A distributed energy scheduling management method and system for a virtual power plant

Abstract

The present invention discloses a distributed energy dispatching management method and system for a virtual power plant, which relates to the technical field of distributed energy management, including collecting electricity price information and operation information, cleaning and preliminarily processing the data to ensure data quality, using machine learning algorithms to predict load information, electricity prices and related energy prices within the virtual power plant, constructing and solving a hybrid optimization model, generating optimal power generation, electricity consumption and energy storage operation plans for different power trading markets, realizing efficient resource allocation, recombining distributed energy units based on operation information data and prediction result data to form the best resource combination for different market transactions, executing a dispatching strategy for optimizing the configuration of resource combinations, and generating a real-time dispatching optimization strategy based on the latest operation status information. The present invention realizes dynamic optimization configuration of distributed energy units through operation information data and prediction result data.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed energy management, and in particular to a distributed energy scheduling management method and system for a virtual power plant. Background Art

[0002] With the application of emerging technologies such as big data, cloud computing and the Internet of Things, the potential of virtual power plants in energy management and scheduling has been further explored. Existing forecasting technologies can estimate future load and market price trends to a certain extent, but their accuracy and timeliness need to be improved. Especially in the face of complex and changeable weather environments, the limitations of such forecasts are particularly obvious.

[0003] Although existing forecasting models can provide load and electricity price forecasts within a certain range, they still have limitations in dealing with complex nonlinear relationships and multivariate influences, especially when dealing with factors such as market fluctuations and weather changes. The forecast accuracy is not high. In addition, existing scheduling strategies mostly use static optimization methods, which are difficult to adapt to the rapidly changing power market environment and cannot achieve real-time scheduling optimization. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a distributed energy scheduling management method and system for a virtual power plant to solve the problems of optimal scheduling and real-time adjustment of distributed energy resources in a virtual power plant.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a distributed energy scheduling management method and system for a virtual power plant, wherein: electricity price information and operation information are collected and the data is pre-processed;

[0008] Build a time series forecasting model to predict load information, electricity prices, and related energy prices within the virtual power plant;

[0009] Build a hybrid optimization model to generate optimal power generation, consumption, and storage operation plans for different power trading markets;

[0010] Based on operational information and forecast results, distributed energy units are reorganized to form resource combinations and data information for different power trading markets;

[0011] Optimize resource allocation to form a scheduling strategy and obtain energy management operation plans based on the latest operating status information;

[0012] Generate real-time scheduling optimization strategies based on energy management operation plans.

[0013] As a preferred solution of the distributed energy dispatching management method and system of the virtual power plant described in the present invention, wherein: the electricity price information includes real-time electricity prices and historical electricity prices, the operation information includes weather data, geographic data, electricity trading market data, log data and historical load of distributed energy units, the weather data includes temperature, humidity and wind speed, the geographic data includes the location and altitude information of the distributed energy units, the log data of the distributed energy units includes power generation, electricity consumption, electricity purchase price and energy storage information, the electricity trading market data includes transaction volume and contract information in transaction records, the collected data are integrated into a unified data platform, and the collected data are preliminarily processed to remove invalid data and handle missing values.

[0014] As a preferred solution of the distributed energy dispatching management method and system of the virtual power plant described in the present invention, a time series prediction model is constructed to predict load information, electricity prices and related energy prices within the scope of the virtual power plant, including the following steps:

[0015] The long short-term memory network is selected as the time series prediction model, and the dataset is divided into training set and test set according to the time window length and split ratio;

[0016] The training set is used to train the time series prediction model, and the test set is used to evaluate the performance of the time series prediction model and verify the generalization ability of the model;

[0017] The comprehensive feature vector is used as the input feature and input into the time series forecasting model for prediction.

[0018] As a preferred solution of the distributed energy scheduling management method and system of the virtual power plant described in the present invention, wherein: constructing a hybrid optimization model to generate the optimal power generation, power consumption and energy storage operation plan for different power trading markets includes the following steps:

[0019] Select maximizing profit as the objective function and construct a hybrid optimization model;

[0020] Set generation capacity, load balancing, and energy storage constraints based on market rules, equipment capabilities, and operational limitations;

[0021] Select linear programming as the algorithm to solve the hybrid optimization model;

[0022] The integrated electricity price information, load demand, power generation capacity and energy storage status data are input into the hybrid optimization model;

[0023] Convert the objective function and constraints into linear form and set the coefficient matrix;

[0024] Use the optimization solver to solve the hybrid optimization model to obtain the optimal solution and obtain the optimal operation plan for power generation, power consumption and energy storage.

[0025] As a preferred solution of the distributed energy dispatching management method and system of the virtual power plant described in the present invention, the distributed energy units are recombined based on the operation information data and the forecast result data to form resource combinations and data information for different market transactions, including the following steps:

[0026] Based on the forecast results of weather data and power generation and consumption data, different types of distributed energy units are classified by function and location to form multiple resource pools, and the resource pool is set as the collection of all distributed energy units;

[0027] Based on the results of the hybrid optimization model, each distributed energy unit is adjusted, the resource pool and optimization objectives are mapped to the optimal output combination, and control instructions are generated and issued to each distributed energy unit to adjust its power generation, consumption and storage status;

[0028] The information in each resource pool is integrated to form resource combinations and data information for different market transactions. As a preferred solution of the distributed energy scheduling management method and system of the virtual power plant described in the present invention, the scheduling strategy is executed by optimizing the configuration of resource combinations, and the energy management operation plan is optimized and adjusted according to the latest operating status information to generate a real-time scheduling optimization strategy, including the following steps:

[0029] Monitor the operating status of distributed energy units in real time and update operational information data;

[0030] Re-run the hybrid optimization model using the updated operational information data to adjust the energy management operation plan; adjust the energy management operation plan based on the updated forecast results and real-time operation status information to generate a real-time scheduling optimization strategy.

[0031] In a second aspect, the present invention provides a distributed energy dispatching and management system for a virtual power plant, comprising:

[0032] The data collection and preprocessing module is responsible for collecting electricity price information and operation information, and cleaning and preliminarily processing the data to ensure data quality;

[0033] Predictive modeling module, which uses machine learning algorithms to predict load information, electricity prices and related energy prices within the virtual power plant, providing a basis for subsequent decision-making;

[0034] Hybrid optimization model module, which builds and solves hybrid optimization models to generate optimal power generation, power consumption, and energy storage operation plans for different power trading markets, achieving efficient resource allocation;

[0035] The resource reorganization module recombines distributed energy units based on operational information data and forecast results data to form the best resource combination for different market transactions;

[0036] The real-time scheduling and optimization module executes the scheduling strategy of optimizing the configuration of resource combinations, continuously optimizes and adjusts the energy management operation plan based on the latest operating status information, and generates a real-time scheduling optimization strategy.

[0037] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the distributed energy dispatching and management method and system for a virtual power plant as described in the first aspect of the present invention.

[0038] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, it implements any step of the distributed energy dispatching management method and system for a virtual power plant as described in the first aspect of the present invention.

[0039] The beneficial effects of the present invention are as follows: by collecting electricity price information and operation information and performing preliminary processing on the data, the data quality is improved, laying the foundation for subsequent analysis; by constructing a time series prediction model, the load information, electricity price and related energy prices within the virtual power plant are predicted, so as to achieve accurate prediction of future energy supply and demand conditions; by constructing a hybrid optimization model, the optimal power generation, power consumption and energy storage operation plans for different power trading markets are generated, and the purpose of seeking the optimal solution under multiple constraints is achieved, thereby reducing operating costs; by recombining distributed energy units based on operation information data and prediction result data, dynamic optimization configuration of distributed energy units is achieved; the output combination of each distributed energy unit is adjusted according to the prediction results of weather data and power generation and consumption data, thereby enhancing the ability to respond to market changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 This is a flow chart of the distributed energy scheduling and management method of the virtual power plant in Example 1.

[0042] Figure 2 This is a flow chart of the distributed energy dispatching and management system of the virtual power plant in Example 1. DETAILED DESCRIPTION

[0043] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0044] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a distributed energy scheduling management method and system for a virtual power plant, comprising the following steps:

[0045] S1. Collect electricity price information and operation information and pre-process the data;

[0046] Among them, electricity price information includes real-time electricity prices and historical electricity prices; operational information includes weather data, geographic data, electricity market data, distributed energy unit log data and historical load; weather data includes temperature, humidity and wind speed; geographic data includes the location and altitude information of distributed energy units; distributed energy unit log data includes power generation, power consumption, power purchase price and energy storage information; electricity market data includes transaction volume and contract information in transaction records;

[0047] Furthermore, electricity price information is collected. Real-time electricity price data is updated every 15 minutes, reflecting the current electricity market demand. Historical electricity price data covers the daily average electricity price over the past year. By comparing real-time electricity prices with historical prices, we can gain insight into market price fluctuation patterns.

[0048] Comprehensive operational information is collected, and weather data is updated hourly to better coordinate resource allocation within the region;

[0049] Electricity market data includes transaction volume and contract information from trading records. Transaction volume data reflects the level of electricity trading activity in the market, while contract information provides details about long-term supply agreements, playing an important role in formulating long-term energy management strategies.

[0050] Log data from distributed energy units, which is updated hourly and reflects the actual operating status of distributed energy units. Energy storage information helps assess the charge and discharge status of energy storage devices.

[0051] After all data is collected, it is integrated into a unified data platform to query and process data from different sources;

[0052] Invalid data was removed from the collected data. All data were checked and data outside the normal range was deleted to ensure the authenticity and reliability of the data. Missing values were then processed and filled with interpolation to avoid analytical bias caused by missing data and ensure the data quality for subsequent analysis and modeling.

[0053] S2. Build a time series prediction model to predict load information, electricity prices, and related energy prices within the virtual power plant, including the following steps:

[0054] The long short-term memory network is selected as the time series prediction model, and the dataset is divided into training set and test set according to the time window length and split ratio;

[0055] The training set is used to train the time series prediction model, and the test set is used to evaluate the performance of the time series prediction model and verify the generalization ability of the model;

[0056] Use the comprehensive feature vector as the input feature and input it into the time series prediction model for prediction. The formula is:

[0057]

[0058] Among them, Y is the predicted value, q is the number of model parameters, g l (X l ) is the nonlinear value of the lth parameter, λ is the attenuation factor, t is the current time, t0 is the start time, x is the target variable, μ is the mean of the target variable, σ is the standard deviation of the target variable, and T is the time span.

[0059] S3. Build a hybrid optimization model to generate optimal power generation, power consumption, and energy storage operation plans for different power trading markets, including the following steps:

[0060] We choose maximizing profit as the objective function and build a hybrid optimization model. The formula is:

[0061]

[0062] Among them, π is the total profit, P m is the electricity price in the mth market, Q m is the electricity sold in the mth market, C m (Q m ) is the sales volume Q in the mth market m The cost of electricity, N is the number of energy storage devices, C f,n is the fixed operating cost of the nth energy storage device;

[0063] Set generation capacity, load balancing, and energy storage constraints based on market rules, equipment capabilities, and operational limitations;

[0064] Select linear programming as the algorithm to solve the hybrid optimization model;

[0065] The integrated electricity price information, load demand, power generation capacity and energy storage status data are input into the optimization model;

[0066] Convert the objective function and constraints into linear form and set the coefficient matrix;

[0067] The optimization solver is used to solve the hybrid optimization model to obtain the optimal solution and obtain the optimal operation plan for power generation, consumption and energy storage status.

[0068] According to the above objective function, a mixed integer nonlinear programming model is constructed, which includes the following constraints:

[0069] Power generation limit, power generation P g (t) The maximum power generation capacity P shall not be exceeded mg ;

[0070] 0≤P g (t)≤P mg ;

[0071] Power consumption limit, power consumption P l (t) The maximum power consumption P shall not be exceeded ml ;

[0072] 0≤P l (t)≤P ml

[0073] Energy storage state limit, energy storage state P s (t) The maximum energy storage capacity E shall not be exceeded me ;

[0074] 0≤E e (t)≤E me

[0075] Energy conservation, the change of energy storage state is determined by power generation and power consumption;

[0076] E e (t) = E e (t-1)+P g (t)-P l (t);

[0077] Use the optimization solver to solve the hybrid optimization model to obtain the optimal solution and obtain the optimal operation plan for power generation, consumption and energy storage status;

[0078] Set the initial energy storage state to 0 and initialize other variables. Input the optimization model into the optimization solver. The solver searches for the optimal solution that minimizes the total cost while satisfying all constraints. The solver outputs the optimal operation plan for power generation, power consumption, and energy storage state, and obtains the solution result.

[0079] Based on the solution results, the optimal power generation, power consumption and energy storage operation plans for different power trading markets are generated.

[0080] According to P g The optimal solution of (t) generates the optimal operation plan for power generation;

[0081] According to P l The optimal solution of (t) generates the optimal operation plan of power consumption;

[0082] According to E me The optimal solution of ,generates the optimal operation plan of energy storage state.

[0083] S4, based on the operation information data and the forecast result data, recombining the distributed energy units to form resource combinations and data information for different market transactions, including the following steps:

[0084] Based on the forecast results of weather data and power generation and consumption data, different types of distributed energy units are classified by function and location to form multiple resource pools, and the resource pool is set as the collection of all distributed energy units;

[0085] Distributed energy units are classified according to their main functions:

[0086] Solar photovoltaic panels, whose main function is to generate electricity;

[0087] Wind turbines, whose main function is to generate electricity;

[0088] Energy storage device, whose main function is to store and release electrical energy;

[0089] Demand response loads, whose main function is to adjust electricity consumption in response to market price changes;

[0090] Distributed energy units are classified according to their primary location:

[0091] The central area of a city usually has a high load and large electricity demand;

[0092] Suburban areas, which generally have lower loads and more renewable energy facilities;

[0093] In rural areas, where loads are generally lower, renewable energy facilities may be more dispersed;

[0094] Based on the results of the hybrid optimization model, each distributed energy unit is adjusted, the resource pool and optimization objectives are mapped to the optimal output combination, and control instructions are generated and issued to each distributed energy unit to adjust its power generation and consumption;

[0095] Integrate the information in each resource pool to form resource combinations and data information for different market transactions.

[0096] S5. Utilize the optimized resource configuration combination to execute the scheduling strategy, optimize and adjust the energy management operation plan according to the latest operation status information, and generate a real-time scheduling optimization strategy, including the following steps:

[0097] Monitor the operating status of distributed energy units in real time and update operational information data;

[0098] Re-run the hybrid optimization model using the updated operational information data to adjust the energy management operation plan; adjust the energy management operation plan based on the updated forecast results and real-time operational status information to generate a real-time scheduling optimization strategy;

[0099] This embodiment also provides a distributed energy dispatching and management system for a virtual power plant, including: a data collection and preprocessing module, which is responsible for collecting electricity price information and operation information, and cleaning and preliminarily processing the data to ensure data quality.

[0100] Predictive modeling module, which uses machine learning algorithms to predict load information, electricity prices and related energy prices within the virtual power plant, providing a basis for subsequent decision-making;

[0101] Hybrid optimization model module, which builds and solves hybrid optimization models to generate optimal power generation, power consumption, and energy storage operation plans for different power trading markets, achieving efficient resource allocation;

[0102] The resource reorganization module recombines distributed energy units based on operation information data and forecast result data to form the best resource combination for different market transactions.

[0103] This embodiment also provides a computer device, which is suitable for the distributed energy scheduling and management method and system of a virtual power plant, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the distributed energy scheduling and management method and system of a virtual power plant proposed in the above embodiment.

[0104] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WI FI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0105] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the distributed energy dispatching and management method and system for implementing a virtual power plant as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0106] In summary, the present invention improves data quality by: collecting electricity price information and operation information, and performing preliminary processing on the data, thereby laying the foundation for subsequent analysis; utilizing the construction of a time series prediction model to predict load information, electricity prices and related energy prices within the virtual power plant, thereby achieving accurate predictions of future energy supply and demand conditions; constructing a hybrid optimization model to generate optimal power generation, power consumption and energy storage operation plans for different power trading markets, thereby seeking the optimal solution under multiple constraints and reducing operating costs; and recombining distributed energy units based on operation information data and prediction result data to achieve dynamic optimization configuration of distributed energy units; adjusting the output combination of each distributed energy unit according to the prediction results of weather data and power generation and consumption data, thereby enhancing the ability to respond to market changes.

[0107] Example 2, referring to Table 1, is the second embodiment of the present invention. In order to further verify the technical solution of the present invention, experimental simulation data of the distributed energy scheduling management method and system of the virtual power plant are provided.

[0108] First, the collected data was cleaned and missing values processed to ensure data quality. A prediction model was then constructed using a long-short-term memory network (LSTM) in machine learning to predict load information, electricity prices, and related energy prices within the virtual power plant. When constructing the prediction model, a comprehensive feature vector was used as input to extract features, enhancing the accuracy of the prediction model.

[0109] Based on the prediction results, a mixed integer nonlinear programming model was constructed to optimize the virtual power plant's power generation, power consumption, and energy storage operation plans. The objective function of the model was to minimize the total cost.

[0110] Based on operational information and forecast data, distributed energy units were reorganized to form resource combinations and data information for different market transactions. The output combination of each distributed energy unit was adjusted through the results of the hybrid optimization model, and control instructions were generated and issued to each distributed energy unit to adjust its power generation and consumption.

[0111] By optimizing resource configuration and implementing scheduling strategies, the system optimized and adjusted the energy management operation plan based on the latest operating status information, generating a real-time scheduling optimization strategy. Throughout the entire process, the operating status of distributed energy units was monitored in real time, and operational information was updated based on real-time data, thus ensuring the real-time and effectiveness of the scheduling strategy.

[0112] The details are shown in Table 1 below:

[0113] Table 1 Experimental record table

[0114]

[0115] Data Analysis:

[0116] By comparing the data of the embodiment with those of control groups A and B, it can be seen that the predicted load in the embodiment is very close to the actual load, with an error of only 2 kWh. In control group A, the predicted load differs from the actual load by 20 kWh, and the predicted load of control group B differs from the actual load by 10 kWh. Through the method of the present invention, the prediction model can more accurately predict load information, thereby helping the virtual power plant to better adjust power generation and consumption plans and reduce energy waste or shortages caused by inaccurate predictions.

[0117] In addition, through the optimal power generation, power consumption and energy storage operation plan generated by the hybrid optimization model, the virtual power plant can manage its internal resources more efficiently. In the embodiment, through the optimized scheduling strategy, the virtual power plant saved about 10% of operating costs within a week, while the cost savings of the control groups A and B were 5% and 7% respectively, which proves the superiority of the method of the present invention in improving economic benefits.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A distributed energy scheduling and management method for a virtual power plant, characterized in that: include: S1. Collect electricity price information and operation information and pre-process the data; S2. Build a time series prediction model to predict load information, electricity prices, and related energy prices within the virtual power plant; S3. Build a hybrid optimization model to generate optimal power generation, power consumption, and energy storage operation plans for different power trading markets; S4. Based on operational information and forecast results, regroup distributed energy units to form resource combinations and data information for different power trading markets; S5. Optimize resource configuration to form a scheduling strategy, obtain an energy management operation plan based on the latest operating status information, and generate a real-time scheduling optimization strategy based on the energy management operation plan; In S3, a hybrid optimization model is constructed to generate the optimal power generation, power consumption and energy storage operation plans for different power trading markets, including the following steps: We choose maximizing profit as the objective function and build a hybrid optimization model. The formula is: Among them, π is the total profit, P m is the electricity price in the mth market, Q m is the electricity sold in the mth market, C m (Q m ) is the sales volume Q in the mth market m The cost of electricity, N is the number of energy storage devices, C f,n is the fixed operating cost of the nth energy storage device; Set generation capacity, load balancing, and energy storage constraints based on market rules, equipment capabilities, and operational limitations; Select linear programming as the algorithm to solve the hybrid optimization model; The integrated electricity price information, load demand, power generation capacity and energy storage status data are input into the hybrid optimization model; Convert the objective function and constraints into linear form and set the coefficient matrix; Use the optimization solver to solve the hybrid optimization model to obtain the optimal solution and obtain the optimal operation plan for power generation, power consumption and energy storage; According to the above objective function, a mixed integer nonlinear programming model is constructed, which includes the following constraints: Power generation limit, power generation P g (t) The maximum power generation capacity P shall not be exceeded mg ; 0≤P g (t)≤P mg ; Power consumption limit, power consumption P l (t) The maximum power consumption P shall not be exceeded ml ; 0≤P l (t)≤P ml Energy storage state limit, energy storage state P s (t) The maximum energy storage capacity E shall not be exceeded me ; 0≤E e (t)≤E me Energy conservation, the change of energy storage state is determined by power generation and power consumption; E e (t)=E e (t-1)+P g (t)-P l (t); Use the optimization solver to solve the hybrid optimization model to obtain the optimal solution and obtain the optimal operation plan for power generation, consumption and energy storage status; Set the initial energy storage state to 0 and initialize other variables. Input the optimization model into the optimization solver. The solver searches for the optimal solution that minimizes the total cost while satisfying all constraints. The solver outputs the optimal operation plan for power generation, power consumption, and energy storage state, and obtains the solution result. Based on the solution results, the optimal power generation, power consumption and energy storage operation plans for different power trading markets are generated. According to P g The optimal solution of (t) generates the optimal operation plan for power generation; According to P l The optimal solution of (t) generates the optimal operation plan of power consumption; According to E me The optimal solution of ,generates the optimal operation plan of energy storage state.

2. The distributed energy scheduling and management method for a virtual power plant according to claim 1, wherein: The electricity price information includes real-time electricity prices and historical electricity prices. The operation information includes weather data, geographic data, electricity trading market data, log data of distributed energy units and historical loads. The weather data includes temperature, humidity and wind speed. The geographic data includes the location and altitude information of the distributed energy units. The log data of the distributed energy units includes power generation, electricity consumption, electricity purchase price and energy storage information. The electricity trading market data includes transaction volume and contract information in transaction records. The collected data is integrated into a unified data platform, and the collected data is preliminarily processed to remove invalid data and handle missing values.

3. The distributed energy scheduling and management method for a virtual power plant according to claim 2, wherein: Based on the operation information data and forecast result data, the distributed energy units are recombined to form resource combinations and data information for different market transactions, including the following steps: Based on the forecast results of weather data and power generation and consumption data, different types of distributed energy units are classified by function and location to form multiple resource pools, and the resource pool is set as the collection of all distributed energy units; Based on the results of the hybrid optimization model, each distributed energy unit is adjusted, the resource pool and optimization objectives are mapped to the optimal output combination, and control instructions are generated and issued to each distributed energy unit to adjust its power generation, consumption and storage status; Integrate the information in each resource pool to form resource combinations and data information for different market transactions.

4. The distributed energy scheduling and management method for a virtual power plant according to claim 3, wherein: Utilize the optimized configuration resource combination to execute the scheduling strategy, optimize and adjust the energy management operation plan according to the latest operation status information, and generate real-time scheduling optimization strategy. The following steps are included: Monitor the operating status of distributed energy units in real time and update operational information data; Re-run the hybrid optimization model using updated operational information data to adjust the energy management operation plan; According to the updated forecast results and real-time operation status information, the real-time operation status data of the energy management operation meter is adjusted to generate a real-time scheduling optimization strategy.

5. A distributed energy dispatching and management system for a virtual power plant, based on the distributed energy dispatching and management method for a virtual power plant according to any one of claims 1 to 4, characterized in that: include: The data collection and preprocessing module is responsible for collecting electricity price information and operation information, and cleaning and preliminarily processing the data to ensure data quality; Predictive modeling module, which uses machine learning algorithms to predict load information, electricity prices and related energy prices within the virtual power plant, providing a basis for subsequent decision-making; Hybrid optimization model module, which builds and solves hybrid optimization models to generate optimal power generation, power consumption, and energy storage operation plans for different power trading markets, achieving efficient resource allocation; The resource reorganization module recombines distributed energy units based on operational information data and forecast results data to form the best resource combination for different market transactions; The real-time scheduling and optimization module executes the scheduling strategy of optimizing the configuration of resource combinations, continuously optimizes and adjusts the energy management operation plan based on the latest operating status information, and generates a real-time scheduling optimization strategy.

Images