Virtual power plant optimal scheduling method, system and equipment combined with vehicle network interaction and medium

Abstract

The invention relates to a virtual power plant optimal scheduling method, system and device combined with vehicle network interaction and a medium. And predicting a controllable load power demand, a vehicle network interaction system charging and discharging amount, a traditional power supply generating capacity, an energy storage electric quantity, a distributed power supply generating capacity, a weather condition, a power grid frequency change and greenhouse gas emission in the virtual power plant at the next moment. According to prediction, feature extraction is carried out through a convolutional neural network, and then an attention mechanism is used to obtain prediction results concerning load peak periods and weather change periods. And describing state transfer by adopting a Markov decision process. And obtaining an optimal action based on the deep Q network, determining generator set output, energy storage system charging and discharging, controllable load scheduling and vehicle network charging and discharging scheduling strategies, and adjusting the operation of the power grid in real time. Compared with the prior art, the method has the advantages of low operation and maintenance cost, high stability, environmental protection and the like.

Description

Technical Field

[0001] The present invention relates to a virtual power plant technology system, and in particular to a virtual power plant optimization scheduling method, system, equipment and medium combined with vehicle-grid interaction. Background Art

[0002] The efficiency of the current power grid system is not ideal. On the one hand, the operating cost of the power grid is high; on the other hand, the design and operation mode of the power grid easily lead to energy waste. When the load demand of the power grid fluctuates, the power grid not only needs to adjust the power output, but also needs to continuously adjust the voltage and frequency to ensure the stable operation of the power grid. When the power grid demand exceeds the power generation capacity of the base load power plant, the power grid lacks sufficient energy storage equipment to balance the demand, so it is necessary to start the peak load power plant to meet the peak demand. In some cases, the rotating standby power plant also needs to intervene. When the power grid demand is low, the power generation often exceeds the actual demand, and the unused power will be wasted. In addition, the power grid will also increase additional operating costs in the process of voltage and frequency regulation. Since the power generation of renewable energy, that is, the power generation of distributed power sources, is greatly affected by natural conditions, it is discontinuous and volatile, and it is difficult for the power grid to directly respond to these fluctuations. With the large-scale access of distributed power sources to the power grid system, this problem has become more prominent. Therefore, the key factor for the stable operation of the power grid also includes the effective balancing of the fluctuations of renewable energy. This requires not only timely replenishment of the power generation capacity of the power grid, but also the use of energy storage systems to smooth the fluctuations of renewable energy to ensure the stability of the power grid frequency and avoid problems such as voltage rise caused by reverse power flow. The vehicle-grid interactive system uses two-way energy transmission between charging stations and electric vehicles to achieve coordinated deployment with the power grid. Electric vehicles can input surplus energy into the power grid as renewable energy, balance the power grid load, improve power grid stability, and store renewable energy to reduce energy waste.

[0003] Virtual power plants combine the above-mentioned types of resources. Building virtual power plants on the basis of abundant resources plays an important role and significance in improving system regulation capabilities and alleviating power shortages, and needs to be fully explored and utilized. Therefore, how to optimize power distribution in virtual power plants, improve grid stability, reduce environmental impact, and reduce operating costs are technical issues that need to be solved. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a virtual power plant optimization scheduling method, system, equipment and medium combined with vehicle-grid interaction.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] According to one aspect of the present invention, a virtual power plant optimization scheduling method combining vehicle-grid interaction is provided, characterized in that it includes the following steps:

[0007] Collect historical data to predict the power demand of controllable loads in the virtual power plant at the next moment, the charging and discharging of the vehicle-grid interactive system, the power generation of traditional power sources, the power storage, the power generation of distributed power sources, weather conditions, grid frequency changes, and greenhouse gas emissions; the prediction is performed through feature extraction by convolutional neural networks, and the prediction results focusing on load peak periods and weather change periods are obtained through the attention mechanism;

[0008] Defining a state according to the prediction result to obtain a state space, and using a Markov decision process to describe the state transition;

[0009] The optimal action is obtained based on the deep Q network to determine the output of the generator set, the charging and discharging of the energy storage system, the controllable load scheduling and the vehicle-grid charging and discharging scheduling strategy, and adjust the power grid operation in real time.

[0010] The historical data includes the power regulation of controllable loads, the charging and discharging power of electric vehicles, the status of vehicle batteries, the power generation of traditional power grids, the charging and discharging power of batteries, battery energy storage, the power generation power of distributed power sources, power grid loads, electricity prices, meteorological data, power grid frequency and greenhouse gas emissions.

[0011] After collecting the historical data, constraint condition judgment and preprocessing are performed; the constraint conditions include the balance of total power generation and total load of the power grid, electric vehicle charging and discharging constraints, energy storage capacity limitations, energy storage system charging and discharging power limitations, and power grid frequency range limitations.

[0012] The preprocessed data is input into the convolution layer, and nonlinearly transformed through convolution processing and activation function to obtain the features extracted in time; the attention weight of each time step of the feature is calculated, and the feature of each time step is weighted using the attention weight; the weighted feature is input into the pooling layer to obtain the aggregated feature; the aggregated feature is input into the fully connected layer to obtain the predicted value.

[0013] The state and state transition are described by the Markov decision process, where the state is: S t =[P gen (t), E storage (t), L load (t), C ev (t), D weather (t)], where P gen (t) is the current power generation of distributed power sources and traditional power sources, E storage (t) is the power of the energy storage system, L load (t) is the load demand, C ev (t) is the charge and discharge capacity of the electric vehicle, Dweather (t) is the weather condition; the action space is: a t =[ΔP gen (t), ΔE storage (t), ΔL load (t), ΔC ev (t)], where ΔP gen (t) is the adjusted power generation, ΔE storage (t) is the increment of charging and discharging of the energy storage system, ΔL load (t) is the adjustment amount of the controllable load, ΔC ev (t) is the charging or discharging strategy of the electric vehicle.

[0014] The objective function L includes the operation and maintenance costs of distributed power generation and traditional power generation equipment, environmental protection costs and non-distributed power utilization. The specific expression is:

[0015] min L=αC operation +βC environment +γC efficiency ,

[0016] Among them, α, β and γ are weight coefficients, which adjust the importance of each objective in the overall optimization objective; C operation The operation and maintenance cost of distributed power generation and traditional power generation equipment; C environment Environmental protection cost; C efficiency is the utilization rate of non-distributed power source.

[0017] The reward function R(t) of the deep Q network is:

[0018]

[0019] Among them, λ1, λ2, λ3, λ4 and λ5 are weight parameters; P gen (t) is the current power generation of distributed power sources and traditional power sources; P demand (t) is the load demand; P renew (t) is the power generation of distributed generation; emissions(t) is the greenhouse gas emissions; k1 and k2 are the positive parameters for scaling the objective function L; f(t) is the frequency of the power grid at time t; f ev Historical average frequency of the power grid.

[0020] According to another aspect of the present invention, there is provided a virtual power plant optimization scheduling system combined with vehicle-grid interaction, comprising a distributed power supply module, an energy storage module, a controllable load module, a vehicle-grid interaction module and a communication control module;

[0021] The distributed power supply module is used to generate new energy electricity; the energy storage module is a module used for storing energy during low-peak electricity consumption and discharging energy during peak electricity consumption in power grid dispatch; the controllable load module is an energy-consuming power-consuming device that adjusts the power load according to the operating status of the power grid without affecting the user's power consumption experience; the vehicle-grid interaction module is used to regulate the two-way interaction between electric vehicles and the power grid; the communication control module includes a perception layer, a network layer, a platform layer and an application layer, wherein the perception layer is used to collect historical data, the network layer is used to realize communication between the communication control module and other modules, the platform layer is used to process the data collected by the perception layer and transmitted by the network layer, and generate a strategy for optimizing the scheduling of the virtual power plant; the application layer generates control instructions according to the optimized scheduling strategy generated by the platform layer, and sends them to each module for power scheduling.

[0022] According to a third aspect of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the method described above is implemented when the processor executes the program.

[0023] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program implements the method described when executed by a processor.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] (1) Improved safety and stability of virtual power plants: By constraining the total load balance and grid frequency range, the total power generation in all time periods must meet the load demand, reducing grid frequency fluctuations and improving the stability of the virtual power plant grid. By constraining the charging and discharging power of electric vehicles, energy storage capacity, and the charging and discharging power of the energy storage system, the safety of batteries in electric vehicles and energy storage systems is ensured.

[0026] (2) Reduce environmental pollution: By setting the greenhouse gas emission term in the reward function, the environmental pollution caused by greenhouse gas emissions generated by each module can be reduced while ensuring a stable power supply.

[0027] (3) Make the regulation of virtual power plants more in line with actual working conditions and reduce operation and maintenance costs: By using the attention mechanism to weight the features extracted by the convolutional layer by time step, the input of the optimization scheduling strategy can focus more on key periods, such as peak power consumption and weather changes. At the same time, multiple objectives and reward functions including cost, environmental protection, grid frequency stability and power generation load balance make the scheduling of virtual power plants more in line with actual needs, reducing power waste and unnecessary operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 Flowchart of the optimization scheduling method for virtual power plants combined with vehicle-grid interaction. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] Example 1

[0031] like Figure 1 As shown, a virtual power plant optimization scheduling method combining vehicle-grid interaction is provided, which includes the following steps:

[0032] Collect historical data to predict the power demand of controllable loads in the virtual power plant at the next moment, the charging and discharging of the vehicle-grid interactive system, the power generation of traditional power sources, the power storage, the power generation of distributed power sources, weather conditions, grid frequency changes and greenhouse gas emissions; predict the features through convolutional neural networks, and obtain the prediction results focusing on the peak load period and weather change period through the attention mechanism; define the state according to the prediction results, obtain the state space, and use the Markov decision process to describe the state transition; obtain the optimal action based on the deep Q network, determine the output of the generator set, the charging and discharging of the energy storage system, the controllable load scheduling and the vehicle-grid charging and discharging scheduling strategy, and adjust the grid operation in real time.

[0033] Historical data includes power regulation of controllable loads, charging and discharging power of electric vehicles, vehicle battery status, power generation of traditional power grids, charging and discharging power of batteries, battery energy storage, power generation of distributed power sources, grid load, electricity prices, meteorological data, grid frequency and greenhouse gas emissions.

[0034] After collecting historical data, constraint judgment and preprocessing are performed; preprocessing includes data cleaning, normalization and smoothing. Constraints include the balance of total power generation and total load of the power grid, electric vehicle charging and discharging constraints, energy storage capacity restrictions, energy storage system charging and discharging power restrictions and power grid frequency range restrictions. The total power generation in all time periods meets the load demand, reduces power grid frequency fluctuations, improves the stability of the virtual power plant power grid, and ensures the safety of batteries in electric vehicles and energy storage systems, reduces losses and prolongs their life.

[0035] The total power generation and total load balance constraint expressions of the power grid are:

[0036]

[0037] Among them, P gen (t) is the current power generation of distributed power sources and traditional power sources; P storage(t) is the charging and discharging power of the energy storage system; P load-controlled (t) is the power of the controllable load; P demand (t) is the load demand.

[0038] The constraint expression of electric vehicle charging and discharging is:

[0039]

[0040] Among them, E EV,min E is the minimum charging capacity of the electric vehicle battery; EV,max E is the maximum charge capacity of the electric vehicle battery; EV (t) is the battery capacity of the electric vehicle at time t.

[0041] The energy storage capacity constraint expression is:

[0042]

[0043] Among them, E storage,min E is the minimum charging capacity of the electric vehicle battery; storage,max E is the maximum charge capacity of the electric vehicle battery; storage (t) is the battery capacity of the electric vehicle at time t.

[0044] The charging and discharging power limit constraint expression of the energy storage system is:

[0045]

[0046] Among them, P storage (t) is the battery charge change power of the electric vehicle at time t; P storage,max It is the maximum charge and discharge power of electric vehicle battery.

[0047] The power grid frequency range limit expression is:

[0048]

[0049] Among them, f min is the minimum value allowed by the grid frequency; f max is the maximum value allowed for the grid frequency; f(t) is the frequency of the grid at time t.

[0050] The preprocessed data is input into the convolution layer, and after convolution processing and activation function, nonlinear transformation is performed to obtain the features extracted in time; the attention weight of each time step of the feature is calculated, and the features of each time step are weighted using the attention weight; the weighted features are input into the pooling layer to obtain the aggregated features; the aggregated features are input into the fully connected layer to obtain the predicted values. With the participation of the attention mechanism, the input of the optimized scheduling strategy is more focused on key periods, such as peak power consumption and weather changes.

[0051] The state and state transition are described by the Markov decision process, where the state is: S t =[P gen (t), E storage (t), L load (t), C ev (t), D weather (t)], where P gen (t) is the current power generation of distributed power sources and traditional power sources, E storage (t) is the power of the energy storage system, L load (t) is the load demand, C ev (t) is the charge and discharge capacity of the electric vehicle, D weather (t) is the weather condition; the action space is: a t =[ΔP gen (t), ΔE storage (t), ΔL load (t), ΔC ev (t)], where ΔP gen (t) is the adjusted power generation, ΔE storage (t) is the increment of charging and discharging of the energy storage system, ΔL load (t) is the adjustment amount of the controllable load, ΔC ev (t) is the charging or discharging strategy of the electric vehicle; the state transition is: S t+1 =f(S t ,a t ), where f is the state transition function, S t+1 It is the state of the next moment.

[0052] The objective function L includes the operation and maintenance costs of distributed power generation and traditional power generation equipment, environmental protection costs and non-distributed power utilization. The specific expression is:

[0053] min L=αC operation +βC environment +γC efficiency ,

[0054] Among them, α, β and γ are weight coefficients, which adjust the importance of each objective in the overall optimization objective; C operation The operation and maintenance cost of distributed power generation and traditional power generation equipment; C environment Environmental protection cost; C efficiency is the utilization rate of non-distributed power source.

[0055] The expression of environmental protection cost is:

[0056]

[0057] Where, T is the set acquisition period; N is the number of power supplies; αi P is the amount of greenhouse gas emitted by power source i for every 1MWh of electricity generated; i (t) is the power generated by power source i at time t; C em is the cost per unit of greenhouse gas emissions.

[0058] The expression of greenhouse gas emissions emissions(t) is:

[0059]

[0060] The loss function expression is:

[0061]

[0062] Among them, Y true,i For historical data, is the predicted value, and N is the number of samples.

[0063] The reward function R(t) of the deep Q network is:

[0064]

[0065] Among them, λ1, λ2, λ3, λ4 and λ5 are weight parameters; P gen (t) is the current power generation of distributed power sources and traditional power sources; P demand (t) is the load demand; P renew (t) is the power generation of distributed generation; emissions(t) is the greenhouse gas emissions; k1 and k2 are the positive parameters for scaling the objective function L; f(t) is the frequency of the power grid at time t; f ev Historical average frequency of the power grid.

[0066] Example 2

[0067] A virtual power plant optimization and dispatching system combined with vehicle-grid interaction, comprising a distributed power supply module, an energy storage module, a controllable load module, a vehicle-grid interaction module and a communication control module; the distributed power supply module is used to generate new energy electricity; the energy storage module is a module used to store energy during low-peak hours and discharge energy during power grid dispatch; the controllable load module is an energy-consuming power-consuming device that adjusts the power load according to the operating status of the power grid without affecting the user's power consumption experience; the vehicle-grid interaction module is used to regulate the two-way interaction between electric vehicles and the power grid; the communication control module comprises a perception layer, a network layer, a platform layer and an application layer, wherein the perception layer is used to collect historical data, the network layer is used to realize the communication between the communication control module and other modules, the platform layer is used to process the data collected by the perception layer and transmitted by the network layer, and generate a strategy for optimizing the dispatching of the virtual power plant; the application layer generates control instructions according to the optimization dispatching strategy generated by the platform layer and sends them to each module for power dispatching. Through the controllable load module, vehicle-grid interaction module and energy storage module, adjustments are made in the virtual power plant power grid to store excess electricity, replenish it in time when power generation is low, flexibly adapt to the actual power consumption of the virtual power plant, and comprehensively dispatch multiple modules so that the power of the entire power source and load can be uniformly dispatched, reducing operating costs and reducing overall resource waste.

[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0069] The electronic device of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0070] A plurality of components in the device are connected to the I / O interface, including: an input unit, such as a keyboard, a mouse, etc.; an output unit, such as various types of displays, speakers, etc.; a storage unit, such as a disk, an optical disk, etc.; and a communication unit, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit allows the device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks. The processing unit performs the various methods and processes described above, such as the method of the present invention. For example, in some embodiments, the method of the present invention may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of the method of the present invention described above may be performed. Alternatively, in other embodiments, the CPU may be configured to perform the method of the present invention in any other appropriate manner (e.g., by means of firmware).

[0071] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0072] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0073] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0074] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A virtual power plant optimization scheduling method combining vehicle-grid interaction, characterized in that: The following steps are involved: Collect historical data to predict the power demand of controllable loads in the virtual power plant at the next moment, the charging and discharging of the vehicle-grid interactive system, the power generation of traditional power sources, the power storage, the power generation of distributed power sources, weather conditions, grid frequency changes, and greenhouse gas emissions; the prediction is performed through feature extraction by convolutional neural networks, and the prediction results focusing on load peak periods and weather change periods are obtained through the attention mechanism; Defining a state according to the prediction result to obtain a state space, and using a Markov decision process to describe the state transition; The optimal action is obtained based on the deep Q network to determine the output of the generator set, the charging and discharging of the energy storage system, the controllable load scheduling and the vehicle-grid charging and discharging scheduling strategy, and adjust the power grid operation in real time.

2. The method for optimizing and dispatching a virtual power plant in combination with vehicle-grid interaction according to claim 1, characterized in that: The historical data includes the power regulation of controllable loads, the charging and discharging power of electric vehicles, the status of vehicle batteries, the power generation of traditional power grids, the charging and discharging power of batteries, battery energy storage, the power generation power of distributed power sources, power grid loads, electricity prices, meteorological data, power grid frequency and greenhouse gas emissions.

3. The method for optimizing and dispatching a virtual power plant in combination with vehicle-grid interaction according to claim 1, characterized in that: After collecting the historical data, constraint condition judgment and preprocessing are performed; The constraints include the balance of total power generation and total load of the power grid, the charging and discharging constraints of electric vehicles, the energy storage capacity limitations, the charging and discharging power limitations of the energy storage system, and the frequency range limitations of the power grid.

4. The method for optimizing and dispatching a virtual power plant in combination with vehicle-grid interaction according to claim 1, characterized in that: The preprocessed data is input into the convolution layer, and nonlinearly transformed through convolution processing and activation function to obtain the features extracted in time; The attention weight of each time step of the feature is calculated, and the feature of each time step is weighted using the attention weight; the weighted feature is input into the pooling layer to obtain the aggregated feature; and the aggregated feature is input into the fully connected layer to obtain the predicted value.

5. The method for optimizing and dispatching a virtual power plant in combination with vehicle-grid interaction according to claim 1, characterized in that: The states and state transitions are described by the Markov decision process, where Status: S t =[P gen (t), E storage (t), L load (t), C ev (t), D weather (t)], where P gen (t) is the current power generation of distributed power sources and traditional power sources, E storage (t) is the power of the energy storage system, L load (t) is the load demand, C ev (t) is the charge and discharge capacity of the electric vehicle, D weather (t) weather conditions; The action space is: a t =[ΔP gen (t), ΔE storage (t), ΔL load (t), ΔC ev (t)], where ΔP gen (t) is the adjusted power generation, ΔE storage (t) is the increment of charging and discharging of the energy storage system, ΔL load (t) is the adjustment amount of the controllable load, ΔC ev (t) is the charging or discharging strategy of the electric vehicle.

6. The method for optimizing and dispatching a virtual power plant in combination with vehicle-grid interaction according to claim 1, characterized in that: The objective function L includes the operation and maintenance costs of distributed power generation and traditional power generation equipment, environmental protection costs and non-distributed power utilization. The specific expression is: min L=αC operation +βC environment +γC efficiency , Among them, α, β and γ are weight coefficients, which adjust the importance of each objective in the overall optimization objective; C operation The operation and maintenance cost of distributed power generation and traditional power generation equipment; C environment Environmental protection cost; C efficiency is the utilization rate of non-distributed power source.

7. The method for optimizing and dispatching a virtual power plant in combination with vehicle-grid interaction according to claim 1, characterized in that: The reward function R(t) of the deep Q network is: Among them, λ1, λ2, λ3, λ4 and λ5 are weight parameters; P gen (t) is the current power generation of distributed power sources and traditional power sources; P demand (t) is the load demand; P renew (t) is the power generation of distributed generation; emissions(t) is the greenhouse gas emissions; k1 and k2 are the positive parameters for scaling the objective function L; f(t) is the frequency of the power grid at time t; f ev Historical average frequency of the power grid.

8. A virtual power plant optimization dispatching system combining vehicle-grid interaction using the method according to any one of claims 1 to 7, characterized in that: Including distributed power supply module, energy storage module, controllable load module, vehicle-grid interaction module and communication control module; The distributed power supply module is used to generate new energy power; the energy storage module is used to store energy during low power consumption and discharge energy during peak power consumption in grid dispatching; The controllable load module is an energy-consuming electrical device that adjusts the power load according to the operating status of the power grid without affecting the user's power consumption experience; the vehicle-grid interaction module is used to regulate the two-way interaction between the electric vehicle and the power grid; the communication control module includes a perception layer, a network layer, a platform layer and an application layer, wherein the perception layer is used to collect historical data, the network layer is used to realize the communication between the communication control module and other modules, the platform layer is used to process the data collected by the perception layer and transmitted by the network layer, and generate a strategy for optimizing the scheduling of the virtual power plant; the application layer generates control instructions according to the optimized scheduling strategy generated by the platform layer, and sends them to each module for power scheduling.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images