so as to optimize the configuration of each virtual power plant resource based on the resource evaluation results corresponding to each virtual power plant resource and preset configuration requirements, so that various virtual power plant resources can be more effectively mined and utilized through precise resource characteristic analysis and adjustable capacity evaluation, so as to improve resource utilization and reduce energy consumption.

[0139] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0140] Based on the same inventive concept, the embodiment of the present application also provides an optimization configuration device based on virtual power plant resources for implementing the above-mentioned optimization configuration method based on virtual power plant resources. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the optimization configuration device based on virtual power plant resources provided below can refer to the limitations of the optimization configuration method based on virtual power plant resources in the above text, and will not be repeated here.

[0141] In an exemplary embodiment, Figure 7 As shown, a virtual power plant resource optimization configuration device is provided, comprising: a virtual power plant resource acquisition module 702, a resource characteristic model construction module 704, a load prediction module 706, a resource evaluation result acquisition module 708 and a resource optimization configuration module 710, wherein:

[0142] A virtual power plant resource acquisition module 702 is used to acquire different types of virtual power plant resources and resource parameters of each virtual power plant resource, and to acquire historical load data, external load data, and user behavior data associated with each virtual power plant resource;

[0143] A resource characteristic model building module 704 is used to build a resource characteristic model corresponding to each virtual power plant resource according to resource parameters of the virtual power plant resource and historical load data, external load data and user behavior data associated with the virtual power plant resource;

[0144] The load forecasting module 706 is used to perform load forecasting based on historical load data, external load data, and user behavior data associated with the virtual power plant resources, and obtain load forecasting results corresponding to the virtual power plant resources;

[0145] The resource evaluation result obtaining module 708 is used to determine the adjustable capacity index corresponding to the virtual power plant resources according to the load forecasting results and resource characteristic models corresponding to the virtual power plant resources, and to perform weighted fusion according to the adjustable capacity index corresponding to the virtual power plant resources and the index weights corresponding to each adjustable capacity index, so as to obtain the resource evaluation results corresponding to the virtual power plant resources;

[0146] The resource optimization configuration module 710 is used to optimize the configuration of each virtual power plant resource according to the resource evaluation results corresponding to each virtual power plant resource and the preset configuration requirements.

[0147] In the above-mentioned optimization configuration device based on virtual power plant resources, by acquiring different types of virtual power plant resources, the resource parameters of each virtual power plant resource, and the historical load data, external load data and user behavior data associated with each virtual power plant resource, it is possible to construct a resource characteristic model corresponding to the virtual power plant resources for each virtual power plant resource according to the resource parameters of the virtual power plant resources, and the historical load data, external load data and user behavior data associated with the virtual power plant resources. Furthermore, load forecasting is performed based on historical load data, external load data, and user behavior data associated with virtual power plant resources to obtain load forecasting results corresponding to virtual power plant resources, and based on the load forecasting results and resource characteristic models corresponding to the virtual power plant resources, adjustable capacity indicators corresponding to the virtual power plant resources are determined, and weighted fusion is performed based on the adjustable capacity indicators corresponding to the virtual power plant resources and the indicator weights corresponding to each adjustable capacity indicator to obtain resource evaluation results corresponding to the virtual power plant resources, so as to optimize the configuration of each virtual power plant resource based on the resource evaluation results corresponding to each virtual power plant resource and preset configuration requirements, so that various virtual power plant resources can be more effectively mined and utilized through precise resource characteristic analysis and adjustable capacity evaluation, so as to improve resource utilization and reduce energy consumption.

[0148] In an exemplary embodiment, the resource characteristic model construction module is also used to: determine the resource prediction target corresponding to the virtual power plant resources based on the resource parameters of the virtual power plant resources; perform data cleaning and feature extraction on the historical load data, external load data and user behavior data associated with the virtual power plant resources to obtain the resource load characteristics corresponding to the virtual power plant resources; construct a model training set and a model test set according to each resource load characteristic; perform model training on the initial machine learning model according to the model training set to obtain a trained resource characteristic model; perform model performance evaluation on the trained resource characteristic model according to the model test set to obtain a performance evaluation result; if, according to the performance evaluation result, it is determined that the prediction result obtained by the trained resource characteristic model for the resource prediction target meets the model training end condition, the trained resource characteristic model is determined as the resource characteristic model corresponding to the virtual power plant resources.

[0149] In an exemplary embodiment, the load forecasting module is also used to: for each virtual power plant resource, perform power consumption pattern analysis and load trend analysis on the historical load data associated with the virtual power plant resource, and obtain the historical power consumption pattern and load change trend corresponding to the virtual power plant resource; perform external demand analysis and personalized power consumption analysis on the external load data and user behavior data associated with the virtual power plant resources, and obtain external demand analysis results and personalized power consumption analysis results; perform load forecasting based on the historical power consumption pattern, load change trend, external demand analysis results and personalized power consumption analysis results corresponding to the virtual power plant resource, and obtain the load forecasting result corresponding to the virtual power plant resource.

[0150] In an exemplary embodiment, the resource assessment result acquisition module is also used to: obtain the resource capacity and current load corresponding to the virtual power plant resources, and determine the upward adjustment margin and downward adjustment margin corresponding to the virtual power plant resources through the resource characteristic model according to the load forecast results, resource capacity and current load corresponding to the virtual power plant resources; determine the maximum adjustable power corresponding to the virtual power plant resources according to the upward adjustment margin and downward adjustment margin corresponding to the virtual power plant resources; determine the power change and time change corresponding to the virtual power plant resources according to the load forecast results corresponding to the virtual power plant resources, and determine the response rate corresponding to the virtual power plant resources according to the power change and time change corresponding to the virtual power plant resources.

[0151] In an exemplary embodiment, the resource evaluation result acquisition module is also used to: obtain external evaluation indicators corresponding to the virtual power plant resources, and evaluation weights corresponding to each external evaluation indicator; perform weighted fusion according to the adjustable capacity indicators corresponding to the virtual power plant resources, the indicator weights corresponding to each adjustable capacity indicator, the external evaluation indicators, and the evaluation weights corresponding to each external evaluation indicator to obtain resource evaluation results corresponding to the virtual power plant resources.

[0152] In an exemplary embodiment, the resource optimization configuration module is also used to: determine the optimization configuration target according to preset configuration requirements; sort each virtual power plant resource according to the resource evaluation results corresponding to each virtual power plant resource to obtain a virtual power plant resource sequence; determine at least one target virtual power plant resource from the virtual power plant resource sequence according to the optimization configuration target, and perform resource scheduling and optimization configuration for the at least one target virtual power plant resource determined.

[0153] Each module in the above-mentioned virtual power plant resource optimization configuration device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0154] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store different types of virtual power plant resources, resource parameters of each virtual power plant resource, historical load data associated with each virtual power plant resource, external load data and user behavior data, resource characteristic models, load forecasting results, adjustable capacity indicators, indicator weights, resource evaluation results, and preset configuration requirements and other data. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an optimization configuration method based on virtual power plant resources is implemented.

[0155] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0158] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0160] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0161] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0162] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for optimizing the configuration of virtual power plant resources, characterized in that: The method comprises: Acquire different types of virtual power plant resources and resource parameters of each of the virtual power plant resources, and acquire historical load data, external load data, and user behavior data associated with each of the virtual power plant resources; For each of the virtual power plant resources, construct a resource characteristic model corresponding to the virtual power plant resource according to resource parameters of the virtual power plant resource, and historical load data, external load data, and user behavior data associated with the virtual power plant resource; Perform load forecasting based on historical load data, external load data, and user behavior data associated with the virtual power plant resources to obtain load forecasting results corresponding to the virtual power plant resources; Determine the adjustable capacity index corresponding to the virtual power plant resource according to the load forecast result corresponding to the virtual power plant resource and the resource characteristic model, and perform weighted fusion according to the adjustable capacity index corresponding to the virtual power plant resource and the index weight corresponding to each of the adjustable capacity indicators to obtain a resource evaluation result corresponding to the virtual power plant resource; According to the resource evaluation results corresponding to each of the virtual power plant resources and the preset configuration requirements, each of the virtual power plant resources is optimally configured.

2. The method according to claim 1, characterized in that: For each of the virtual power plant resources, a resource characteristic model corresponding to the virtual power plant resource is constructed according to the resource parameters of the virtual power plant resource, and the historical load data, external load data and user behavior data associated with the virtual power plant resource, including: Determining a resource prediction target corresponding to the virtual power plant resources according to resource parameters of the virtual power plant resources; Performing data cleaning and feature extraction on historical load data, external load data, and user behavior data associated with the virtual power plant resources to obtain resource load features corresponding to the virtual power plant resources; Constructing a model training set and a model test set according to the resource load characteristics; According to the model training set, the initial machine learning model is trained to obtain a trained resource characteristic model; According to the model test set, performing model performance evaluation on the trained resource characteristic model to obtain a performance evaluation result; If, based on the performance evaluation results, the prediction results obtained by the trained resource characteristic model for the resource prediction target are determined, and when the model training end conditions are met, the trained resource characteristic model is determined as the resource characteristic model corresponding to the virtual power plant resources.

3. The method according to claim 1, characterized in that The step of performing load forecasting according to historical load data, external load data, and user behavior data associated with the virtual power plant resources to obtain a load forecasting result corresponding to the virtual power plant resources includes: For each of the virtual power plant resources, perform power consumption pattern analysis and load trend analysis on the historical load data associated with the virtual power plant resource to obtain the historical power consumption pattern and load change trend corresponding to the virtual power plant resource; Performing external demand analysis and personalized power consumption analysis on the external load data and user behavior data associated with the virtual power plant resources, respectively, to obtain external demand analysis results and personalized power consumption analysis results; Load forecasting is performed based on historical power consumption patterns, load change trends, external demand analysis results and personalized power consumption analysis results corresponding to the virtual power plant resources to obtain load forecasting results corresponding to the virtual power plant resources.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining the adjustable capacity index corresponding to the virtual power plant resources according to the load forecast result corresponding to the virtual power plant resources and the resource characteristic model includes: Obtaining the resource capacity and current load corresponding to the virtual power plant resources, and determining the upward adjustment margin and downward adjustment margin corresponding to the virtual power plant resources according to the load forecast result, resource capacity and current load corresponding to the virtual power plant resources through the resource characteristic model; Determining a maximum adjustable power corresponding to the virtual power plant resources according to an upward adjustment margin and a downward adjustment margin corresponding to the virtual power plant resources; According to the load forecast results corresponding to the virtual power plant resources, the power change and time change corresponding to the virtual power plant resources are determined, and according to the power change and time change corresponding to the virtual power plant resources, the response rate corresponding to the virtual power plant resources is determined.

5. The method according to any one of claims 1 to 3, characterized in that: The step of performing weighted fusion according to the adjustable capacity index corresponding to the virtual power plant resources and the index weight corresponding to each of the adjustable capacity indexes to obtain a resource evaluation result corresponding to the virtual power plant resources includes: Acquire external evaluation indicators corresponding to the virtual power plant resources and evaluation weights corresponding to each of the external evaluation indicators; According to the adjustable capacity indicators corresponding to the virtual power plant resources, the indicator weights corresponding to each of the adjustable capacity indicators, the external evaluation indicators, and the evaluation weights corresponding to each of the external evaluation indicators, weighted fusion is performed to obtain resource evaluation results corresponding to the virtual power plant resources.

6. The method according to any one of claims 1 to 3, characterized in that: The optimizing configuration of each of the virtual power plant resources according to the resource evaluation results corresponding to each of the virtual power plant resources and the preset configuration requirements includes: Determine an optimization configuration target according to the preset configuration requirements; According to the resource evaluation results corresponding to the virtual power plant resources, the virtual power plant resources are sorted to obtain a virtual power plant resource sequence; According to the optimization configuration target, at least one target virtual power plant resource is determined from the virtual power plant resource sequence, and resource scheduling and optimization configuration are performed on the determined at least one target virtual power plant resource.

7. An optimization configuration device based on virtual power plant resources, characterized in that: The device comprises: A virtual power plant resource acquisition module, used to acquire different types of virtual power plant resources and resource parameters of each of the virtual power plant resources, and to acquire historical load data, external load data and user behavior data associated with each of the virtual power plant resources; A resource characteristic model building module, for building a resource characteristic model corresponding to each virtual power plant resource according to resource parameters of the virtual power plant resource, and historical load data, external load data and user behavior data associated with the virtual power plant resource; A load forecasting module, configured to perform load forecasting based on historical load data, external load data, and user behavior data associated with the virtual power plant resources, and obtain load forecasting results corresponding to the virtual power plant resources; A resource evaluation result obtaining module, used to determine the adjustable capacity index corresponding to the virtual power plant resource according to the load forecast result corresponding to the virtual power plant resource and the resource characteristic model, and to perform weighted fusion according to the adjustable capacity index corresponding to the virtual power plant resource and the index weight corresponding to each of the adjustable capacity indexes, so as to obtain the resource evaluation result corresponding to the virtual power plant resource; The resource optimization configuration module is used to optimize the configuration of each virtual power plant resource according to the resource evaluation results corresponding to each virtual power plant resource and the preset configuration requirements.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images