Virtual power plant energy scheduling and carbon transaction method, device, system and storage medium

Abstract

This application discloses a method, apparatus, system, and storage medium for energy dispatch and carbon trading in a virtual power plant. The virtual power plant includes multiple charging stations connected to the power grid and equipped with renewable energy modules. The method includes: responding to charging commands by acquiring real-time status information of multiple charging stations, wherein the real-time status information includes the charging station's own power demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota; inputting the real-time status information into a trained strategy network model to output a charging dispatch and carbon emission trading strategy; and performing energy dispatch and carbon trading on the multiple charging stations based on the charging dispatch and carbon emission trading strategy. This method integrates distributed renewable energy output, the main grid's dynamic electricity price, and vehicle charging demand, linking the entire process of energy dispatch and carbon trading to achieve optimized allocation of power resources from multiple charging stations, reasonable sharing of carbon emission costs, and efficient circulation of carbon assets.

Description

Technical Field

[0001] This application relates to the fields of energy management and carbon emission technology for charging stations, and in particular to a method, apparatus, system and storage medium for virtual power plant energy dispatch and carbon trading. Background Technology

[0002] Guided by the goals of "peak carbon and carbon neutrality," electrification in the transportation sector has become a core pathway to promote the low-carbon transformation of the energy structure. With the continuous iteration of new energy and battery technologies, China's new energy vehicle market has entered a mainstream development stage, and the scale of the charging infrastructure system has also grown accordingly.

[0003] The deployment of large-scale charging infrastructure not only meets the charging demand brought about by the popularization of electric vehicles, but also places higher demands on the precision and low-carbon nature of charging scheduling. Currently, some charging stations are equipped with renewable energy devices such as photovoltaic power generation and wind power generation, which can carry out demand response based on the real-time dynamic electricity price of the main grid and the intermittent output characteristics of renewable energy. This optimizes operating revenue while ensuring charging services. However, the industry still faces problems such as imperfect layout and insufficient scheduling coordination. Moreover, most charging stations still rely on traditional fossil fuels for power supply, and the large amount of indirect carbon emissions generated during the charging process have not yet been reasonably attributed to their costs.

[0004] From a liability perspective, indirect carbon emissions during the charging process are an inevitable byproduct of charging stations generating operational revenue, and the related costs should be borne by the charging station operators, not upstream power plants. Since the establishment of a market mechanism for trading carbon emission rights, the carbon trading system has gradually matured. China has not only introduced mandatory emission reduction trading mechanisms for enterprises but also innovatively implemented market-based incentive models such as carbon credits for new energy vehicle charging, realizing the quantification and monetization of charging emission reductions. Against this backdrop, allowing charging stations with emissions below the limit to sell their remaining quotas and those exceeding the limit to purchase additional permits through carbon emission quotas and trading rules has become an effective path to promote the low-carbon transformation of charging stations. However, the current lack of a distributed energy dispatch and carbon trading coordination mechanism adapted to the multi-charging-station virtual power plant model makes it difficult to meet the industry's needs for large-scale low-carbon development. Summary of the Invention

[0005] This application aims to at least partially address one of the technical problems in related technologies. Therefore, the first objective of this application is to propose a virtual power plant energy dispatch and carbon trading method. By integrating distributed renewable energy output, dynamic electricity prices from the main grid, and vehicle charging demand, and linking the entire process of energy dispatch and carbon trading, this method achieves optimized allocation of power resources from multiple charging stations, reasonable sharing of carbon emission costs, and efficient circulation of carbon assets. This addresses the limitations of related technologies, such as insufficient adaptability of charging dispatch and carbon trading coordination mechanisms and unclear attribution of carbon emission costs.

[0006] The second objective of this application is to propose a virtual power plant energy dispatch and carbon trading system.

[0007] The third objective of this application is to propose a virtual power plant energy dispatch and carbon trading system.

[0008] The fourth objective of this application is to provide a computer-readable storage medium.

[0009] To achieve the above objectives, the first aspect of this application proposes a virtual power plant energy dispatch and carbon trading method. The virtual power plant includes multiple charging stations connected to the power grid and equipped with renewable energy modules. The method includes: responding to a charging command, acquiring real-time status information of multiple charging stations, wherein the real-time status information includes the charging station's own electricity demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota; inputting the real-time status information into a trained policy network model to output a charging dispatch and carbon emission trading strategy; and performing energy dispatch and carbon trading on the multiple charging stations based on the charging dispatch and carbon emission trading strategy.

[0010] According to the virtual power plant energy dispatch and carbon trading method of this application, in response to charging commands, real-time status information of multiple charging stations is acquired. This real-time status information includes the charging station's own electricity demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon allowance. The real-time status information is input into a trained policy network model to output a charging dispatch and carbon emission trading strategy. Then, based on this strategy, energy dispatch and carbon trading are performed on multiple charging stations. Thus, this method integrates distributed renewable energy output, dynamic electricity prices from the main grid, and vehicle charging demand, linking the entire process of energy dispatch and carbon trading. This achieves optimized allocation of power resources across multiple charging stations, reasonable allocation of carbon emission costs, and efficient circulation of carbon assets, addressing the limitations of insufficient adaptability of charging dispatch and carbon trading coordination mechanisms and unclear attribution of carbon emission costs in related technologies.

[0011] In addition, the virtual power plant energy dispatch and carbon trading method according to the above embodiments of this application may also have the following additional technical features: In some embodiments of this application, the virtual power plant energy scheduling and carbon trading method further includes: acquiring historical state information of multiple charging stations; determining the heterogeneous characteristics of multiple charging stations based on the historical state information to construct a corresponding charging scheduling and carbon emission trading optimization problem; remodeling the charging scheduling and carbon emission trading optimization problem to obtain a partially observable Markov game, and defining the state space, action space, and reward function of each charging station; using multi-agent proximal policy optimization as the core algorithm to construct a charging scheduling and carbon emission trading optimization algorithm; building a centralized training-distributed execution training framework based on shared parameters, and training the centralized training-distributed execution training framework based on historical state information to obtain a trained policy network model.

[0012] In some embodiments of this application, heterogeneous characteristics include charging revenue, load cost, and carbon emission cost. The heterogeneous characteristics of multiple charging stations are determined based on historical state information to construct a corresponding charging scheduling and carbon emission trading optimization problem, including: determining the charging revenue, load cost, and carbon emission cost of each charging station based on historical state information; and constructing a charging scheduling and carbon emission trading optimization problem based on the charging revenue, load cost, and carbon emission cost of each charging station.

[0013] In some embodiments of this application, the charging scheduling and carbon emission trading optimization problem is characterized by the following calculation formula:

[0014] in, for t Time slot charging station i The charging revenue, for t Time slot charging station i The load cost, For carbon emission costs, For charging stations i Inner h Charging and discharging decisions for individual charging stations For charging stations i and j Carbon emissions trading decisions between [the parties].

[0015] In some embodiments of this application, the formula for calculating charging revenue is as follows:

[0016] in, for t Time slot charging station i The charging revenue, As the first coefficient, for t Time slot charging station iReal-time electricity price For charging stations i Inner h The charging and discharging decisions of each charging station.

[0017] In some embodiments of this application, the formula for calculating load cost is as follows:

[0018] in, for t Time slot charging station i The load cost, for t Time slot charging station i Real-time electricity price For charging stations i Inner h Charging and discharging decisions for each charging station for t Time slot charging station i Its own power needs.

[0019] In some embodiments of this application, the formula for calculating carbon emission costs is as follows:

[0020] in, for t Time slot charging station i The load cost, for t Time slot charging station i Real-time carbon trading prices for t Time slot charging station i Carbon emissions trading decisions.

[0021] To achieve the above objectives, a second aspect of this application proposes a virtual power plant energy dispatch and carbon trading device. The virtual power plant includes multiple charging stations connected to the power grid and equipped with renewable energy modules. The device includes: an acquisition module for acquiring real-time status information of multiple charging stations in response to charging commands, wherein the real-time status information includes the charging station's own electricity demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota; a strategy generation module for inputting the real-time status information into a trained strategy network model to output a charging dispatch and carbon emission trading strategy; and a control module for performing energy dispatch and carbon trading on the multiple charging stations based on the charging dispatch and carbon emission trading strategy.

[0022] According to the virtual power plant energy dispatch and carbon trading device of this application embodiment, the acquisition module responds to charging commands and acquires real-time status information of multiple charging stations. This real-time status information includes the charging station's own electricity demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota. The strategy generation module inputs the real-time status information into a trained strategy network model to output charging dispatch and carbon emission trading strategies. The control module performs energy dispatch and carbon trading for multiple charging stations based on these strategies. Thus, by integrating distributed renewable energy output, the main grid's dynamic electricity price, and vehicle charging demand, the device links the entire process of energy dispatch and carbon trading, achieving optimized allocation of power resources across multiple charging stations, reasonable sharing of carbon emission costs, and efficient circulation of carbon assets.

[0023] To achieve the above objectives, the third aspect of this application proposes a virtual power plant energy dispatch and carbon trading system, comprising: multiple charging stations, each charging station including a renewable energy module; a main grid module and multiple charging station energy dispatch modules, wherein the multiple charging stations are respectively connected to the main grid module through corresponding charging station energy dispatch modules; a carbon emission quota trading market module, wherein the multiple charging stations are connected to the carbon emission quota trading market module; and a control module configured to execute the above-described virtual power plant energy dispatch and carbon trading method.

[0024] According to the virtual power plant energy dispatch and carbon trading system of this application embodiment, multiple charging stations include a renewable energy module. The multiple charging stations are respectively connected to the main grid module and the carbon emission quota trading market module through the corresponding charging station energy dispatch module. The multiple charging stations are connected to the carbon emission quota trading market module. The control module executes the above-mentioned virtual power plant energy dispatch and carbon trading method, which can integrate distributed renewable energy output, main grid dynamic electricity price and vehicle charging demand, link the entire process of energy dispatch and carbon trading, and realize the optimized allocation of power resources of multiple charging stations, reasonable sharing of carbon emission costs and efficient circulation of carbon assets.

[0025] To achieve the above objectives, the fourth aspect of this application proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described virtual power plant energy dispatch and carbon trading method.

[0026] According to embodiments of this application, a computer-readable storage medium stores a computer program thereon that, when executed by a processor, implements the above-described virtual power plant energy dispatching and carbon trading method, thereby achieving optimized allocation of power resources from multiple charging stations, reasonable sharing of carbon emission costs, and efficient circulation of carbon assets.

[0027] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of a system architecture for virtual power plant energy dispatch and carbon trading according to an embodiment of this application; Figure 2 This is a flowchart of a virtual power plant energy dispatch and carbon trading method according to an embodiment of this application; Figure 3 This is a schematic diagram of the connection of a virtual power plant energy dispatch and carbon trading device according to an embodiment of this application. Detailed Implementation

[0029] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0030] The following description, with reference to the accompanying drawings, outlines the virtual power plant energy dispatch and carbon trading method, apparatus, system, and storage medium proposed in this application.

[0031] In some embodiments of this application, the virtual power plant includes multiple charging stations connected to the power grid and configured with renewable energy modules.

[0032] Specifically, the virtual power plant energy dispatch and carbon trading method is applied to the energy dispatch and carbon trading system of the virtual power plant, which includes multiple charging stations connected to the power grid and equipped with renewable energy modules.

[0033] by Figure 1 Taking the virtual power plant energy dispatch and carbon trading system shown as an example, it includes multiple charging station modules, multiple distributed renewable energy modules, a main grid module, a charging station energy dispatch module, a charging station carbon emission trading module, and a carbon emission quota trading market module.

[0034] Among them, multiple charging station modules are distributed in different geographical locations to provide charging services for arriving vehicles, optimize their own charging scheduling based on real-time electricity prices, charging demand and other information, and participate in the carbon emissions trading market with the indirect carbon emissions generated by charging. Multiple distributed renewable energy modules can be renewable energy power generation devices such as photovoltaic power generation or wind power generation, which are respectively equipped in the above-mentioned multiple charging station modules to provide a portion of the charging power; The main grid module is used to publish real-time dynamic electricity prices and is connected to the charging station module to provide power support for the charging station. The charging station energy scheduling module is used to arrange charging plans based on information such as electricity prices and vehicle charging demand published by the main power grid, and output charging decision information for each time period; The charging station carbon emission trading module is specifically designed as a trusted third-party module to provide a safe, efficient, and privacy-protected environment for carbon emission trading between charging stations. The carbon emission quota trading market module is used to sell (or recycle) the corresponding carbon emission quotas for charging stations with insufficient (or surplus) carbon emission quotas after the completion of carbon emission trading between charging stations.

[0035] Each of the above modules performs its own function and complements the others. The distributed renewable energy module and the main grid module jointly provide charging power to each charging station module. The main grid simultaneously publishes real-time electricity prices. The charging station energy dispatch module combines electricity prices and vehicle charging demand to issue time-period charging decisions to the charging station modules. The charging station modules optimize dispatching and generate indirect carbon emission data accordingly. The charging station carbon emission trading module provides a secure and privacy-protected environment for carbon emission rights trading between charging stations. The carbon emission quota trading market module recovers or replenishes the remaining or insufficient carbon emission quotas after distributed trading. Through data flow and functional collaboration, the modules achieve efficient power dispatching and optimized carbon asset allocation for multiple charging stations.

[0036] The virtual power plant energy dispatch and carbon trading method of this application will be described in detail below with reference to the accompanying drawings. like Figure 2 As shown, the virtual power plant energy dispatch and carbon trading method of this application includes: S1, in response to a charging command, obtains real-time status information of multiple charging stations, including the charging station's own power demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota. S2 inputs real-time status information into the trained policy network model to output charging scheduling and carbon emission trading strategies. S3 performs energy scheduling and carbon trading for multiple charging stations based on charging scheduling and carbon emission trading strategies.

[0037] Specifically, the charging command indicates the charging action, indicating that the current charging station is in a real-time adaptive decision-making stage, so as to respond to the charging command to control the charging station and control carbon trading.

[0038] Continue to apply to Figure 1 Taking the system shown as an example, the steps executed in the real-time adaptive decision-making phase are as follows: First, in each time slot t, each charging station's energy scheduling and carbon emission trading module obtains information such as its own power demand, the output of its renewable energy source, real-time electricity price, carbon price, and dynamic carbon quota based on the arrival, departure, and charging demand of vehicles at each charging station, as well as the real-time electricity price and carbon quota published by the main grid. The time slot is a preset statistical compensation and can be defined by the user. Then, the well-trained policy network model and its corresponding weight parameters are called, the real-time status information of the system is input into the policy network, and the real-time charging scheduling and carbon emission trading strategies are output to perform charging scheduling and carbon trading for multiple charging stations based on the charging scheduling and carbon emission trading strategies.

[0039] This embodiment optimizes charging scheduling decisions based on vehicle arrival, departure, and charging demand at each charging station, as well as real-time electricity prices published by the main grid. Secondly, under government-provided carbon allowances, any surplus or shortage of carbon emissions generated by charging stations can be traded through a trusted third party. The remaining surplus can then be traded with the higher-level carbon emission limit trading market module. This application enables distributed charging scheduling and carbon emission trading across multiple charging stations in different regions, and introduces a trusted third party to improve the security of the trading process. This increases charging revenue and reduces carbon emission costs for charging stations, while providing a new solution for the implementation of a carbon limit trading market.

[0040] In some embodiments of this application, the virtual power plant energy scheduling and carbon trading method further includes: acquiring historical state information of multiple charging stations; determining the heterogeneous characteristics of multiple charging stations based on the historical state information to construct a corresponding charging scheduling and carbon emission trading optimization problem; remodeling the charging scheduling and carbon emission trading optimization problem to obtain a partially observable Markov game, and defining the state space, action space, and reward function of each charging station; using multi-agent proximal policy optimization as the core algorithm to construct a charging scheduling and carbon emission trading optimization algorithm; building a centralized training-distributed execution training framework based on shared parameters, and training the centralized training-distributed execution training framework based on historical state information to obtain a trained policy network model.

[0041] In other words, during the offline training phase of the policy network model, the following steps are performed: First, collect historical data from each charging station's energy dispatch and carbon emission trading module, including its own electricity demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota, as historical status information.

[0042] Then, based on the heterogeneous characteristics of each charging station, and considering both endogenous and exogenous uncertainties, a distributed charging scheduling and carbon emission trading optimization problem for multi-charging-station virtual power plants is established. For example, the heterogeneous characteristics of each charging station can be identified based on historical state information.

[0043] Then, the optimization problem is remodeled as a partially observable Markov game, with each charging station regarded as an agent, and the state space, action space, and reward function of the charging station agent are defined.

[0044] In other words, the optimization problem of distributed charging scheduling and carbon emission trading for multi-charging station virtual power plants is remodeled and formulated as a partially observable Markov game. The elements in this six-tuple represent the global state space of the multi-charging-station system, the action decision space of the charging station, the reward function, the local observation space of the charging station, the total number of charging stations, and the discount factor, respectively.

[0045] The state space of charging station i is defined as follows:

[0046] Action space is defined as:

[0047] The reward function is defined as:

[0048] in, for t Time slot charging station i Real-time electricity price for t Time slot charging station i Real-time carbon trading prices for t Time slot charging station i renewable energy production, for t Time slot charging station i Its own power demand, for t Time slot charging station i The charging revenue, for t Time slot charging station i The load cost, For carbon emission costs, For charging stations i Inner h Charging and discharging decisions for each charging station For charging stations i and j Carbon emissions trading decisions between [the parties].

[0049] Then, an optimization algorithm for distributed charging scheduling and carbon emission trading of virtual power plants with multiple charging stations based on Multi-Agent Proximal Policy Optimization (MAPPO) was developed. A centralized training-distributed execution training framework based on shared parameters was introduced, and the algorithm was trained using a large amount of historical data collected in the above steps. After the algorithm was trained to full convergence, the policy network model and its weight parameters were saved.

[0050] Furthermore, the MAPPO algorithm comprises I Actor networks and I Critic networks.

[0051] The Actor network aims to maximize the cumulative discount reward of the system while ensuring the policy update magnitude. It updates the network parameters using the gradient ascent method. , in, The advantage function is the truncated version. and For new strategies and old strategies.

[0052] The goal of the RITIC network is to minimize the loss function, and it updates the network parameters using gradient descent. .

[0053] The distributed charging scheduling and carbon emission trading optimization algorithm based on MAPPO multi-charging station virtual power plant introduces a neural network parameter sharing mechanism, which accelerates the training convergence speed.

[0054] Meanwhile, this embodiment, based on the MAPPO multi-charging-station virtual power plant distributed charging scheduling and carbon emission trading optimization algorithm, designs a centralized training-decentralized execution training framework, which can protect the privacy and security of each charging station to a certain extent while ensuring scalability.

[0055] Based on the strategy network model constructed in the above manner, the charging scheduling and carbon trading decisions during system operation can be made quickly and in real time according to the current system status information, without relying on future statistical information of the system.

[0056] Therefore, this embodiment introduces the MAPPO algorithm based on parameter sharing into the charging and discharging scheduling and carbon emission trading problems of multi-charging station virtual power plant systems. It does not rely on future statistical information of the system, but provides energy scheduling and carbon trading strategies online based on the real-time status of the system, providing decision-making solutions for the low-carbon and economical operation of charging station clusters.

[0057] In some embodiments of this application, heterogeneous characteristics include charging revenue, load cost, and carbon emission cost. The heterogeneous characteristics of multiple charging stations are determined based on historical state information to construct a corresponding charging scheduling and carbon emission trading optimization problem, including: determining the charging revenue, load cost, and carbon emission cost of each charging station based on historical state information; and constructing a charging scheduling and carbon emission trading optimization problem based on the charging revenue, load cost, and carbon emission cost of each charging station.

[0058] In other words, the charging revenue, load cost, and carbon emission cost of each charging station are determined based on historical status information. Then, the charging revenue, load cost, and carbon emission cost of each charging station are integrated to construct an optimization problem for charging scheduling and carbon emission trading, so as to ensure the accuracy of the optimization problem construction.

[0059] In some embodiments of this application, the charging scheduling and carbon emission trading optimization problem is characterized by the following calculation formula:

[0060] in, for t Time slot charging station i The charging revenue, for t Time slot charging station i The load cost, For carbon emission costs, For charging stations i Inner h Charging and discharging decisions for each charging station For charging stations i and j Carbon emissions trading decisions between [the parties].

[0061] In other words, the charging revenue, load cost, and carbon emission cost of each charging station are combined using the above model formula to represent the optimization problem of charging scheduling and carbon emission trading, thereby solving for the maximum revenue allocation.

[0062] In some embodiments of this application, the formula for calculating charging revenue is as follows:

[0063] in, for t Time slot charging station i The charging revenue, As the first coefficient, The real-time electricity price for charging station i in time slot t. For charging stations i Inner h The charging and discharging decisions of each charging station.

[0064] In other words, charging revenue The revenue comes from charging stations providing charging and discharging services to arriving electric vehicles, specifically calculated by combining charging revenue and real-time electricity prices.

[0065] In some embodiments of this application, the formula for calculating load cost is as follows:

[0066] in, for t Time slot charging station i The load cost, The real-time electricity price for charging station i in time slot t. For charging stations i Inner h Charging and discharging decisions for each charging station for t Time slot charging station i Its own power needs.

[0067] In other words, in the problem of distributed charging scheduling and carbon emission trading optimization of multi-charging-station virtual power plants, the load cost comes from the charging station's own electricity demand and the cost of purchasing electricity from the grid to charge electric vehicles. The specific cost is determined based on real-time electricity prices, charging and discharging decisions, and its own electricity demand.

[0068] In some embodiments of this application, the formula for calculating carbon emission costs is as follows:

[0069] in, The load cost of charging station i in time slot t. for t Time slot charging station i Real-time carbon trading prices Carbon emission trading decisions for charging station i in time slot t.

[0070] In other words, in the problem of distributed charging scheduling and carbon emission trading optimization of virtual power plants with multiple charging stations, the carbon emission cost comes from the charging station's own electricity demand and the cost of purchasing electricity from the grid to charge electric vehicles, and is specifically determined based on the real-time carbon trading price and carbon emission trading decisions.

[0071] As a specific embodiment of this application, a distributed scheduling and carbon trading system for multi-charging-station virtual power plants, such as Figure 1 As shown, there are I charging stations in different areas equipped with renewable energy generation. These charging stations provide charging services for connected electric vehicles, and their power mainly comes from the main power grid and renewable energy generation modules.

[0072] The virtual power plant energy dispatch and carbon trading method may include the following steps: The first step is for each charging station to receive real-time electricity prices, renewable energy production, and vehicle arrival information from the main grid module, including vehicle departure time and charging demand, and to calculate the dwell time of electric vehicles and the time required to charge to the desired amount of electricity. The second step involves each charging station actively responding to the above information and optimizing charging decision-making and scheduling. The goal is to improve the charging revenue of the charging stations, that is, to provide charging services when electricity prices are as low as possible, while meeting the charging needs of electric vehicles. For example, increasing charging power when real-time electricity prices are low or renewable energy production is high, and decreasing charging power when real-time electricity prices are high or renewable energy production is low. The third step is to calculate the charging service revenue and indirect carbon emissions for each time period based on the charging station's charging scheduling decision. Specifically, the indirect carbon emissions are calculated by multiplying the power plant's carbon emission intensity by the charging station's electricity purchase. The fourth step involves allocating a fixed amount of free emission allowances to each charging station within the carbon emission cap market. When these allowances are insufficient or surplus, charging stations can trade them using the carbon emission trading module, buying or selling corresponding carbon emission allowances to other charging stations. It's worth noting that the price of carbon emission trading between charging stations is lower than the price of purchasing carbon allowances from the upstream market, but higher than the price of selling carbon allowances to the upstream market. The carbon emission trading module is a trusted third-party system that ensures the security, privacy, and fairness of transactions. The fifth step involves the remaining carbon emission trading between the above charging stations. The charging stations can participate in the upper-level carbon emission quota trading market to clear their carbon emission quotas at a lower selling price or a higher buying price. This allows for the calculation of the final carbon emission cost for each charging station.

[0073] Therefore, the multi-charging-station virtual power plant distributed charging scheduling and carbon trading system proposed in this embodiment connects multiple charging station modules, multiple distributed renewable energy modules, main grid module, charging station energy scheduling module, charging station carbon emission trading module and carbon emission quota trading market module together. This enables charging stations to increase their charging revenue and reduce carbon emission costs by charging when renewable energy production is at its highest and by participating in carbon emission trading between charging stations in a safe and orderly manner.

[0074] In summary, the virtual power plant energy dispatch and carbon trading method of this application, in response to charging commands, acquires real-time status information of multiple charging stations. This real-time status information includes the charging station's own electricity demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon allowance. This real-time status information is input into a trained policy network model to output charging dispatch and carbon emission trading strategies. Then, based on these strategies, energy dispatch and carbon trading are performed on multiple charging stations. Thus, this method integrates distributed renewable energy output, dynamic electricity prices from the main grid, and vehicle charging demand, linking the entire process of energy dispatch and carbon trading. This achieves optimized allocation of power resources across multiple charging stations, reasonable sharing of carbon emission costs, and efficient circulation of carbon assets, addressing the limitations of insufficient adaptability of charging dispatch and carbon trading coordination mechanisms and unclear attribution of carbon emission costs in related technologies.

[0075] Corresponding to the above embodiments, this application also proposes a virtual power plant energy dispatch and carbon trading device.

[0076] In some embodiments of this application, the virtual power plant includes multiple charging stations connected to the power grid and configured with renewable energy modules.

[0077] like Figure 3 As shown, the virtual power plant energy dispatch and carbon trading device of this application embodiment includes: an acquisition module 10, a strategy generation module 20, and a control module 30.

[0078] The acquisition module 10 is used to acquire real-time status information of multiple charging stations in response to charging commands. The real-time status information includes the charging station's own power demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota. The strategy generation module 20 is used to input the real-time status information into the trained strategy network model to output charging scheduling and carbon emission trading strategies. The control module 30 is used to perform energy scheduling and carbon trading for multiple charging stations based on the charging scheduling and carbon emission trading strategies.

[0079] In some embodiments of this application, the policy generation module 20 is further configured to: acquire historical state information of multiple charging stations; determine the heterogeneous characteristics of multiple charging stations based on the historical state information to construct a corresponding charging scheduling and carbon emission trading optimization problem; remodel the charging scheduling and carbon emission trading optimization problem to obtain a partially observable Markov game, and define the state space, action space, and reward function of each charging station; adopt multi-agent proximal policy optimization as the core algorithm to construct a charging scheduling and carbon emission trading optimization algorithm; build a centralized training-distributed execution training framework based on shared parameters, and train the centralized training-distributed execution training framework based on historical state information to obtain a trained policy network model.

[0080] In some embodiments of this application, heterogeneous characteristics include charging revenue, load cost, and carbon emission cost. The heterogeneous characteristics of multiple charging stations are determined based on historical state information to construct a corresponding charging scheduling and carbon emission trading optimization problem, including: determining the charging revenue, load cost, and carbon emission cost of each charging station based on historical state information; and constructing a charging scheduling and carbon emission trading optimization problem based on the charging revenue, load cost, and carbon emission cost of each charging station.

[0081] In some embodiments of this application, the charging scheduling and carbon emission trading optimization problem is characterized by the following calculation formula:

[0082] in, for t Time slot charging station i The charging revenue, for t Time slot charging station i The load cost, For carbon emission costs, For charging stations i Inner h Charging and discharging decisions for each charging station For charging stations i and j Carbon emissions trading decisions between [the parties].

[0083] In some embodiments of this application, the formula for calculating charging revenue is as follows:

[0084] in, for t Time slot charging station i The charging revenue, As the first coefficient, for t Time slot charging station i Real-time electricity price For charging stations i Inner h The charging and discharging decisions of each charging station.

[0085] In some embodiments of this application, the formula for calculating load cost is as follows:

[0086] in, for t Time slot charging station i The load cost, for t Time slot charging station i Real-time electricity price For charging stations i Inner h Charging and discharging decisions for each charging station for t Time slot charging station i Its own power needs.

[0087] In some embodiments of this application, the formula for calculating carbon emission costs is as follows:

[0088] in, for t Time slot charging station i The load cost, for t Time slot charging station i Real-time carbon trading prices for t Time slot charging station i Carbon emissions trading decisions.

[0089] It should be noted that for details not disclosed in the virtual power plant energy dispatch and carbon trading device of the embodiments of this application, please refer to the details disclosed in the virtual power plant energy dispatch and carbon trading method of the above embodiments of this application, which will not be repeated here.

[0090] According to the virtual power plant energy dispatch and carbon trading device of this application embodiment, the acquisition module responds to charging commands and acquires real-time status information of multiple charging stations. This real-time status information includes the charging station's own electricity demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota. The strategy generation module inputs the real-time status information into a trained strategy network model to output charging dispatch and carbon emission trading strategies. The control module performs energy dispatch and carbon trading for multiple charging stations based on these strategies. Thus, by integrating distributed renewable energy output, the main grid's dynamic electricity price, and vehicle charging demand, the device links the entire process of energy dispatch and carbon trading, achieving optimized allocation of power resources across multiple charging stations, reasonable sharing of carbon emission costs, and efficient circulation of carbon assets.

[0091] Corresponding to the above embodiments, this application also proposes a virtual power plant energy dispatch and carbon trading system.

[0092] The virtual power plant energy dispatch and carbon trading system of this application embodiment includes: multiple charging stations, each charging station including a renewable energy module; a main grid module and multiple charging station energy dispatch modules, with each charging station connected to the main grid module through a corresponding charging station energy dispatch module; a carbon emission quota trading market module, with the multiple charging stations connected to the carbon emission quota trading market module; and a control module configured to execute the above-described virtual power plant energy dispatch and carbon trading method. For details, please refer to... Figure 1 The diagram shows a virtual power plant energy dispatch and carbon trading system.

[0093] According to the virtual power plant energy dispatch and carbon trading system of this application embodiment, multiple charging stations include a renewable energy module. The multiple charging stations are respectively connected to the main grid module and the carbon emission quota trading market module through the corresponding charging station energy dispatch module. The multiple charging stations are connected to the carbon emission quota trading market module. The control module executes the above-mentioned virtual power plant energy dispatch and carbon trading method, which can integrate distributed renewable energy output, main grid dynamic electricity price and vehicle charging demand, link the entire process of energy dispatch and carbon trading, and realize the optimized allocation of power resources of multiple charging stations, reasonable sharing of carbon emission costs and efficient circulation of carbon assets.

[0094] Corresponding to the above embodiments, this application also proposes a computer-readable storage medium.

[0095] The computer-readable storage medium of this application embodiment stores a computer program thereon, which, when executed by a processor, implements the above-described virtual power plant energy dispatch and carbon trading method.

[0096] According to embodiments of this application, a computer-readable storage medium stores a computer program thereon that, when executed by a processor, implements the above-described virtual power plant energy dispatching and carbon trading method, thereby achieving optimized allocation of power resources from multiple charging stations, reasonable sharing of carbon emission costs, and efficient circulation of carbon assets.

[0097] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0098] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0099] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0100] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "joining," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0101] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for energy dispatch and carbon trading in a virtual power plant, characterized in that, The virtual power plant includes multiple charging stations connected to the power grid and configured with renewable energy modules. The method includes: In response to a charging command, the system acquires real-time status information of the multiple charging stations, including the charging station's own power demand, renewable energy production, real-time electricity price, carbon price, and dynamic carbon quota. The real-time status information is input into the trained policy network model to output charging scheduling and carbon emission trading strategies. Energy scheduling and carbon trading are performed on the multiple charging stations based on the aforementioned charging scheduling and carbon emission trading strategies.

2. The method according to claim 1, characterized in that, The method further includes: Obtain historical status information of the multiple charging stations; The heterogeneous characteristics of the multiple charging stations are determined based on the historical state information in order to construct the corresponding charging scheduling and carbon emission trading optimization problem; The charging scheduling and carbon emission trading optimization problem is remodeled to obtain a partially observable Markov game, and the state space, action space and reward function of each charging station are defined. The charging scheduling and carbon emission trading optimization algorithm is constructed by using multi-agent proximal strategy optimization as the core algorithm. A centralized training-distributed execution training framework based on shared parameters is constructed, and the centralized training-distributed execution training framework is trained according to the historical state information to obtain the trained policy network model.

3. The method according to claim 2, characterized in that, The heterogeneous characteristics include charging revenue, load cost, and carbon emission cost. Based on the historical state information, the heterogeneous characteristics of the multiple charging stations are determined to construct a corresponding charging scheduling and carbon emission trading optimization problem, including: The charging revenue, load cost, and carbon emission cost of each charging station are determined based on the historical status information. The charging scheduling and carbon emission trading optimization problem is constructed based on the charging revenue, load cost, and carbon emission cost of each charging station.

4. The method according to claim 3, characterized in that, The charging scheduling and carbon emission trading optimization problem is characterized by the following calculation formula: in, for t Time slot charging station i The charging revenue, for t Time slot charging station i The load cost, For carbon emission costs, For charging stations i Inner h Charging and discharging decisions for individual charging stations For charging stations i and j Carbon emissions trading decisions between [the parties].

5. The method according to claim 3, characterized in that, The formula for calculating the charging revenue is as follows: in, for t Time slot charging station i The charging revenue, As the first coefficient, for t Time slot charging station i Real-time electricity price For charging stations i Inner h The charging and discharging decisions of each charging station.

6. The method according to claim 3, characterized in that, The formula for calculating the load cost is as follows: in, for t Time slot charging station i The load cost, for t Time slot charging station i Real-time electricity price For charging stations i Inner h Charging and discharging decisions for each charging station for t Time slot charging station i Its own power needs.

7. The method according to claim 3, characterized in that, The formula for calculating the carbon emission cost is as follows: in, for t Time slot charging station i The load cost, for t Time slot charging station i Real-time carbon trading prices for t Time slot charging station i Carbon emissions trading decisions.

8. A virtual power plant energy dispatch and carbon trading device, characterized in that, The virtual power plant includes multiple charging stations, and the device includes: The acquisition module is used to acquire the real-time status information of the multiple charging stations in response to the charging command. The real-time status information includes the charging station's own power demand, renewable energy output, real-time electricity price, carbon price, and dynamic carbon quota. The strategy generation module is used to input the real-time state information into the trained strategy network model to output charging scheduling and carbon emission trading strategies. The control module is used to perform energy scheduling and carbon trading for the multiple charging stations based on the charging scheduling and carbon emission trading strategy.

9. A virtual power plant energy dispatch and carbon trading system, characterized in that, The system includes: Multiple charging stations, each including a renewable energy module; The system includes a main grid module and multiple charging station energy dispatch modules, with each charging station connected to the main grid module via a corresponding charging station energy dispatch module. A carbon emission quota trading market module, wherein the plurality of charging stations are connected to the carbon emission quota trading market module; The control module is configured to perform the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images