A method and system for optimizing the allocation of virtual power plant resources

Abstract

The present invention relates to the technical field of resource allocation optimization, and particularly to a method and system for optimizing the resource allocation of a virtual power plant. The method includes the following steps: obtaining the energy load storage resource data corresponding to each power generation unit in the virtual power plant, and performing power generation power prediction analysis and charge and discharge state analysis of energy storage devices for each power generation unit in the virtual power plant, so as to obtain the energy power generation power corresponding to each power generation unit and the charge and discharge operation state data of the energy storage devices; performing resource operation load demand prediction analysis on the corresponding power generation units to obtain the predicted amounts of resource operation load demands corresponding to each power generation unit; performing resource allocation optimization target analysis on each power generation unit in the virtual power plant to obtain the resource allocation optimization target and resource optimization allocation processing of the power generation units in the virtual power plant, so as to generate an optimal resource allocation scheme for the power generation units in the virtual power plant. The present invention can achieve efficient optimization of the resources of each power generation unit in the virtual power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of resource allocation optimization, and particularly to a method and system for optimizing the resource allocation of a virtual power plant. Background Art

[0002] As an emerging power management model, the Virtual Power Plant (VPP) is gradually becoming an important means to achieve smart grids and sustainable energy utilization. The virtual power plant optimizes the scheduling and allocation of these resources by integrating various distributed energy resources, such as solar energy, wind energy, energy storage systems, and controllable loads, to improve the overall efficiency and reliability of the power system. At the same time, with the development of big data and artificial intelligence technologies, using intelligent algorithms to optimize the allocation of resources has become a trend. However, due to the volatility and uncertainty of renewable energy, the virtual power plant must consider various dynamic factors such as weather changes and load demands during resource scheduling. However, most of the existing virtual power plant resource optimization methods lack intelligence and mainly rely on manual scheduling and empirical judgment, making it difficult to adapt to changes in market demand and resource availability in real time, resulting in low efficiency of power plant resource allocation. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for optimizing the resource allocation of a virtual power plant to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for optimizing the resource allocation of a virtual power plant includes the following steps:

[0005] Step S1: Obtain the energy-load-storage resource data corresponding to each power generation unit in the virtual power plant, and perform power generation power prediction analysis on each power generation unit in the virtual power plant based on the energy-load-storage resource data corresponding to each power generation unit to obtain the energy power generation corresponding to each power generation unit;

[0006] Step S2: Analyze the charge and discharge states of the energy storage devices for each power generation unit in the virtual power plant based on the energy power generation corresponding to each power generation unit to obtain the charge and discharge operation state data of the energy storage devices corresponding to each power generation unit; perform resource operation load demand prediction analysis on the corresponding power generation unit based on the energy power generation corresponding to each power generation unit and the charge and discharge operation state data of the energy storage devices to obtain the predicted amount of resource operation load demand corresponding to each power generation unit;

[0007] Step S3: Analyze the resource allocation optimization objectives for each power generation unit in the virtual power plant based on the energy power generation corresponding to each power generation unit and the predicted amount of resource operation load demand to obtain the resource allocation optimization objectives of the power generation units in the virtual power plant;

[0008] Step S4: Perform resource optimization allocation processing on each power generation unit in the virtual power plant according to the optimization goal of the virtual power plant power generation unit resource allocation to generate the optimal allocation plan for the virtual power plant power generation unit resources.

[0009] Further, step S1 includes the following steps:

[0010] Step S11: Obtain the energy, load, and storage resource data corresponding to each power generation unit in the virtual power plant;

[0011] Step S12: Obtain the energy resource input and output amounts corresponding to each power generation unit through the energy, load, and storage resource data corresponding to each power generation unit, and perform real-time monitoring of the power generation of each power generation unit in the virtual power plant through an integrated intelligent electricity meter to obtain the energy resource power generation amounts corresponding to each power generation unit; perform power generation capacity estimation and analysis on the corresponding energy resource power generation amounts based on the energy resource input and output amounts corresponding to each power generation unit to obtain the estimated energy generation capacity amounts corresponding to each power generation unit;

[0012] Step S13: Obtain the virtual power plant meteorological change data, and perform seasonal change characteristic analysis on the virtual power plant meteorological change data to obtain the virtual power plant meteorological seasonal change characteristic data;

[0013] Step S14: Perform environmental impact correction calculation on the estimated energy generation capacity amounts corresponding to each power generation unit based on the virtual power plant meteorological seasonal change characteristic data to obtain the corrected estimated actual power generation capacity amounts corresponding to each power generation unit;

[0014] Step S15: Perform power generation power prediction analysis on the corresponding power generation units in the virtual power plant according to the corrected estimated actual power generation capacity amounts corresponding to each power generation unit to obtain the energy generation power corresponding to each power generation unit.

[0015] Further, the power generation capacity estimation and analysis of the corresponding energy resource power generation amounts based on the energy resource input and output amounts corresponding to each power generation unit in step S12 includes the following steps:

[0016] Perform time series synchronization processing on the energy resource input and output amounts corresponding to each power generation unit to obtain the resource input time series change amounts and resource output time series change amounts corresponding to each power generation unit;

[0017] Extract the time series point input amounts from the resource input time series change amounts corresponding to each power generation unit to obtain the resource input amounts corresponding to each power generation unit at each time series point; calculate the time series point-to-point input fluctuation differences for the resource input amounts corresponding to each power generation unit at each time series point to obtain the resource input change fluctuation differences between each adjacent time series point corresponding to each power generation unit;

[0018] Perform a resource input change gradient analysis on the resource input change fluctuation difference between each power generation unit corresponding to each adjacent time series point to obtain the resource input volume change gradient corresponding to each power generation unit;

[0019] Perform a resource output efficiency evaluation analysis on the resource output time series change amount corresponding to each power generation unit to obtain the resource output efficiency corresponding to each power generation unit;

[0020] Based on the resource input volume change gradient and resource output efficiency corresponding to each power generation unit, perform a power generation capacity prediction analysis on the corresponding energy resource power generation to obtain the energy power generation capacity estimation amount corresponding to each power generation unit.

[0021] Furthermore, step S14 includes the following steps:

[0022] Step S141: Based on the seasonal change characteristics of each meteorological factor in the virtual power plant meteorological seasonal change characteristic data, perform an environmental impact factor identification analysis on the energy power generation capacity estimation amount corresponding to each power generation unit to obtain the environmental impact factor of the energy power generation capacity corresponding to each power generation unit;

[0023] Step S142: Perform a quantitative calculation of the environmental impact coefficient on the environmental impact factor of the energy power generation capacity corresponding to each power generation unit to obtain the power generation capacity impact correction coefficient of the environmental impact factor corresponding to each power generation unit;

[0024] Step S143: Based on the power generation capacity impact correction coefficient of the environmental impact factor corresponding to each power generation unit, perform an environmental impact correction calculation on the energy power generation capacity estimation amount corresponding to each power generation unit to obtain the actual power generation capacity correction estimation amount corresponding to each power generation unit.

[0025] Furthermore, step S2 includes the following steps:

[0026] Step S21: Analyze the time period fluctuation change characteristics of the energy power generation power corresponding to each power generation unit to obtain the power generation power fluctuation change characteristics of each power generation unit in different time periods, where the power generation power fluctuation change characteristics include the power generation power fluctuation peak value, the power generation power fluctuation valley value, and the power generation power fluctuation change frequency;

[0027] Step S22: Based on the power generation power fluctuation change characteristics of each power generation unit in different time periods, identify and divide the operation demand time periods of the energy storage devices of the corresponding power generation units in the virtual power plant to obtain the charging demand operation time periods and the discharging demand operation time periods of the energy storage devices corresponding to each power generation unit;

[0028] Step S23: Design the charging and discharging strategies for the energy storage devices corresponding to each power generation unit based on the charging demand operation periods and discharging demand operation periods of the energy storage devices, so as to generate the time-sequence charging and discharging strategies for the energy storage devices corresponding to each power generation unit;

[0029] Step S24: Analyze the charging and discharging states of the energy storage devices of each power generation unit in the virtual power plant according to the time-sequence charging and discharging strategies of the energy storage devices corresponding to each power generation unit, so as to obtain the charging and discharging operation state data of the energy storage devices corresponding to each power generation unit;

[0030] Step S25: Based on the energy generation power of each power generation unit and the charging and discharging operation state data of the energy storage devices, conduct a predictive analysis on the resource operation load demand of the corresponding power generation unit to obtain the predicted values of the resource operation load demand corresponding to each power generation unit.

[0031] Furthermore, Step S22 includes the following steps:

[0032] Visualize the power generation power fluctuations of the energy storage devices corresponding to each power generation unit in the virtual power plant based on the characteristics of the power generation power fluctuations of each power generation unit at different time periods, so as to obtain the power generation power fluctuation curves of the energy storage devices corresponding to each power generation unit;

[0033] Identify and divide the operation demand periods of the power generation power fluctuation curves of the energy storage devices corresponding to each power generation unit. If the power generation power fluctuation frequency continues to rise in the time period before and after the peak of the power generation power fluctuation in the power generation power fluctuation curve, then divide this time period into the charging demand operation period to obtain the charging demand operation periods of the energy storage devices corresponding to each power generation unit;

[0034] If the power generation power fluctuation frequency continues to decline in the time period before and after the trough of the power generation power fluctuation in the power generation power fluctuation curve, then divide this time period into the discharging demand operation period to obtain the discharging demand operation periods of the energy storage devices corresponding to each power generation unit.

[0035] Furthermore, Step S25 includes the following steps:

[0036] Step S251: Conduct a simulation analysis of the power generation power field for the corresponding power generation units in the virtual power plant based on the energy generation power of each power generation unit to generate the resource operation power generation power simulation fields corresponding to each power generation unit;

[0037] Step S252: Conduct an impact analysis on the power generation power load demand for the resource operation power generation power simulation fields corresponding to each power generation unit to obtain the power generation power operation load demand impact factors corresponding to each power generation unit;

[0038] Step S253: Based on the charge-discharge operation status data of the energy storage devices corresponding to each power generation unit, conduct a charge-discharge state field simulation analysis on the corresponding power generation units in the virtual power plant to generate a resource operation charge-discharge state simulation field for each power generation unit;

[0039] Step S254: Conduct an impact analysis on the charge-discharge load demand of the resource operation charge-discharge state simulation field corresponding to each power generation unit to obtain the charge-discharge operation load demand impact factor corresponding to each power generation unit;

[0040] Step S255: Based on the power generation power operation load demand impact factor and the charge-discharge operation load demand impact factor corresponding to each power generation unit, use the resource operation load demand calculation formula to perform load demand prediction calculations on the corresponding power generation units in the virtual power plant to obtain the predicted resource operation load demand for each power generation unit.

[0041] Further, the resource operation load demand calculation formula described in Step S255 is specifically:

[0042]

[0043] In the formula, L i is the predicted resource operation load demand for the i-th power generation unit, n is the total number of power generation units in the virtual power plant, i is the item measurement parameter of the power generation unit, t is the time variable parameter, τ is the integration time variable parameter, P i (t) is the energy power generation power of the i-th power generation unit at time t, η P is the power generation efficiency factor of the power generation unit, f i (t) is the power generation power operation load demand impact factor of the i-th power generation unit at time t, E i (t) is the charge-discharge operation status of the energy storage device of the i-th power generation unit at time t, η E is the charge-discharge efficiency factor of the energy storage device, g i (t) is the charge-discharge operation load demand impact factor of the i-th power generation unit at time t, λ is the resource operation load demand attenuation factor, L(τ) is the resource operation load demand time delay effect factor at time τ, and ξ is the correction coefficient of the predicted resource operation load demand.

[0044] Further, Step S3 includes the following steps:

[0045] Step S31: Based on the energy power generation power and the predicted resource operation load demand corresponding to each power generation unit, conduct a resource allocation potential assessment analysis on each power generation unit in the virtual power plant to obtain the energy resource allocation potential of each power generation unit under specific operation load demand conditions;

[0046] Step S32: Analyze the resource allocation constraints for the corresponding power generation units in the virtual power plant based on the energy resource allocation potential of each power generation unit under specific operating load demand conditions, so as to generate the resource allocation constraint conditions corresponding to each power generation unit;

[0047] Step S33: Analyze the resource optimization strategies for the corresponding power generation units in the virtual power plant based on the resource allocation constraint conditions corresponding to each power generation unit, so as to generate the resource allocation optimization strategies corresponding to each power generation unit;

[0048] Step S34: Analyze the resource allocation optimization objectives for the corresponding power generation units in the virtual power plant according to the resource allocation optimization strategies corresponding to each power generation unit, and obtain the resource allocation optimization objectives of the power generation units in the virtual power plant.

[0049] Furthermore, the present invention also provides a virtual power plant resource optimization and allocation system for executing the virtual power plant resource optimization and allocation method as described above. The virtual power plant resource optimization and allocation system includes:

[0050] A power generation power prediction module for virtual power plant subunits, which is used to obtain the energy, load, and storage resource data corresponding to each power generation unit in the virtual power plant, and perform power generation power prediction analysis on each power generation unit in the virtual power plant based on the energy, load, and storage resource data corresponding to each power generation unit, so as to obtain the energy power generation corresponding to each power generation unit;

[0051] A subunit resource load demand analysis module, which is used to analyze the charge and discharge states of energy storage devices for each power generation unit in the virtual power plant based on the energy power generation corresponding to each power generation unit, so as to obtain the charge and discharge operation state data of the energy storage devices corresponding to each power generation unit; perform resource operation load demand prediction analysis on the corresponding power generation unit based on the energy power generation corresponding to each power generation unit and the charge and discharge operation state data of the energy storage devices, so as to obtain the predicted amount of resource operation load demand corresponding to each power generation unit;

[0052] A virtual power plant resource allocation optimization objective analysis module, which is used to perform resource allocation optimization objective analysis on each power generation unit in the virtual power plant based on the energy power generation corresponding to each power generation unit and the predicted amount of resource operation load demand, so as to obtain the resource allocation optimization objectives of the power generation units in the virtual power plant;

[0053] A resource allocation optimization output module, which is used to perform resource optimization and allocation processing on each power generation unit in the virtual power plant according to the resource allocation optimization objectives of the power generation units in the virtual power plant, so as to generate the optimal resource allocation scheme for the power generation units in the virtual power plant.

[0054] Advantages of the present invention:

[0055] 1. Compared with the prior art, the beneficial effect of the virtual power plant resource optimization configuration method proposed by the present invention is that by obtaining the energy load storage resource data corresponding to each power generation unit in the virtual power plant, the resource status, power generation capacity and its contribution to the overall power grid of each power generation unit can be comprehensively understood. These data include information such as battery energy storage status, fuel energy input and output, and renewable energy generation capacity, which can provide data support for subsequent processing. In addition, accurate data collection can promote the real-time monitoring and maintenance of power generation capacity, timely discover potential problems, reduce failure rates, and thus improve power generation efficiency and safety. Through big data analysis, the virtual power plant manager can conduct trend analysis based on the energy input and output to identify efficient power generation units, optimize resource allocation, improve resource utilization rate, and ensure the best power generation performance under different meteorological conditions. At the same time, through the power generation power prediction analysis of each power generation unit in the virtual power plant based on the energy load storage resource data corresponding to each power generation unit, this step can provide a more accurate power generation power prediction by combining resource power generation, real-time monitoring information and meteorological prediction. Effective power prediction not only helps the power dispatching center reasonably allocate resources during peak load periods to ensure the stability and safety of power supply, but also can reduce operating costs, improve the flexibility and response speed of the power grid, thus providing basic data guarantee for the subsequent operation load demand prediction processing. Secondly, through the analysis of the charge and discharge state of the energy storage device of each power generation unit in the virtual power plant based on the energy power generation power corresponding to each power generation unit, this process not only involves the real-time monitoring of data, but also requires statistical analysis of the energy power generation power to evaluate the actual effect of the charge and discharge strategy. By deeply analyzing the charge and discharge state of the energy storage device, this step can obtain the operation state data of each power generation unit, so as to evaluate the efficiency and reliability of the energy storage device. The effectiveness of this step directly affects the operation efficiency of the whole process, especially when rapid response to power market changes and load fluctuations is required, it can provide necessary support. This analysis not only improves the utilization rate of the energy storage device, but also provides an important basis for optimizing the overall resource optimization configuration management. Also, through the resource operation load demand prediction analysis of the corresponding power generation unit based on the energy power generation power of each power generation unit and the charge and discharge operation state data of the energy storage device, the load demand of each power generation unit in a future period can be accurately predicted. Accurate load demand prediction can not only help operators optimize the power generation portfolio and reduce operating costs, but also provide a basis for the resource optimization configuration strategy of the virtual power plant, contribute to promoting the use of renewable energy and reducing carbon emissions, so that the flexibility and adaptability of the virtual power plant in resource operation are enhanced, thus maintaining a competitive advantage in the increasingly complex power market.Then, through analyzing the resource allocation optimization objectives of each power generation unit in the virtual power plant based on the energy generation power corresponding to each power generation unit and the predicted value of the resource operation load demand, this process is the ultimate goal of the entire virtual power plant resource management chain. Through clear optimization objectives, the virtual power plant can set clear resource optimization allocation objectives and use them as the basis for subsequent evaluation and adjustment. This analysis not only helps to achieve short-term economic benefits but also can improve the overall efficiency and sustainability of each power generation unit in the virtual power plant in the long term. The setting of optimization objectives helps to guide the scientific allocation of virtual power plant resources, can adapt to changes in market demand and resource availability in real time, enables managers to monitor and evaluate the operating status of each power generation unit in real time, and thus improves the efficiency of virtual power plant resource allocation. Finally, according to the virtual power plant power generation unit resource allocation optimization objectives obtained from the previous analysis, resource optimization allocation processing is carried out on each power generation unit in the virtual power plant. The main purpose of this step is to transform the theoretical optimization objectives into actual operation plans to ensure that each power generation unit can reasonably allocate power plant resources according to market demand and its own status. This kind of optimization allocation not only includes the adjustment of power generation power but also covers multiple aspects such as the use strategy of energy storage devices and the allocation of spare parts. It can significantly improve the overall effectiveness of the virtual power plant. Through real-time scheduling and optimization, the virtual power plant can flexibly respond in different power market environments, ensure stable power supply, and thus promote the resource allocation optimization process of the entire virtual power system.

[0056] 2. The virtual power plant resource optimization allocation system proposed by the present invention is generally composed of a virtual power plant subunit power generation power prediction module, a subunit resource load demand analysis module, a virtual power plant resource allocation optimization objective analysis module, and a resource allocation optimization output module, and can implement any virtual power plant resource optimization allocation method described in the present invention. It is used to realize the virtual power plant resource optimization allocation method through the operation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, can quickly and effectively provide a more accurate and efficient virtual power plant resource optimization allocation process, and thus simplifies the operation process of the virtual power plant resource optimization allocation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, objectives, and advantages of the present invention will become more obvious:

[0058] Figure 1 It is a schematic flowchart of the steps of the virtual power plant resource optimization allocation method of the present invention;

[0059] Figure 2 For Figure 1 the detailed step flowchart of step S1 in

[0060] Figure 3 is Figure 2 a detailed step - by - step schematic diagram of step S14 in Specific implementation manner

[0061] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0062] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0063] It should be understood that although the terms "first", "second", etc. may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0064] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a method for optimizing the resource allocation of a virtual power plant, and the method includes the following steps:

[0065] Step S1: Obtain the energy - load - storage resource data corresponding to each power generation unit in the virtual power plant, and perform power generation power prediction and analysis on each power generation unit in the virtual power plant based on the energy - load - storage resource data corresponding to each power generation unit to obtain the energy power generation power corresponding to each power generation unit;

[0066] Step S2: Analyze the charge-discharge states of the energy storage devices of each power generation unit in the virtual power plant based on the energy generation power corresponding to each power generation unit, so as to obtain the charge-discharge operation state data of the energy storage devices corresponding to each power generation unit; based on the energy generation power corresponding to each power generation unit and the charge-discharge operation state data of the energy storage devices, conduct a prediction analysis on the resource operation load demand of the corresponding power generation unit, and obtain the predicted values of the resource operation load demand corresponding to each power generation unit;

[0067] Step S3: Analyze the resource allocation optimization objectives of each power generation unit in the virtual power plant based on the energy generation power corresponding to each power generation unit and the predicted values of the resource operation load demand, and obtain the resource allocation optimization objectives of the power generation units in the virtual power plant;

[0068] Step S4: Perform resource optimization allocation processing on each power generation unit in the virtual power plant according to the resource allocation optimization objectives of the power generation units in the virtual power plant, so as to generate the optimal resource allocation scheme for the power generation units in the virtual power plant.

[0069] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic flowchart of the steps of the method for optimizing the resource allocation of the virtual power plant of the present invention. In this example, the method for optimizing the resource allocation of the virtual power plant includes the following steps:

[0070] Step S1: Obtain the energy-load-storage resource data corresponding to each power generation unit in the virtual power plant, and conduct a power generation power prediction analysis on each power generation unit in the virtual power plant based on the energy-load-storage resource data corresponding to each power generation unit, so as to obtain the energy generation power corresponding to each power generation unit;

[0071] In the embodiment of the present invention, energy load storage resource data is collected through a sensor network installed in each power generation unit within the virtual power plant. These sensors continuously monitor the operating status of the power generation unit, the energy storage level, and the load demand, etc., forming a comprehensive energy load storage resource dataset, thereby obtaining the energy load storage resource data corresponding to each power generation unit. By obtaining the energy resource input and output corresponding to each power generation unit from the previously collected energy load storage resource data, and through the use of integrated smart meters to conduct real-time monitoring of the energy flow of each power generation unit, these meters not only record the input energy of the power generation unit (such as the input of solar energy, wind energy, or other renewable resources) and the output energy (the electrical energy output during the power generation process), but also integrate this data to form a dynamic energy flow diagram. Through data collection and transmission protocols (such as MODBUS or MQTT), the real-time update and accurate transmission of data are ensured, thereby obtaining the energy resource power generation of each power generation unit. And by using statistical analysis methods to conduct predictive analysis of the power generation power of the resources corresponding to each power generation unit based on the previously collected energy resource input and output. This step adopts a time series prediction method. By analyzing the influence relationship between the power generation data and the resource input / output or environmental meteorology, and using a deep learning model (such as a long short-term memory network LSTM) to perform predictive calculations on the future power generation power. Through an ensemble learning method (such as random forest, gradient boosting tree), the accuracy and stability of the prediction are improved. After the prediction is completed, the optimal allocation of the virtual power plant resources is ensured, realizing sustainable and efficient energy management, and finally predicting and calculating the energy power generation corresponding to each power generation unit.

[0072] Step S2: Analyze the charge and discharge status of the energy storage devices of each power generation unit within the virtual power plant based on the energy power generation corresponding to each power generation unit to obtain the charge and discharge operation status data of the energy storage devices corresponding to each power generation unit; conduct predictive analysis of the resource operation load demand of the corresponding power generation unit based on the energy power generation corresponding to each power generation unit and the charge and discharge operation status data of the energy storage devices to obtain the predicted amount of resource operation load demand corresponding to each power generation unit;

[0073] In the embodiments of the present invention, by analyzing the time - period fluctuation change characteristics of the power generation of each power generation unit, a time - series analysis algorithm is used to calculate the peak and valley values of the power generation power fluctuation. The specific method includes calculating the maximum and minimum values of the power generation power to obtain the peak and valley values of the fluctuation. In addition, Fourier transform or wavelet transform methods are used to perform frequency analysis on the data to obtain the power generation power fluctuation change frequency. And by using the power generation power fluctuation change characteristics obtained from the previous fluctuation analysis, the operation demand time periods of the energy storage devices of each power generation unit in the virtual power plant are identified and divided. By setting the upper and lower thresholds of the power generation power and comparing them with the peak and valley values, it is determined when charging and discharging are required. For example, when the corresponding fluctuation change frequency continuously rises in the time period before and after the occurrence of the power generation power fluctuation peak, the energy storage device enters the charging state; conversely, when the fluctuation change frequency continuously decreases in the time period before and after the occurrence of the power generation power fluctuation valley, the energy storage device enters the discharging state. Using the time - series analysis method, the charging and discharging demands of each power generation unit in different time periods are further identified. At the same time, by combining the charging demand operation time periods and discharging demand operation time periods determined from the previous division, the charge - discharge strategies of the energy storage devices of the corresponding power generation units in the virtual power plant are designed. In this process, an optimization algorithm (such as dynamic programming or genetic algorithm) is used to model the charge - discharge strategies of the energy storage devices. The goal is to minimize the operation cost and maximize the resource utilization efficiency. Factors such as electricity price fluctuations, load demand changes, and the instability of renewable energy power generation are considered in the design process to form a time - series charge - discharge strategy for each power generation unit. And based on the time - series charge - discharge strategy of the energy storage device generated from the previous design, the charge - discharge state analysis of the energy storage devices of the corresponding power generation units is carried out. In specific implementation, the charge - discharge state of the energy storage device is tracked through a real - time monitoring system, and the charging duration, discharging duration, and charge - discharge efficiency are recorded. Data analysis tools (such as data analysis libraries in MATLAB or Python) are used to organize and analyze the recorded data to obtain the charge - discharge operation state data. This process can intuitively reflect the operation state of the energy storage device. Then, by combining the energy generation power corresponding to each power generation unit obtained from the previous statistical analysis and the charge - discharge operation state data of the energy storage device, the prediction analysis of the resource operation load demand of the corresponding power generation unit is carried out. This step is achieved by constructing a load prediction model (such as machine - learning algorithms like linear regression, support vector machine, etc.). The input data includes the power generation power, the operation state data of the energy storage device, and other relevant meteorological data. The model will analyze the time - series characteristics of the data and predict the resource operation load demand quantity of each power generation unit in the future time period, and finally obtain the predicted quantity of the resource operation load demand corresponding to each power generation unit.

[0074] Step S3: Based on the energy generation power corresponding to each power generation unit and the predicted resource operation load demand, perform an analysis on the resource allocation optimization objectives of each power generation unit in the virtual power plant to obtain the resource allocation optimization objectives of the power generation units in the virtual power plant;

[0075] In the embodiment of the present invention, a mathematical model is established by combining the energy generation power corresponding to each power generation unit obtained from previous statistical analysis and the predicted resource operation load demand, and data mining technology is used to analyze the power generation resource allocation potential of each power generation unit in the virtual power plant under different operation load demands. And through combining the energy resource allocation potential of each power generation unit under specific operation load demand conditions obtained from previous evaluation analysis, a constraint analysis of the resource allocation of the corresponding power generation unit is carried out to analyze the resource allocation constraint conditions of each power generation unit in the virtual power plant, including factors such as the maximum load, minimum power generation capacity, and fuel supply capacity of the power generation unit. At the same time, through combining the resource allocation constraint conditions obtained from previous analysis, an optimization analysis of the resource optimization strategy of the corresponding power generation unit in the virtual power plant is carried out to generate a resource allocation optimization strategy for each power generation unit by using genetic algorithm, simulated annealing algorithm or other optimization algorithms. Specifically, when implementing, a target function is constructed, such as minimizing the power generation cost or maximizing the economic benefit, and the power generation power of each power generation unit is continuously adjusted through an iterative algorithm to meet the resource allocation constraint conditions. The generation process of the resource optimization strategy is realized by MATLAB programming to ensure the effectiveness and feasibility of the resource allocation scheme. Then, through combining the previously generated resource allocation optimization strategy, an identification analysis of the resource allocation optimization objective of the corresponding power generation unit is carried out to set specific optimization objectives, such as reducing the power generation cost and improving the operation efficiency. Using data analysis tools, combined with historical data and optimization results, a quantitative analysis of the resource allocation optimization objectives of each power generation unit is carried out. Specifically, when implementing, statistical software is used for data regression analysis to generate an evaluation report of the optimization objective to provide a clear optimization direction and basis, providing reliable decision-making support for the resource optimization allocation method of the virtual power plant, and finally obtaining the resource allocation optimization objectives of the power generation units in the virtual power plant.

[0076] Step S4: According to the resource allocation optimization objectives of the power generation units in the virtual power plant, perform resource optimization allocation processing on each power generation unit in the virtual power plant to generate an optimal resource allocation scheme for the power generation units in the virtual power plant.

[0077] In an embodiment of the present invention, by using the previously obtained optimization objective of the resource allocation of the virtual power plant's power generation units to implement a specific resource optimization allocation plan for the corresponding power generation units within the virtual power plant. At this stage, an optimization scheduling tool (such as a power market trading system or a distributed energy management system) needs to be used to allocate resources to each power generation unit according to the previous resource allocation optimization objective. Through real-time data analysis, an optimal power generation plan is implemented to ensure that the output of the power generation unit is consistent with the demand under the condition of load fluctuations. For example, if the load is expected to increase during a certain period, the corresponding power generation unit will be instructed to increase its power generation output, and at the same time, the charge and discharge state of the energy storage device will be adjusted. This process needs to consider the stability and economy of the power grid, and finally generate an optimal resource allocation plan for the virtual power plant's power generation units, improving the overall resource allocation optimization efficiency of the virtual power plant and ensuring the reliability and sustainability of power supply.

[0078] Further, step S1 includes the following steps:

[0079] Step S11: Obtain the energy-load-storage resource data corresponding to each power generation unit within the virtual power plant;

[0080] Step S12: Obtain the energy resource input and output corresponding to each power generation unit through the energy-load-storage resource data corresponding to each power generation unit, and conduct real-time monitoring of the power generation of each power generation unit within the virtual power plant through an integrated smart meter to obtain the energy resource power generation corresponding to each power generation unit; conduct power generation capacity prediction analysis on the corresponding energy resource power generation based on the energy resource input and output corresponding to each power generation unit to obtain the estimated energy power generation capacity corresponding to each power generation unit;

[0081] Step S13: Obtain the meteorological change data of the virtual power plant, and conduct seasonal change characteristic analysis on the meteorological change data of the virtual power plant to obtain the meteorological seasonal change characteristic data of the virtual power plant;

[0082] Step S14: Conduct environmental impact correction calculation on the estimated energy power generation capacity corresponding to each power generation unit based on the meteorological seasonal change characteristic data of the virtual power plant to obtain the corrected estimated actual power generation capacity corresponding to each power generation unit;

[0083] Step S15: Conduct power generation power prediction analysis on the corresponding power generation units within the virtual power plant according to the corrected estimated actual power generation capacity corresponding to each power generation unit to obtain the energy power generation corresponding to each power generation unit.

[0084] As an embodiment of the present invention, referring to Figure 2 shown, for Figure 1 the detailed step flow schematic diagram of step S1 in

[0085] Step S11: Obtain the energy-load-storage resource data corresponding to each power generation unit in the virtual power plant;

[0086] In the embodiment of the present invention, the energy-load-storage resource data is collected through a sensor network installed in each power generation unit in the virtual power plant. These sensors monitor the operating status, energy storage level, and load demand of the power generation unit in real time. The data acquisition system uses high-precision intelligent sensors that can capture the battery energy storage status, fuel energy input and output, renewable energy generation capacity, etc. of each unit. These data are preliminarily processed by edge computing devices to ensure the efficiency and accuracy of data transmission, forming a comprehensive energy-load-storage resource data set, and finally obtaining the energy-load-storage resource data corresponding to each power generation unit.

[0087] Step S12: Obtain the energy resource input and output corresponding to each power generation unit through the energy-load-storage resource data corresponding to each power generation unit, and perform real-time monitoring of the power generation of each power generation unit in the virtual power plant through an integrated intelligent electricity meter to obtain the energy resource power generation corresponding to each power generation unit; perform power generation capacity prediction analysis on the corresponding energy resource power generation based on the energy resource input and output corresponding to each power generation unit to obtain the energy power generation capacity estimation corresponding to each power generation unit;

[0088] In the embodiment of the present invention, the energy resource input and output corresponding to each power generation unit are obtained from the previously collected energy-load-storage resource data, and the real-time monitoring of the energy flow of each power generation unit is performed by using an integrated intelligent electricity meter. These electricity meters not only record the input energy (such as the input of solar energy, wind energy, or other renewable resources) and output energy (the electrical energy output during the power generation process) of the power generation unit, but also integrate these data to form a dynamic energy flow diagram. Through data acquisition and transmission protocols (such as MODBUS or MQTT), the real-time update and accurate transmission of data are ensured, so as to obtain the energy resource power generation corresponding to each power generation unit. At the same time, through the energy resource input and output collected previously, the statistical analysis method is used to perform power generation capacity prediction analysis on the resource power generation. In practice, methods such as regression analysis and time series analysis are adopted, combined with historical power generation data and real-time data, to establish a power generation capacity prediction model, and machine learning algorithms (such as support vector machines and random forests) are used to train the model so that it can predict the future power generation capacity according to the change of input data, and finally obtain the energy power generation capacity estimation corresponding to each power generation unit.

[0089] Step S13: Obtain the virtual power plant meteorological change data, and perform seasonal change characteristic analysis on the virtual power plant meteorological change data to obtain the virtual power plant meteorological seasonal change characteristic data;

[0090] In the embodiment of the present invention, in terms of obtaining meteorological data, the virtual power plant needs to access the regional meteorological service system to obtain the meteorological change data of the virtual power plant in real time, such as temperature, humidity, wind speed, precipitation, etc. These data are updated regularly through the API interface and stored in the database. At the same time, by using statistical software (such as R or MATLAB), seasonal change characteristics analysis is carried out on the meteorological change data of the virtual power plant to identify the impact of meteorological conditions on energy production. Through methods such as Fourier transform or wavelet analysis, the seasonal characteristics of meteorological changes are extracted, and finally the meteorological seasonal change characteristic data of the virtual power plant are obtained.

[0091] Step S14: Based on the meteorological seasonal change characteristic data of the virtual power plant, perform environmental impact correction calculation on the energy generation capacity estimation amounts corresponding to each power generation unit to obtain the actual power generation capacity correction estimation amounts corresponding to each power generation unit;

[0092] In the embodiment of the present invention, after completing the meteorological characteristic analysis, environmental impact correction calculation is performed on the power generation capacity of each power generation unit based on the obtained meteorological seasonal change characteristic data. The specific operation includes using the established correction model to combine the meteorological data with the power generation capacity estimation amount, and adjusting the model through the weighting coefficient to reflect the actual power generation capacity under different meteorological conditions. This process can adopt mathematical optimization techniques (such as linear programming or non-linear programming) to ensure the effectiveness and accuracy of the correction calculation, and finally obtain the actual power generation capacity correction estimation amounts corresponding to each power generation unit.

[0093] Step S15: Perform power generation power prediction analysis on the corresponding power generation units in the virtual power plant according to the actual power generation capacity correction estimation amounts corresponding to each power generation unit to obtain the energy generation power corresponding to each power generation unit.

[0094] In the embodiment of the present invention, through the prediction analysis of the power generation power of the corresponding power generation units according to the actual power generation capacity correction estimation amounts corresponding to each power generation unit obtained from the previous correction calculation. This step adopts the time series prediction method. By analyzing the relationship between historical power generation data and environmental factors, and using a deep learning model (such as long short-term memory network LSTM) to predict and calculate the future power generation power. Through the ensemble learning method (such as random forest, gradient boosting tree), the accuracy and stability of the prediction are improved. After the prediction is completed, it will ensure the optimal allocation of virtual power plant resources and achieve sustainable and efficient energy management. Finally, the energy generation power corresponding to each power generation unit is obtained through prediction calculation.

[0095] Furthermore, the power generation capacity estimation analysis of the corresponding energy resource power generation amount based on the energy resource input amount and the energy resource output amount corresponding to each power generation unit in step S12 includes the following steps:

[0096] Perform time series synchronization processing on the input amount and output amount of energy resources corresponding to each power generation unit to obtain the resource input time series change amount and resource output time series change amount corresponding to each power generation unit;

[0097] In the embodiment of the present invention, by performing time series synchronization processing on the input amount and output amount of energy resources corresponding to each power generation unit, the real-time data of the power generation unit is centrally collected by using a high-precision data acquisition system. In the specific implementation process, by establishing a data processing model, the input and output data of each power generation unit in the same time period are compared to ensure time consistency, and the input and output data are marked with time stamps. Subsequently, the input amount and output amount of each power generation unit are normalized, and the automatic processing of data is realized through programming to ensure that the resource input amount and output amount of each power generation unit are analyzed under the same time reference, and finally the resource input time series change amount and resource output time series change amount corresponding to each power generation unit are obtained.

[0098] Preferably, extract the time series point input amount from the resource input time series change amount corresponding to each power generation unit to obtain the resource input amount corresponding to each power generation unit at each time series point; calculate the input fluctuation difference between time series points for the resource input amount corresponding to each power generation unit at each time series point to obtain the resource input change fluctuation difference between each adjacent time series point corresponding to each power generation unit;

[0099] In the embodiment of the present invention, sample and record the resource input time series change amount corresponding to each power generation unit by setting specific time points. By selecting a suitable time window (such as every hour or every minute) as the time series point, use a data extraction tool (such as the Pandas library in Python) to read and filter out the resource input amount data of each power generation unit at these specific time points. After ensuring the data integrity of each time point, construct a time series data set that can accurately reflect the resource input amount at each time series point, so as to obtain the resource input amount corresponding to each power generation unit at each time series point. At the same time, by using the difference method to calculate the difference in resource input amount between adjacent time points. In the specific implementation, by setting a loop structure, compare the resource input amounts of each power generation unit at adjacent time series points one by one, calculate the input fluctuation difference, and store the calculation results in a data frame, which can reveal the fluctuation characteristics of resource input, and finally obtain the resource input change fluctuation difference between each adjacent time series point corresponding to each power generation unit.

[0100] Preferably, perform resource input change gradient analysis on the resource input change fluctuation difference between each adjacent time series point corresponding to each power generation unit to obtain the resource input amount change gradient corresponding to each power generation unit;

[0101] In the embodiments of the present invention, by statistically analyzing the resource input change gradient of the resource input change fluctuation difference between each adjacent time series point corresponding to each power generation unit, and performing fitting analysis on the fluctuation difference by using a linear regression model to calculate the gradient of the resource input change. Specifically, in implementation, the fluctuation difference is used as the independent variable, and the time is used as the dependent variable, and regression analysis is performed through statistical software (such as R or MATLAB) to obtain the input change gradient between each time series point of each power generation unit. This analysis result can clearly show the resource input change trend of each power generation unit over time, and finally obtain the resource input quantity change gradient corresponding to each power generation unit.

[0102] Preferably, the resource output efficiency evaluation analysis is performed on the resource output time series change amount corresponding to each power generation unit to obtain the resource output efficiency corresponding to each power generation unit;

[0103] In the embodiments of the present invention, by performing the evaluation calculation of the resource output efficiency on the resource output time series change amount corresponding to each power generation unit, and by setting the calculation formula of the resource output efficiency, for example, output efficiency = output quantity / output duration. In the implementation process, statistical methods (such as weighted average) are used to calculate the resource output efficiency of each power generation unit, and finally the resource output efficiency corresponding to each power generation unit is obtained.

[0104] Preferably, based on the resource input quantity change gradient and the resource output efficiency corresponding to each power generation unit, the power generation capacity prediction analysis is performed on the corresponding energy resource power generation amount to obtain the energy power generation capacity estimation amount corresponding to each power generation unit.

[0105] In the embodiments of the present invention, by combining the resource input quantity change gradient and the resource output efficiency corresponding to each power generation unit obtained from the previous analysis, the power generation capacity prediction analysis is performed on the corresponding resource power generation amount. In specific implementation, by combining the resource input change gradient and the output efficiency of each power generation unit, a model prediction method (such as time series prediction or machine learning model) is used to estimate the power generation capacity. In this process, a regression model is constructed, and the input gradient and the output efficiency are used as feature variables, and the corresponding resource power generation amount is combined to predict and calculate the power generation capacity of each power generation unit. By simulating different input conditions and output efficiencies, a more accurate power generation capacity estimation amount is obtained, and finally the energy power generation capacity estimation amount corresponding to each power generation unit is obtained.

[0106] Further, step S14 includes the following steps:

[0107] Step S141: Based on the seasonal change characteristics of each meteorological factor in the virtual power plant meteorological seasonal change characteristic data, conduct an identification and analysis of the environmental impact factors for the estimated energy generation capacity corresponding to each power generation unit, and obtain the environmental impact factors of the energy generation capacity corresponding to each power generation unit;

[0108] Step S142: Quantitatively calculate the environmental impact coefficients for the environmental impact factors of the energy generation capacity corresponding to each power generation unit, and obtain the power generation capacity impact correction coefficients for the environmental impact factors corresponding to each power generation unit;

[0109] Step S143: Based on the power generation capacity impact correction coefficients of the environmental impact factors corresponding to each power generation unit, conduct an environmental impact correction calculation on the estimated energy generation capacity corresponding to each power generation unit, and obtain the corrected estimated actual power generation capacity corresponding to each power generation unit.

[0110] As an embodiment of the present invention, referring to Figure 3 shown, it is Figure 2 a detailed step - by - step schematic diagram of step S14 in

[0111] Step S141: Based on the seasonal change characteristics of each meteorological factor in the virtual power plant meteorological seasonal change characteristic data, conduct an identification and analysis of the environmental impact factors for the estimated energy generation capacity corresponding to each power generation unit, and obtain the environmental impact factors of the energy generation capacity corresponding to each power generation unit;

[0112] In the embodiment of the present invention, by collecting and organizing the meteorological seasonal change characteristic data in the virtual power plant, through the use of a variety of meteorological observation tools, such as meteorological stations, satellite remote sensing technology, and meteorological simulation software, meteorological factors related to each power generation unit are obtained, including temperature, humidity, wind speed, precipitation, and sunshine duration, etc. These meteorological data will be classified by season, statistically analyzed, and the time - series analysis method is used to identify the seasonal fluctuation characteristics of each meteorological factor, determine its impact on the energy generation capacity of the power generation unit in different seasons, and further use statistical analysis software (such as SPSS or R) for correlation analysis to identify environmental impact factors. For example, it is found that in the case of high temperature in summer, the power generation capacity of the photovoltaic power generation unit is significantly improved, while in winter with low temperature, the power generation capacity of the wind power generation unit significantly decreases. These analysis results will form the environmental impact factors corresponding to the power generation unit, and finally, the environmental impact factors of the energy generation capacity corresponding to each power generation unit are obtained.

[0113] Step S142: Quantitatively calculate the environmental impact coefficients for the environmental impact factors of the energy generation capacity corresponding to each power generation unit, and obtain the power generation capacity impact correction coefficients for the environmental impact factors corresponding to each power generation unit;

[0114] In the embodiments of the present invention, for the environmental impact factors identified previously, the environmental impact coefficient quantification calculation is performed on the energy generation capabilities of each power generation unit, so as to calculate the impact coefficients of each power generation unit under different meteorological conditions by using the weighted average method. Tools such as Excel tables are used to input the statistical results of the environmental impact factors into the table, and the data analysis function is applied to calculate the correction coefficients of the power generation capabilities of each power generation unit under specific meteorological conditions, that is, multiplying the corresponding environmental impact factors by weights and calculating the average value. In this process, different influence degrees of each meteorological factor on the power generation capabilities of the power generation units need to be considered, and the weights of each factor are determined in combination with the actual meteorological data. For example, for a photovoltaic power generation unit, the influence weight of temperature is higher than that of humidity. Therefore, the calculated correction coefficients of the power generation capabilities can truly reflect the actual influence of environmental changes on its power generation capabilities. This process ensures that the obtained influence coefficients have practical operability, and finally the correction coefficients of the power generation capabilities of each power generation unit corresponding to the environmental impact factors are obtained.

[0115] Step S143: Perform environmental impact correction calculation on the estimated energy generation capabilities corresponding to each power generation unit based on the correction coefficients of the power generation capabilities of each power generation unit corresponding to the environmental impact factors, so as to obtain the corrected estimated actual power generation capabilities corresponding to each power generation unit.

[0116] In the embodiments of the present invention, the estimated energy generation capabilities obtained from the previous estimation calculation are corrected by combining the correction coefficients of the power generation capabilities of each power generation unit corresponding to the environmental impact factors obtained from the previous quantitative calculation. In specific implementation, first, the original estimated power generation capabilities of each power generation unit and their corresponding environmental impact correction coefficients are summarized to form a data set. Subsequently, a programming tool (such as Python or MATLAB) is used for batch calculation to perform multiplication operations on the environmental impact correction coefficients and the original power generation capabilities to obtain the corrected estimated actual power generation capabilities. The obtained corrected estimation shows that the power generation capability of a certain photovoltaic power generation unit increases by 20% under specific meteorological conditions. Finally, the corrected estimated actual power generation capabilities corresponding to each power generation unit are obtained.

[0117] Further, step S2 includes the following steps:

[0118] Step S21: Analyze the time - period fluctuation change characteristics of the energy generation power corresponding to each power generation unit to obtain the power generation power fluctuation change characteristics of each power generation unit in different time periods, where the power generation power fluctuation change characteristics include the power generation power fluctuation peak value, the power generation power fluctuation valley value, and the power generation power fluctuation change frequency;

[0119] In an embodiment of the present invention, by analyzing the time - period fluctuation characteristics of the power generation of each power generation unit, first, a data acquisition system is used to collect the power generation data of each power generation unit within a certain period of time. The data acquisition can be carried out using high - precision power monitoring equipment. During the data processing, a time - series analysis algorithm is used to calculate the fluctuation peak and valley values of the power generation. The specific method includes calculating the maximum and minimum values of the power generation to obtain the fluctuation peak and valley values. In addition, Fourier transform or wavelet transform methods are used to perform frequency analysis on the data to obtain the power generation fluctuation change frequency. Through these analyses, the power generation fluctuation change characteristics of each power generation unit in different time periods are finally obtained, including the power generation fluctuation peak value, the power generation fluctuation valley value, and the power generation fluctuation change frequency.

[0120] Step S22: Based on the power generation fluctuation change characteristics of each power generation unit in different time periods, identify and divide the operation demand time periods of the energy storage devices corresponding to the power generation units in the virtual power plant, so as to obtain the charging demand operation time periods and the discharging demand operation time periods of the energy storage devices corresponding to each power generation unit.

[0121] In an embodiment of the present invention, by using the power generation fluctuation change characteristics obtained from the previous fluctuation analysis to identify and divide the operation demand time periods of the energy storage devices of each power generation unit in the virtual power plant, by setting the upper and lower thresholds of the power generation and comparing them with the fluctuation peak and valley values, it is determined when charging and discharging are required. For example, when the corresponding fluctuation change frequency continuously rises in the time period before and after the appearance of the power generation fluctuation peak value, the energy storage device enters the charging state; conversely, when the fluctuation change frequency continuously decreases in the time period before and after the appearance of the power generation fluctuation valley value, the energy storage device enters the discharging state. Using the time - series analysis method, the charging demand and discharging demand of each power generation unit in different time periods are further identified, and finally, the charging demand operation time periods and the discharging demand operation time periods of the energy storage devices corresponding to each power generation unit are obtained.

[0122] Step S23: Based on the charging demand operation time periods and the discharging demand operation time periods of the energy storage devices corresponding to each power generation unit, design the charge - discharge strategies for the energy storage devices corresponding to the power generation units in the virtual power plant, so as to generate the time - series charge - discharge strategies of the energy storage devices corresponding to each power generation unit.

[0123] In the embodiments of the present invention, by combining the energy storage device charging demand operation period and the energy storage device discharging demand operation period determined by the previous division, a charging and discharging strategy for the energy storage devices of the corresponding power generation units in the virtual power plant is designed. In this process, an optimization algorithm (such as dynamic programming or genetic algorithm) is used to model the charging and discharging strategy of the energy storage device, with the goal of minimizing the operating cost and maximizing the resource utilization efficiency. Factors such as electricity price fluctuations, load demand changes, and the instability of renewable energy generation are considered during the design process to form a time-series charging and discharging strategy for each power generation unit. These strategies will guide the energy storage device to charge and discharge at appropriate times, thereby optimizing the resource allocation, and finally designing and generating the time-series charging and discharging strategies for the energy storage devices corresponding to each power generation unit.

[0124] Step S24: Analyze the charging and discharging states of the energy storage devices of each power generation unit in the virtual power plant according to the time-series charging and discharging strategies of the energy storage devices corresponding to each power generation unit, so as to obtain the charging and discharging operation state data of the energy storage devices corresponding to each power generation unit.

[0125] In the embodiments of the present invention, by analyzing the charging and discharging states of the energy storage devices of the corresponding power generation units according to the time-series charging and discharging strategies of the energy storage devices generated previously. In specific implementation, the charging and discharging states of the energy storage devices are tracked through a real-time monitoring system, the charging duration, discharging duration, and charging and discharging efficiency are recorded, and a data analysis tool (such as a data analysis library in MATLAB or Python) is used to organize and analyze the recorded data to obtain the charging and discharging operation state data. This process can intuitively reflect the operation state of the energy storage device, help judge the effectiveness and rationality of the charging and discharging strategy, and finally obtain the charging and discharging operation state data of the energy storage devices corresponding to each power generation unit.

[0126] Step S25: Based on the energy generation power of each power generation unit and the charging and discharging operation state data of the energy storage device, perform a prediction analysis on the resource operation load demand of the corresponding power generation unit to obtain the predicted amount of the resource operation load demand corresponding to each power generation unit.

[0127] In the embodiments of the present invention, by combining the energy generation power of each power generation unit obtained by the previous statistical analysis and the charging and discharging operation state data of the energy storage device, a prediction analysis on the resource operation load demand of the corresponding power generation unit is performed. This step is implemented by constructing a load prediction model (such as machine learning algorithms like linear regression and support vector machine). The input data includes the generation power, the operation state data of the energy storage device, and other relevant meteorological data. The model will analyze the time-series characteristics of the data and predict the resource operation load demand of each power generation unit in the future period, and finally obtain the predicted amount of the resource operation load demand corresponding to each power generation unit.

[0128] Further, step S22 includes the following steps:

[0129] Visualize the power generation power fluctuations of the energy storage devices corresponding to the power generation units in the virtual power plant based on the characteristics of the power generation power fluctuations of each power generation unit in different time periods, and obtain the power generation power fluctuation change curves of the energy storage devices corresponding to each power generation unit;

[0130] In the embodiment of the present invention, by combining the characteristics of the power generation power fluctuations of each power generation unit in different time periods obtained through previous statistical analysis, the power generation power fluctuations of the energy storage devices in the virtual power plant are visualized by using a data visualization tool. Real-time power generation power data of each power generation unit in a certain time period are obtained through a data acquisition system and stored in a database. Then, data processing is performed using data analysis software (such as Python combined with the Pandas and Matplotlib libraries). By writing a program, the change trend of the power generation power is analyzed, and the power generation power fluctuation change curves of each power generation unit are drawn. These curves not only show the change of the power generation power of each power generation unit over time, but also help identify the peaks and valleys of the power generation power, and finally obtain the power generation power fluctuation change curves of the energy storage devices corresponding to each power generation unit.

[0131] Preferably, identify and divide the operation demand time periods for the power generation power fluctuation change curves of the energy storage devices corresponding to each power generation unit. If the power generation power fluctuation change frequency continuously increases in the time periods before and after the occurrence of the power generation power fluctuation peak in the power generation power fluctuation change curve, then divide the time period into a charging demand operation time period to obtain the charging demand operation time periods of the energy storage devices corresponding to each power generation unit;

[0132] In the embodiment of the present invention, by identifying and dividing the operation demand time periods for the previously generated power generation power fluctuation change curves, an algorithm is set to analyze the power generation power fluctuation peaks in the curves, determine the time points of the peaks and the time periods before and after them, calculate the power generation power fluctuation change frequency in these time periods, and judge whether it continuously increases. If the power generation power fluctuation frequency in the time periods before and after the peak significantly increases, then mark these time periods as the charging demand operation time periods. In specific implementation, a signal processing tool can be used for frequency analysis, mathematical methods such as Fourier transform are used to extract the characteristic frequencies, and combined with a set threshold for determination, and finally the charging demand operation time periods of the energy storage devices corresponding to each power generation unit are identified and divided.

[0133] Preferably, if the power generation power fluctuation change frequency continuously decreases in the time periods before and after the occurrence of the power generation power fluctuation valley in the power generation power fluctuation change curve, then divide the time period into a discharging demand operation time period to obtain the discharging demand operation time periods of the energy storage devices corresponding to each power generation unit.

[0134] In the embodiment of the present invention, by analyzing the trough value in the power generation power fluctuation curve, the time point of the trough value and the time periods before and after it are determined. By evaluating whether the power generation power fluctuation frequency continuously decreases during these time periods, it is judged whether the time period conforms to the characteristics of the discharge demand. If the fluctuation frequency of the power generation power continuously decreases during the time periods before and after the trough value, it is marked as the discharge demand operation time period. In this step, a statistical analysis software is used to perform a regression analysis on the fluctuation change trend, determine the specific parameters of the time period, and generate a detailed report on the discharge demand time period, and finally identify and divide the discharge demand operation time periods corresponding to each power generation unit.

[0135] Further, step S25 includes the following steps:

[0136] Step S251: Based on the energy power generation power corresponding to each power generation unit, perform a power generation power field simulation analysis on the corresponding power generation unit in the virtual power plant to generate a resource operation power generation power simulation field corresponding to each power generation unit;

[0137] In the embodiment of the present invention, by combining the energy power generation power corresponding to each power generation unit obtained from the previous statistical analysis, a simulation analysis of the power change scenario is performed on the corresponding power generation unit, so as to establish a change field space model by using simulation software (such as MATLAB / Simulink or PVSYST), input the characteristic parameters of wind power generation, solar power generation and traditional power generation units and environmental factors. During the simulation process, the influence of different meteorological conditions (such as wind speed, light intensity) on the power generation power is considered, and the power output distribution of each power generation unit under specific conditions is obtained through numerical calculation methods, and finally a resource operation power generation power simulation field corresponding to each power generation unit is simulated and generated.

[0138] Step S252: Perform an analysis on the influence of the power generation power load demand on the resource operation power generation power simulation field corresponding to each power generation unit to obtain the influence factor of the power generation power operation load demand corresponding to each power generation unit;

[0139] In the embodiment of the present invention, after the power generation power simulation field is generated, an analysis on the influence of the power output of each power generation unit on the load demand is performed, so as to perform a cross-analysis on the historical load data and the power generation power data obtained by simulation by using statistical analysis tools (such as the pandas and numpy libraries in Python), calculate the power response coefficients of different power generation units under different load conditions, and determine the influence factor of the power generation power operation load demand of each power generation unit by constructing a regression model. The specific steps include data cleaning, feature extraction and model fitting, so as to obtain the demand response characteristics of the power output of the power generation unit, and finally obtain the influence factor of the power generation power operation load demand corresponding to each power generation unit.

[0140] Step S253: Based on the charge-discharge operation status data of the energy storage devices corresponding to each power generation unit, perform charge-discharge state field simulation analysis on the corresponding power generation units in the virtual power plant, and generate a resource operation charge-discharge state simulation field corresponding to each power generation unit.

[0141] In the embodiment of the present invention, by combining the charge-discharge operation status data of the energy storage devices corresponding to each power generation unit obtained from the previous analysis, perform simulation analysis on the charge-discharge state change scenarios of the corresponding power generation units, so as to collect the charging and discharging historical records of the energy storage devices of each power generation unit, and use simulation tools (such as ANSYS or OpenDSS) to construct a dynamic model of the energy storage system, input relevant parameters such as current, voltage, and the efficiency of the energy storage device, simulate the charge-discharge state of the energy storage device under different operating conditions, and consider the external load change and the real-time fluctuation of the power generation power during the analysis process, obtain the charge-discharge state field corresponding to each power generation unit, thereby revealing the operating efficiency and response ability of the energy storage device, and finally generate a resource operation charge-discharge state simulation field corresponding to each power generation unit.

[0142] Step S254: Perform an impact analysis on the charge-discharge load demand of the resource operation charge-discharge state simulation field corresponding to each power generation unit, and obtain the charge-discharge operation load demand impact factor corresponding to each power generation unit.

[0143] In the embodiment of the present invention, after completing the simulation of the charge-discharge state field, carry out an impact assessment analysis of the charge-discharge load demand, so as to deeply analyze the charge-discharge simulation results by using a time series analysis tool, combine the load demand model, consider the influence of external factors (such as electricity price, market demand) on the charge-discharge state, set the load demand threshold and charge-discharge strategy, calculate the charge-discharge operation load demand impact factor of each power generation unit under a specific load demand, form a quantitative description of the charge-discharge behavior of the energy storage device, and finally obtain the charge-discharge operation load demand impact factor corresponding to each power generation unit.

[0144] Step S255: Based on the power generation power operation load demand impact factor and the charge-discharge operation load demand impact factor corresponding to each power generation unit, use the resource operation load demand calculation formula to perform load demand prediction calculation on the corresponding power generation units in the virtual power plant, and obtain the resource operation load demand prediction quantity corresponding to each power generation unit.

[0145] In the embodiment of the present invention, by combining time variable parameters, energy power generation, power generation efficiency factor of the power generation unit, influence factor of power generation power operation load demand, charge and discharge operation state of the energy storage device, charge and discharge efficiency factor of the energy storage device, influence factor of charge and discharge operation load demand of the energy storage, resource operation load demand attenuation factor, resource operation load demand time delay effect factor, and related parameters, a suitable resource operation load demand calculation formula is constructed to perform load demand prediction calculation on the corresponding power generation units in the virtual power plant, so as to integrate the power demand of each power generation unit and the charge and discharge demand of the energy storage device, predict the future load demand, obtain the predicted load demand of each power generation unit, and finally obtain the predicted resource operation load demand corresponding to each power generation unit.

[0146] Further, the resource operation load demand calculation formula described in step S255 is specifically:

[0147]

[0148] In the formula, L i is the predicted value of the resource operation load demand corresponding to the i-th power generation unit, n is the total number of power generation units in the virtual power plant, i is the item measurement parameter of the power generation unit, t is the time variable parameter, τ is the integral time variable parameter, P i (t) is the energy power generation of the i-th power generation unit at time t, η P is the power generation efficiency factor of the power generation unit, f i (t) is the influence factor of the power generation power operation load demand of the i-th power generation unit at time t, E i (t) is the charge and discharge operation state of the energy storage device of the i-th power generation unit at time t, η E is the charge and discharge efficiency factor of the energy storage device, g i (t) is the influence factor of the charge and discharge operation load demand of the energy storage of the i-th power generation unit at time t, λ is the resource operation load demand attenuation factor, L(τ) is the resource operation load demand time delay effect factor at time τ, and ξ is the correction coefficient of the predicted value of the resource operation load demand.

[0149] The present invention obtains a resource operation load demand calculation formula through the use of a specific mathematical model and verification, which is used to perform load demand prediction calculation on the corresponding power generation units in the virtual power plant. P i (t) in the resource operation load demand calculation formula represents the energy power generation of the i-th power generation unit at time t, reflecting the current power generation capacity of the power generation unit; η P represents the power generation efficiency factor of the power generation unit, reflecting the ratio between the actual power generation and the theoretical power generation; f i(t) represents the influencing factor of power generation power operation load demand, reflecting the impact degree of load demand on power generation power, which may vary with time; E i (t) represents the charge and discharge state of the energy storage device of the i-th power generation unit at time t, indicating whether the energy storage device is charging or discharging; η E represents the charge and discharge efficiency factor of the energy storage device, referring to the proportion of energy loss during the charging or discharging process; g i (t) represents the influencing factor of energy storage charge and discharge operation load demand, reflecting the impact degree of energy storage operation state on load demand; λ represents the resource operation load demand attenuation factor, reflecting the attenuation speed of load demand; L(τ) represents the resource operation load demand time delay effect factor at time τ, considering the influence of historical load demand on the current load. This calculation formula can reflect the operation state of each power generation unit and the change of external load demand in real time by combining the above parameters, enabling the virtual power plant to quickly adjust the power generation strategy and optimize the power supply. By considering factors such as power generation efficiency, energy storage state, and time delay, the accuracy of load demand prediction can be significantly improved, thereby enhancing the reliability of the power system. Using the load demand prediction results, the virtual power plant can optimize resource allocation, reasonably arrange the operation of power generation and energy storage devices, reduce waste, and improve economic benefits. At the same time, by introducing the time delay effect of historical load demand, the dynamic characteristics of the system can be better captured, and future power dispatching decisions can be optimized. In addition, by introducing the correction coefficient ξ, a certain degree of flexibility can be provided for load demand prediction, enabling it to adapt to uncertain market conditions and user demands. This load demand calculation formula provides strong support for the energy management of the virtual power plant by comprehensively considering various operation states of power generation units, historical influencing factors, and their dynamic changes, which will enhance the flexibility, economy, and sustainability of the virtual power system. Especially in the context of the increasing growth of renewable energy, it has important practical significance. To sum up, this formula fully considers the predicted value L of the resource operation load demand corresponding to the i-th power generation unit i , the total number n of power generation units in the virtual power plant, the item measurement parameter i of the power generation unit, the time variable parameter t, the integral time variable parameter τ, the energy power generation P i (t) of the i-th power generation unit at time t, the power generation efficiency factor η P of the power generation unit, the influencing factor f i (t) of the power generation power operation load demand of the i-th power generation unit at time t, the charge and discharge operation state E i (t) of the energy storage device of the i-th power generation unit at time t, the charge and discharge efficiency factor η E of the energy storage device, the influencing factor g i(t), the resource operation load demand attenuation factor λ, the resource operation load demand time delay effect factor L(τ) at time τ, the correction coefficient ξ of the predicted value of the resource operation load demand, and the predicted value of the resource operation load demand corresponding to the i-th power generation unit L i The mutual correlation relationship among the above parameters constitutes a functional relationship:

[0150]

[0151] This formula can realize the calculation process of predicting the load demand of the corresponding power generation unit in the virtual power plant. At the same time, by introducing the correction coefficient ξ of the predicted value of the resource operation load demand, it can be adjusted according to the error situation in the calculation process, thereby improving the accuracy and applicability of the formula for calculating the resource operation load demand.

[0152] Furthermore, step S3 includes the following steps:

[0153] Step S31: Based on the energy generation power corresponding to each power generation unit and the predicted value of the resource operation load demand, evaluate and analyze the resource allocation potential of each power generation unit in the virtual power plant to obtain the energy resource allocation potential of each power generation unit under specific operation load demand conditions;

[0154] In the embodiment of the present invention, a mathematical model is established by combining the energy generation power corresponding to each power generation unit obtained from previous statistical analysis and the predicted value of the resource operation load demand, and data mining technology is used to analyze the power generation resource allocation potential of each power generation unit in the virtual power plant under different operation load demands. By using linear programming and non-linear programming algorithms, the power generation units under different load demands are evaluated to determine the resource allocation potential of each power generation unit. Specifically, tools such as Python or MATLAB are used to calculate the power generation capacity of each power generation unit under specific load demand conditions by writing algorithm codes, thereby obtaining the corresponding resource allocation potential, and finally obtaining the energy resource allocation potential of each power generation unit under specific operation load demand conditions.

[0155] Step S32: Based on the energy resource allocation potential of each power generation unit under specific operation load demand conditions, analyze the resource allocation constraints of the corresponding power generation unit in the virtual power plant to generate the resource allocation constraint conditions corresponding to each power generation unit;

[0156] In the embodiments of the present invention, by combining the energy resource allocation potential of each power generation unit obtained from the previous evaluation analysis under specific operating load demand conditions, a constraint analysis of the resource allocation for the corresponding power generation unit is carried out to analyze the resource allocation constraint conditions of each power generation unit in the virtual power plant, including factors such as the maximum load, minimum power generation capacity, and fuel supply capacity of the power generation unit, determine the specific limitations of the resource allocation. In the specific implementation process, an optimization algorithm is used to deduce the constraint conditions, ensure that each power generation unit conducts resource allocation within its working range, data can be sorted out with the help of Excel, and the Solver add-in is used to solve the resource allocation constraints of each power generation unit, and finally the resource allocation constraint conditions corresponding to each power generation unit are generated by the constraints.

[0157] Step S33: Based on the resource allocation constraint conditions corresponding to each power generation unit, an analysis of the resource optimization strategy is carried out for the corresponding power generation unit in the virtual power plant to generate a resource allocation optimization strategy corresponding to each power generation unit;

[0158] In the embodiments of the present invention, by combining the previously analyzed resource allocation constraint conditions, an optimization analysis of the resource optimization strategy is carried out for the corresponding power generation unit in the virtual power plant, so as to generate a resource allocation optimization strategy for each power generation unit by using a genetic algorithm, a simulated annealing algorithm or other optimization algorithms. In the specific implementation, an objective function is constructed, such as minimizing the power generation cost or maximizing the economic benefit, and the power generation power of each power generation unit is continuously adjusted through an iterative algorithm to meet the resource allocation constraint conditions. The generation process of the resource optimization strategy is realized by MATLAB programming to ensure the effectiveness and feasibility of the resource allocation scheme, and finally a resource allocation optimization strategy corresponding to each power generation unit is generated.

[0159] Step S34: Based on the resource allocation optimization strategy corresponding to each power generation unit, an analysis of the resource allocation optimization target is carried out for the corresponding power generation unit in the virtual power plant to obtain the resource allocation optimization target of the power generation unit in the virtual power plant.

[0160] In the embodiments of the present invention, by combining the previously generated resource allocation optimization strategies corresponding to each power generation unit, an identification analysis of the resource allocation optimization target is carried out for the corresponding power generation unit to set specific optimization targets, such as reducing the power generation cost and improving the operation efficiency. Using a data analysis tool, combined with historical data and optimization results, a quantitative analysis of the resource allocation optimization target of each power generation unit is carried out. In the specific implementation, statistical software is used for data regression analysis to generate an evaluation report of the optimization target to provide a clear optimization direction and basis, provide reliable decision-making support for the resource optimization allocation method of the virtual power plant, and finally obtain the resource allocation optimization target of the power generation unit in the virtual power plant.

[0161] Furthermore, the present invention also provides a virtual power plant resource optimization configuration system for implementing the virtual power plant resource optimization configuration method as described above. The virtual power plant resource optimization configuration system includes:

[0162] A power generation power prediction module for virtual power plant sub-units, which is used to obtain the energy load storage resource data corresponding to each power generation unit in the virtual power plant, and perform power generation power prediction analysis on each power generation unit in the virtual power plant based on the energy load storage resource data corresponding to each power generation unit, so as to obtain the energy power generation power corresponding to each power generation unit;

[0163] A sub-unit resource load demand analysis module, which is used to perform charge and discharge state analysis of energy storage devices for each power generation unit in the virtual power plant based on the energy power generation power corresponding to each power generation unit, so as to obtain the charge and discharge operation state data of the energy storage devices corresponding to each power generation unit; perform resource operation load demand prediction analysis on the corresponding power generation unit based on the energy power generation power corresponding to each power generation unit and the charge and discharge operation state data of the energy storage devices, so as to obtain the predicted amount of resource operation load demand corresponding to each power generation unit;

[0164] A virtual power plant resource configuration optimization target analysis module, which is used to perform resource configuration optimization target analysis on each power generation unit in the virtual power plant based on the energy power generation power corresponding to each power generation unit and the predicted amount of resource operation load demand, so as to obtain the virtual power plant power generation unit resource configuration optimization target;

[0165] A resource configuration optimization output module, which is used to perform resource optimization configuration processing on each power generation unit in the virtual power plant according to the virtual power plant power generation unit resource configuration optimization target, so as to generate an optimal resource configuration plan for the virtual power plant power generation unit.

[0166] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0167] The above are only specific embodiments of the present invention, which enable those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A virtual power plant resource optimization configuration method, characterized in that: The following steps are involved: Step S1: Obtain energy load storage resource data corresponding to each power generation unit in the virtual power plant, and perform power generation prediction analysis on each power generation unit in the virtual power plant based on the energy load storage resource data corresponding to each power generation unit to obtain the energy power generation corresponding to each power generation unit; Step S2: Based on the energy generation power corresponding to each power generation unit, the energy storage device charging and discharging status analysis is performed on each power generation unit in the virtual power plant to obtain the energy storage device charging and discharging operation status data corresponding to each power generation unit; based on the energy generation power corresponding to each power generation unit and the energy storage device charging and discharging operation status data, the corresponding power generation unit is subjected to resource operation load demand forecasting analysis to obtain the resource operation load demand forecast amount corresponding to each power generation unit. Step S2 includes the following steps: Step S21: Analyze the time period fluctuation characteristics of the energy power generation corresponding to each power generation unit to obtain the power generation fluctuation characteristics of each power generation unit in different time periods, wherein the power generation fluctuation characteristics include the power generation fluctuation peak value, the power generation fluctuation valley value and the power generation fluctuation frequency; Step S22: Based on the power fluctuation characteristics of each power generation unit in different time periods, the energy storage equipment corresponding to the power generation unit in the virtual power plant is identified and divided into operation demand time periods, so as to obtain the energy storage equipment charging demand operation time periods and energy storage equipment discharging demand operation time periods corresponding to each power generation unit. Step S22 includes the following steps: Based on the power fluctuation characteristics of each power generation unit in different time periods, the power generation fluctuation of the energy storage equipment corresponding to the power generation unit in the virtual power plant is visualized to obtain the power generation fluctuation curve of the energy storage equipment corresponding to each power generation unit; The power generation fluctuation change curve corresponding to the energy storage device of each power generation unit is identified and divided into operation demand time periods. If the power generation fluctuation change frequency continues to rise in the time period before and after the power generation fluctuation peak in the power generation fluctuation change curve, the time period is identified and divided into the charging demand operation period, so as to obtain the charging demand operation period of the energy storage device corresponding to each power generation unit; If the power generation fluctuation frequency continues to decrease in the time period before and after the power generation fluctuation valley value appears in the power generation fluctuation change curve, then the time period is identified and divided into the discharge demand operation period to obtain the energy storage device discharge demand operation period corresponding to each power generation unit; Step S23: Designing charging and discharging strategies for energy storage devices corresponding to power generation units in the virtual power plant based on the charging demand operation period of energy storage devices corresponding to each power generation unit and the discharging demand operation period of energy storage devices, so as to generate a sequential charging and discharging strategy for energy storage devices corresponding to each power generation unit; Step S24: analyzing the energy storage device charging and discharging status of each power generation unit in the virtual power plant according to the energy storage device timing charging and discharging strategy corresponding to each power generation unit, so as to obtain the energy storage device charging and discharging operation status data corresponding to each power generation unit; Step S25: Based on the energy generation power corresponding to each power generation unit and the charging and discharging operation status data of the energy storage device, a resource operation load demand forecast analysis is performed on the corresponding power generation unit to obtain the resource operation load demand forecast amount corresponding to each power generation unit; Step S3: Analyze the resource allocation optimization target of each power generation unit in the virtual power plant based on the energy generation power corresponding to each power generation unit and the resource operation load demand forecast, and obtain the resource allocation optimization target of the virtual power plant power generation unit; Step S4: performing resource optimization configuration processing on each power generation unit in the virtual power plant according to the resource configuration optimization target of the virtual power plant power generation unit to generate an optimal resource configuration plan for the virtual power plant power generation unit.

2. The virtual power plant resource optimization configuration method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire energy storage resource data corresponding to each power generation unit in the virtual power plant; Step S12: Obtain the energy resource input and energy resource output corresponding to each power generation unit through the energy load storage resource data corresponding to each power generation unit, and monitor the power generation of each power generation unit in the virtual power plant in real time through the integrated smart meter to obtain the energy resource power generation corresponding to each power generation unit; perform power generation capacity estimation analysis on the corresponding energy resource power generation based on the energy resource input and energy resource output corresponding to each power generation unit to obtain the energy power generation capacity estimation corresponding to each power generation unit; Step S13: Acquire the meteorological change data of the virtual power plant, and perform seasonal change characteristic analysis on the meteorological change data of the virtual power plant to obtain the meteorological seasonal change characteristic data of the virtual power plant; Step S14: performing environmental impact correction calculation on the estimated energy generation capacity corresponding to each power generation unit based on the virtual power plant meteorological seasonal variation characteristic data, and obtaining the corrected estimated actual generation capacity corresponding to each power generation unit; Step S15: Perform power generation prediction analysis on the corresponding power generation units in the virtual power plant according to the actual power generation capacity correction estimate corresponding to each power generation unit, and obtain the energy power generation corresponding to each power generation unit.

3. The virtual power plant resource optimization configuration method according to claim 2, characterized in that: The power generation capacity estimation analysis of the corresponding energy resource power generation based on the energy resource input and energy resource output corresponding to each power generation unit in step S12 includes the following steps: Performing time-series synchronization processing on the energy resource input and energy resource output corresponding to each power generation unit to obtain the time-series change of resource input and the time-series change of resource output corresponding to each power generation unit; Extract the time-series point input quantity of the resource input time-series change quantity corresponding to each power generation unit to obtain the resource input quantity corresponding to each time-series point of each power generation unit; calculate the input fluctuation difference between time-series points for the resource input quantity corresponding to each power generation unit at each time-series point to obtain the resource input change fluctuation difference between each adjacent time-series point of each power generation unit; The resource input change gradient analysis is performed on the resource input change fluctuation difference between each adjacent time sequence point corresponding to each power generation unit to obtain the resource input change gradient corresponding to each power generation unit; The resource output efficiency is evaluated and analyzed for the time series variation of resource output corresponding to each power generation unit to obtain the resource output efficiency corresponding to each power generation unit; Based on the resource input change gradient and resource output efficiency of each power generation unit, the corresponding energy resource power generation is estimated and analyzed to obtain the energy power generation capacity estimate of each power generation unit.

4. The virtual power plant resource optimization configuration method according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: Based on the seasonal variation characteristics of each meteorological factor in the virtual power plant meteorological seasonal variation characteristic data, an environmental impact factor identification analysis is performed on the estimated energy generation capacity corresponding to each power generation unit to obtain the environmental impact factor of the energy generation capacity corresponding to each power generation unit; Step S142: quantifying the environmental impact coefficient of the energy generation capacity environmental impact factor corresponding to each power generation unit to obtain the power generation capacity impact correction coefficient of each power generation unit corresponding to the environmental impact factor; Step S143: performing environmental impact correction calculation on the energy power generation capacity estimate corresponding to each power generation unit based on the power generation capacity impact correction coefficient of the environmental impact factor corresponding to each power generation unit, and obtaining the actual power generation capacity correction estimate corresponding to each power generation unit.

5. The method for optimizing resource configuration of a virtual power plant according to claim 1, characterized in that: Step S25 includes the following steps: Step S251: Based on the energy generation power corresponding to each generation unit, a power generation field simulation analysis is performed on the corresponding generation unit in the virtual power plant to generate a resource operation power generation simulation field corresponding to each generation unit; Step S252: Perform power generation load demand impact analysis on the resource operation power generation power simulation field corresponding to each power generation unit to obtain the power generation load demand impact factor corresponding to each power generation unit; Step S253: Based on the charge and discharge operation status data of the energy storage device corresponding to each power generation unit, a charge and discharge state field simulation analysis is performed on the corresponding power generation unit in the virtual power plant to generate a resource operation charge and discharge state simulation field corresponding to each power generation unit; Step S254: performing a charge and discharge load demand impact analysis on the resource operation charge and discharge state simulation field corresponding to each power generation unit, and obtaining an energy storage charge and discharge operation load demand impact factor corresponding to each power generation unit; Step S255: Based on the power generation operation load demand influencing factors corresponding to each power generation unit and the energy storage charging and discharging operation load demand influencing factors, the resource operation load demand calculation formula is used to perform load demand forecasting calculations on the corresponding power generation units in the virtual power plant to obtain the resource operation load demand forecast corresponding to each power generation unit.

6. The method for optimizing resource configuration of a virtual power plant according to claim 5, characterized in that: The resource operation load demand calculation formula described in step S255 is specifically: ； In the formula, For the The resource operation load demand forecast corresponding to each power generation unit, is the total number of power generation units in the virtual power plant, is the item measurement parameter of the power generation unit, is the time variable parameter, is the integral time variable parameter, For the The power generation unit at time Energy generation power at is the power generation efficiency factor of the power generation unit, For the The power generation unit at time The influencing factors of the power generation load demand at the location are: For the The power generation unit at time The charging and discharging operation status of the energy storage equipment at is the charging and discharging efficiency factor of the energy storage device, For the The power generation unit at time The influencing factors of energy storage charging and discharging operation load demand at is the resource operation load demand attenuation factor, For in time The resource operation load demand time delay effect factor at The correction factor for the resource operating load demand forecast.

7. The method for optimizing resource configuration of a virtual power plant according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Based on the energy generation power corresponding to each power generation unit and the resource operation load demand forecast, the resource allocation potential of each power generation unit in the virtual power plant is evaluated and analyzed to obtain the energy resource allocation potential of each power generation unit under specific operation load demand conditions; Step S32: performing resource configuration constraint analysis on the corresponding power generation units in the virtual power plant based on the energy resource configuration potential of each power generation unit under specific operating load demand conditions, so as to generate resource configuration constraint conditions corresponding to each power generation unit; Step S33: performing resource optimization strategy analysis on the corresponding power generation units in the virtual power plant based on the resource configuration constraint conditions corresponding to each power generation unit, so as to generate a resource configuration optimization strategy corresponding to each power generation unit; Step S34: According to the resource allocation optimization strategy corresponding to each power generation unit, the resource allocation optimization target analysis is performed on the corresponding power generation unit in the virtual power plant to obtain the resource allocation optimization target of the power generation unit of the virtual power plant.

8. A virtual power plant resource optimization configuration system, characterized in that: Used to execute the virtual power plant resource optimization configuration method according to claim 1, the virtual power plant resource optimization configuration system comprises: The virtual power plant sub-unit power generation prediction module is used to obtain the energy load storage resource data corresponding to each power generation unit in the virtual power plant, and perform power generation prediction analysis on each power generation unit in the virtual power plant based on the energy load storage resource data corresponding to each power generation unit, so as to obtain the energy power generation corresponding to each power generation unit; The sub-unit resource load demand analysis module is used to analyze the charging and discharging status of the energy storage equipment of each power generation unit in the virtual power plant based on the energy generation power corresponding to each power generation unit, so as to obtain the charging and discharging operation status data of the energy storage equipment corresponding to each power generation unit; based on the energy generation power corresponding to each power generation unit and the charging and discharging operation status data of the energy storage equipment, the corresponding power generation unit is predicted and analyzed for the resource operation load demand, so as to obtain the predicted amount of resource operation load demand corresponding to each power generation unit; The virtual power plant resource allocation optimization target analysis module is used to analyze the resource allocation optimization target of each power generation unit in the virtual power plant based on the energy generation power corresponding to each power generation unit and the resource operation load demand forecast, so as to obtain the resource allocation optimization target of the virtual power plant power generation unit; The resource configuration optimization output module is used to perform resource optimization configuration processing on each power generation unit in the virtual power plant according to the resource configuration optimization target of the virtual power plant power generation unit, so as to generate the optimal resource configuration plan for the virtual power plant power generation unit.

Images