Vehicle network interaction multi-zone-area scheduling method, device and equipment fusing evolutionary game

Abstract

The invention provides a vehicle network interaction multi-zone-area scheduling method, device and equipment fusing an evolutionary game, and relates to the technical field of electric vehicle scheduling. The method comprises the following steps: formulating a subsidy strategy of a transformer area according to a predicted electrical load; wherein the subsidy strategy comprises a subsidy time period and an initial subsidy amount of each transformer area; in the peak period of electricity consumption, the initial tendency degree of the electric vehicle for selection of each transformer area is obtained, the initial subsidy amount and the initial tendency degree are input into the evolutionary game model, the game process is optimized through an NSGA-II algorithm, and a game result is obtained; wherein the game result comprises the optimal subsidy amount of each zone area and the optimal tendency degree of each electric vehicle, the discharge price of each electric vehicle in each zone area is formulated according to the optimal subsidy amount of each zone area, and the zone area where each electric vehicle selects to discharge is determined according to the optimal tendency degree of each electric vehicle. According to the invention, resources among a plurality of transformer areas can be effectively integrated during the peak period of power utilization.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicle scheduling technology, and in particular to a vehicle-grid interactive multi-station scheduling method, device and equipment integrating evolutionary game. Background Art

[0002] With the increasing popularity of electric vehicles and the widespread use of renewable energy, vehicle-grid interaction (V2I) is playing an increasingly important role in smart grids. By allowing electric vehicles to discharge energy into the grid when needed, V2I not only improves grid stability and reliability but also provides additional economic benefits for electric vehicle users.

[0003] However, existing research is mostly limited to optimizing the scheduling of a single distribution area or microgrid. Research on the interaction and coordination mechanisms between multiple distribution areas is relatively scarce. This is especially true during peak hours, when resources between multiple distribution areas cannot be effectively integrated, limiting overall system performance. Therefore, a scheduling method for vehicle-grid interaction that can integrate resources across multiple distribution areas is urgently needed. Summary of the Invention

[0004] The embodiments of the present invention provide a vehicle-grid interactive multi-zone scheduling method, device and equipment that integrates evolutionary game to solve the problem that the existing electric vehicle scheduling method cannot effectively integrate resources between multiple zones during peak electricity consumption periods.

[0005] In a first aspect, an embodiment of the present invention provides a multi-station scheduling method for vehicle-grid interaction integrating evolutionary game, including:

[0006] Formulate a subsidy strategy for each substation based on the predicted electricity load; the subsidy strategy includes the subsidy period and the initial subsidy amount for each substation;

[0007] During peak hours, the initial preference of electric vehicles for each substation is obtained. The initial subsidy amount and initial preference are input into the evolutionary game model. The game process is optimized using the NSGA-II algorithm to obtain the game results. The game results include the optimal subsidy amount for each substation and the optimal preference for each electric vehicle. The evolutionary game model takes maximizing the benefits of the substation, maximizing the benefits of electric vehicles, and minimizing carbon emissions as its objective functions.

[0008] The discharge price of electric vehicles in each area is determined based on the optimal subsidy amount of each area, and the area where each electric vehicle chooses to discharge is determined based on the optimal tendency of each electric vehicle.

[0009] In one possible implementation, the initial subsidy amount and initial propensity are input into the evolutionary game model, and the game process is optimized using the NSGA-II algorithm, including:

[0010] According to the evolutionary game model, the initial subsidy amount and initial propensity are updated to obtain the updated subsidy amount and updated propensity;

[0011] The updated subsidy amount and the updated propensity are optimized by the NSGA-Ⅱ algorithm to obtain the optimized subsidy amount and the optimized propensity;

[0012] Inputting the optimized subsidy amount and the optimized propensity into the evolutionary game model, and updating the optimized subsidy amount and the optimized propensity;

[0013] When the subsidy amounts for all substations no longer change, the game result is obtained.

[0014] In one possible implementation, the process of optimizing the game process using the NSGA-II algorithm includes:

[0015] Encode the updated subsidy amount and the updated propensity to generate the initial population;

[0016] Calculate the fitness of each individual according to the objective function;

[0017] The replication dynamic equation is used to adjust the proportion of each subsidy amount and each preference degree;

[0018] Generate new populations through crossover and mutation operations;

[0019] Determine the Pareto front solution based on non-dominated sorting and crowding;

[0020] When the Pareto frontier solution no longer changes, the optimal subsidy amount and the optimal propensity are selected from the Pareto frontier solution to obtain the optimized subsidy amount and the optimized propensity.

[0021] In one possible implementation, based on the evolutionary game model, the process of updating the initial subsidy amount and initial propensity includes:

[0022] Calculate the number of electric vehicles required in each district based on the initial subsidy amount and the revenue of each district;

[0023] According to the initial preference of electric vehicles for each area, the number of electric vehicles that choose each area is determined;

[0024] When the number of electric vehicles in each district is insufficient, the initial subsidy amount will be increased;

[0025] The increased initial subsidy amount is sent to each electric vehicle, and a propensity of each electric vehicle determined according to the increased initial subsidy amount is obtained.

[0026] In one possible implementation, the process of obtaining the initial preference of electric vehicles for selecting each station area includes:

[0027] Calculate the benefits of charging electric vehicles in each area based on the initial subsidy amount and rank the benefits of electric vehicles;

[0028] Sending the sorting results to the electric vehicle;

[0029] Obtain the initial inclination of electric vehicles for selecting each substation; wherein the initial inclination is determined by the electric vehicles according to the sorting results.

[0030] In one possible implementation, the calculation formula for the revenue of the substation is:

[0031] U i (s i ,x i )=β i s i -α i x i

[0032] Where s i The amount of subsidy provided to station i, x i is the number of electric vehicles discharged in station i, α i and β i are the benefit coefficient and cost coefficient of area i respectively;

[0033] The formula for calculating the benefits of electric vehicles is:

[0034] U j (s i )=γ j s i -c j

[0035] Where, γ j and c j are subsidy benefit coefficient and discharge cost respectively, s i The amount of subsidy provided to district i.

[0036] In one possible implementation, the replication dynamic equation is:

[0037]

[0038] Where, is the average revenue of all electric vehicles, is the average revenue of all substations, x ij The proportion of electric vehicle j to select the discharge area i, y i Subsidy amount s provided to station i i The ratio of U i (s i , x i ) is the income of the area, U j(s i )Benefits of electric vehicles.

[0039] In one possible implementation, a subsidy strategy for each substation is formulated based on the predicted electricity load, including:

[0040] Obtain the predicted power load; the power load is predicted by the Trans-LSTM module;

[0041] Determine the peak electricity consumption period based on the predicted electricity load;

[0042] The initial subsidy amount for each district will be determined based on the district’s revenue, the revenue of electric vehicles, and carbon emissions.

[0043] In a second aspect, an embodiment of the present invention provides a vehicle-grid interactive multi-station scheduling device integrating evolutionary game, including:

[0044] The initial subsidy formulation module is used to formulate the subsidy strategy for each substation based on the predicted electricity load; the subsidy strategy includes the subsidy period and the initial subsidy amount for each substation;

[0045] The game module is used to obtain the initial preference of electric vehicles for each substation during peak electricity consumption hours, input the initial subsidy amount and initial preference into the evolutionary game model, and optimize the game process using the NSGA-II algorithm to obtain the game results. The game results include the optimal subsidy amount for each substation and the optimal preference of each electric vehicle. The evolutionary game model uses maximizing the benefits of the substation, maximizing the benefits of electric vehicles, and minimizing carbon emissions as its objective functions.

[0046] The scheduling module is used to formulate the discharge price of electric vehicles in each area according to the optimal subsidy amount of each area, and to determine the area where each electric vehicle chooses to discharge according to the optimal tendency of each electric vehicle.

[0047] In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method in the first aspect or any possible implementation of the first aspect is implemented.

[0048] In an embodiment of the present invention, a subsidy strategy is used to guide electric vehicles to discharge to power distribution areas during peak hours, thereby reducing the peak load of the power distribution area and improving the operating efficiency and stability of the power grid. Specifically, an evolutionary game model is used to dynamically adjust the subsidy amount for the power distribution area and the propensity of electric vehicles. The NSGA-II algorithm further optimizes these subsidies and guides electric vehicles to select the optimal power distribution area for discharge, improving the flexibility and adaptability of scheduling. This achieves a comprehensive optimization of the power distribution area's revenue, the revenue of electric vehicles, and carbon emissions, achieving a multi-objective balance. By optimizing the scheduling strategy, carbon emissions in the power distribution area are reduced, achieving environmental protection goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flowchart for implementing the vehicle-grid interactive multi-station scheduling method based on the fusion evolutionary game provided by an embodiment of the present invention;

[0050] Figure 2 This is a logic block diagram of a multi-station scheduling method for vehicle-grid interaction based on fusion evolutionary game provided by an embodiment of the present invention;

[0051] Figure 3a : is a load comparison diagram of the substation C1 before and after scheduling provided by an embodiment of the present invention;

[0052] Figure 3b : is a load comparison diagram of the substation C2 before and after scheduling provided by an embodiment of the present invention;

[0053] Figure 4a This is a comparison chart of carbon emissions of the substation C1 before and after scheduling provided by an embodiment of the present invention;

[0054] Figure 4b This is a comparison chart of carbon emissions of the substation C2 before and after scheduling provided by an embodiment of the present invention;

[0055] Figure 5a 3. This is a cost comparison diagram of the substation C1 before and after scheduling provided by an embodiment of the present invention;

[0056] Figure 5b 3 is a cost comparison diagram of the substation C2 before and after scheduling provided by an embodiment of the present invention;

[0057] Figure 6 1. It is a structural diagram of a multi-station scheduling device for vehicle-grid interaction integrating evolutionary game provided by an embodiment of the present invention;

[0058] Figure 7 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] During peak hours, the load on the grid increases, impacting the grid's efficiency and stability. Utilizing electric vehicles to discharge power at the grid can alleviate this load. Traditional dispatching methods struggle to effectively address this challenge because they are typically based on fixed rules or simple optimization algorithms, lacking flexibility and adaptability, and fail to fully consider the behavior and preferences of electric vehicle users.

[0060] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0061] See also Figure 1 , which shows a flowchart of the implementation of the vehicle-grid interactive multi-station scheduling method based on the fusion evolutionary game provided by an embodiment of the present invention, which is detailed as follows:

[0062] Step 101: Formulate a subsidy strategy for each substation based on the predicted electricity load; wherein the subsidy strategy includes a subsidy period and an initial subsidy amount for each substation.

[0063] In the present application, a controller is also included. The controller is the execution body, and each area and each electric vehicle are enabled to interact through the controller to perform scheduling control of each electric vehicle between each area.

[0064] In one possible implementation, a subsidy strategy for each substation is formulated based on the predicted electricity load, including:

[0065] Obtain the predicted power load; the power load is predicted by the Trans-LSTM module;

[0066] Determine the peak electricity consumption period based on the predicted electricity load;

[0067] The initial subsidy amount for each district will be determined based on the district’s revenue, the revenue of electric vehicles, and carbon emissions.

[0068] In this embodiment, historical electricity load and meteorological data are first obtained, and the historical electricity load and meteorological data are input into the trained Trans-LSTM module to obtain the predicted value of the electricity load. By analyzing the predicted load data, the time period with higher load is identified. Usually, the peak load period is certain specific time periods in a day, such as morning and evening. The benefits obtained by the substation during the discharge process include the power support obtained by feeding the electric energy in the battery of the electric vehicle back to the power grid when it is not in use, thereby reducing the cost of purchasing electricity. The benefits of electric vehicles include the amount of subsidies and other economic returns obtained by electric vehicles during the discharge process. It is necessary to ensure that the subsidy amount is sufficient to attract electric vehicle users to participate. By guiding electric vehicles to discharge during peak hours, the carbon emissions of the substation are reduced. The reduction in carbon emissions is an important goal of the subsidy strategy.

[0069] Step 102: During peak electricity consumption hours, obtain the initial preference of electric vehicles for each substation, input the initial subsidy amount and initial preference into the evolutionary game model, and optimize the game process using the NSGA-II algorithm to obtain the game result; the game result includes the optimal subsidy amount for each substation and the optimal preference for each electric vehicle. The evolutionary game model takes maximizing the benefits of the substation, maximizing the benefits of the electric vehicles, and minimizing carbon emissions as its objective functions.

[0070] In this embodiment, the initial inclination of electric vehicles for each substation refers to the initial preference of each electric vehicle for each substation. This inclination can be based on multiple factors, such as the subsidy amount of the substation, the charging demand of the electric vehicle, the load situation of the substation, etc. The evolutionary game model dynamically adjusts the strategy by simulating the interaction between the substation and the electric vehicle to achieve the optimal scheduling result. The NSGA-Ⅱ algorithm is a multi-objective optimization algorithm that can find the Pareto optimal solution in multi-objective optimization problems. Through the NSGA-Ⅱ algorithm, the comprehensive optimization of substation revenue, electric vehicle revenue and carbon emissions can be achieved to achieve a balance between multiple objectives. After optimization through the evolutionary game model and the NSGA-Ⅱ algorithm, the optimal subsidy amount for each substation and the optimal inclination of each electric vehicle are obtained. The evolutionary game model takes the maximum revenue of the substation, the maximum revenue of the electric vehicle and the minimum carbon emissions as the objective function to ensure that the optimization result is balanced among multiple objectives.

[0071] In one possible implementation, the process of obtaining the initial preference of electric vehicles for selecting each area includes:

[0072] Calculate the benefits of charging electric vehicles in each area based on the initial subsidy amount and rank the benefits of electric vehicles;

[0073] Sending the sorting results to the electric vehicle;

[0074] Obtain the initial inclination of electric vehicles for selecting each substation; wherein the initial inclination is determined by the electric vehicles according to the sorting results.

[0075] In this embodiment, the initial subsidy amount is the initial subsidy amount provided to each electricity distribution center during peak hours. The benefits of charging at each distribution center are calculated for each electric vehicle based on the initial subsidy amount and other relevant factors (such as charging costs and discharge benefits). The benefits can be expressed as a numerical value, reflecting the economic advantages of charging at a particular distribution center. The calculated benefits of each distribution center are sorted to determine the order of preference for each electric vehicle. Distribution centers with higher benefits are ranked higher, indicating that the electric vehicle is more inclined to choose these distribution centers for charging. The sorting results are sent to each electric vehicle to inform them of the order of benefits of charging at different distribution centers. Based on the received sorting results, the electric vehicle determines its initial preference for each distribution center. This preference can be represented as a list or vector, where each element represents the degree of preference for a distribution center. Based on the sorting results, the electric vehicle selects the distribution center with the highest benefit as the first choice, the distribution center with the second highest benefit as the second choice, and so on. This process can be automatic or manual.

[0076] In one possible implementation, the initial subsidy amount and initial propensity are input into the evolutionary game model, and the game process is optimized using the NSGA-II algorithm, including:

[0077] According to the evolutionary game model, the initial subsidy amount and initial propensity are updated to obtain the updated subsidy amount and updated propensity;

[0078] The updated subsidy amount and the updated propensity are optimized by the NSGA-Ⅱ algorithm to obtain the optimized subsidy amount and the optimized propensity;

[0079] Inputting the optimized subsidy amount and the optimized propensity into the evolutionary game model, and updating the optimized subsidy amount and the optimized propensity;

[0080] When the subsidy amounts for all substations no longer change, the game result is obtained.

[0081] In this embodiment, first, an initial subsidy amount is set for each substation, and the number of electric vehicles required for the substation is calculated based on the initial subsidy amount and the revenue function, and the initial subsidy amount is published for invitation;

[0082] Then, after each electric vehicle receives subsidy offers from different regions, it calculates the potential benefits of discharging the electric vehicle in each region based on the benefit function. Based on the benefit ranking, it selects the region with the highest benefit and updates its preference list to indicate its preference for each region.

[0083] Secondly, after receiving the electric vehicle selection feedback, the district compares the current number of participating electric vehicles with the required number. If the number of electric vehicles does not meet the district's needs, the district will increase the subsidy amount, recalculate the required number of electric vehicles, continue to issue new subsidy amounts and invite bids;

[0084] The above process is repeated again until one of the two conditions is met: ① The number of electric vehicles obtained by the district meets the requirement, and the subsidy amount remains unchanged. ② After the subsidy amount is adjusted, the calculated number of electric vehicles is reduced compared to the previous plan. At this point, it is believed that further increasing the subsidy will not bring more electric vehicles, so the subsidy amount is not changed;

[0085] Finally, when the subsidy amount of all the stations remains unchanged, the process ends, e.g. Figure 2 shown.

[0086] Figure 2 These are the main steps of this application, not all the contents, in which the execution of the main controller is omitted.

[0087] In this process, the strategic goal of the power grid is to attract a sufficient number of electric vehicles to discharge by adjusting the subsidy amount, and the electric vehicle party will choose the power grid that will maximize its own benefits for discharge based on the subsidy amount and other factors.

[0088] In one possible implementation, the process of optimizing the game process using the NSGA-II algorithm includes:

[0089] Encode the updated subsidy amount and the updated propensity to generate the initial population;

[0090] Calculate the fitness of each individual according to the objective function;

[0091] The replication dynamic equation is used to adjust the proportion of each subsidy amount and each preference degree;

[0092] Generate new populations through crossover and mutation operations;

[0093] Determine the Pareto front solution based on non-dominated sorting and crowding;

[0094] When the Pareto frontier solution no longer changes, the optimal subsidy amount and the optimal propensity are selected from the Pareto frontier solution to obtain the optimized subsidy amount and the optimized propensity.

[0095] In this embodiment, NSGA-II is a multi-objective optimization algorithm that helps optimize multiple objectives in the game between electric vehicles and power distribution centers. Each participant in the evolutionary game has their own strategy and payoff function. The dynamic evolution of the system can be described by replicating dynamic equations. NSGA-II can find the optimal strategy combination within the framework of multi-objective optimization. Each individual represents a strategy combination. The fitness of each individual, i.e., the payoff of each strategy, is calculated. The strategy ratio is dynamically adjusted by replicating dynamic equations, making strategies with higher payoffs more popular within the group and strategies with lower payoffs less popular, simulating the dynamic game between electric vehicles and power distribution centers. New strategy combinations are generated using crossover and mutation operations. This process generates new electric vehicle selection strategies and power distribution center subsidy strategies, thereby introducing diversity into the evolutionary process. Non-dominated sorting is used to find the Pareto frontier solution, a strategy combination that optimizes the payoffs of both electric vehicles and power distribution centers. After each evolutionary generation, non-dominated solutions are retained, and the diversity of solutions is ensured through congestion calculations. When the Pareto frontier solutions of multiple generations of strategy combinations do not change significantly, the algorithm converges and the game strategy reaches a stable equilibrium.

[0096] In one possible implementation, the replication dynamic equation is:

[0097]

[0098] Where, is the average revenue of all electric vehicles, U i is the average revenue of all substations, x ij The proportion of electric vehicle j to select the discharge area i, y i Subsidy amount s provided to station i i The ratio of U i (s i , x i ) is the income of the area, U j (s i )Benefits of electric vehicles.

[0099] In this embodiment, when and When , the system reaches dynamic equilibrium, and the strategy at this time is a stable strategy.

[0100] In one possible implementation, based on the evolutionary game model, the process of updating the initial subsidy amount and initial propensity includes:

[0101] Calculate the number of electric vehicles required in each district based on the initial subsidy amount and the revenue of each district;

[0102] According to the initial preference of electric vehicles for each area, the number of electric vehicles that choose each area is determined;

[0103] When the number of electric vehicles in each district is insufficient, the initial subsidy amount will be increased;

[0104] The increased initial subsidy amount is sent to each electric vehicle, and a propensity of each electric vehicle determined according to the increased initial subsidy amount is obtained.

[0105] In this embodiment, the initial subsidy amount is the initial subsidy provided to each substation during peak electricity consumption hours. Each substation benefits from V2G technology, including reduced electricity purchase costs and increased power support. The number of electric vehicles required for each substation is calculated based on the initial subsidy amount and substation benefits. For example, if a substation has higher benefits, more electric vehicles may be needed to participate in discharging to maximize benefits. Electric vehicles determine their preference for each substation based on the initial subsidy amount and other factors (such as charging costs and discharging benefits). The number of electric vehicles selected for each substation is determined based on the electric vehicles' initial preference. If a substation does not have enough electric vehicles to meet its demand, the current subsidy amount may not be sufficient to attract enough electric vehicles. To attract more electric vehicles to that substation, the initial subsidy amount for that substation is increased. For example, the subsidy amount can be increased from 0.8 yuan to 1.0 yuan. The increased subsidy amount is sent to each electric vehicle to inform them of the new subsidy amount. Electric vehicles recalculate the benefits of charging in each substation based on the new subsidy amount and update their preference for each substation. For example, if the subsidy amount for a particular substation is increased, electric vehicles may be more inclined to choose that substation.

[0106] In one possible implementation, the calculation formula for the revenue of the substation is:

[0107] U i (s i ,x i )=β i s i -α i x i

[0108] Where s i The amount of subsidy provided to station i, x i is the number of electric vehicles discharged in station i, α i and β i are the benefit coefficient and cost coefficient of area i respectively;

[0109] The formula for calculating the benefits of electric vehicles is:

[0110] U j (s i )=γ j s i -c j

[0111] Where, γ j and c j are subsidy benefit coefficient and discharge cost respectively, s i The amount of subsidy provided to district i.

[0112] In one possible implementation, the carbon emissions calculation formula is:

[0113]

[0114] Where ρ is the electricity carbon emission coefficient, and P is the actual load of the substation.

[0115] Step 103: The discharge price of the electric vehicle in each area is determined based on the optimal subsidy amount of each area, and the area selected for discharge by each electric vehicle is determined based on the optimal propensity of each electric vehicle.

[0116] In this embodiment, the optimal subsidy amount is the optimal subsidy amount for each area, obtained through optimization using an evolutionary game model and the NSGA-II algorithm. The discharge price is determined based on the optimal subsidy amount, and can be expressed as a numerical value reflecting the economic benefit of discharging an electric vehicle in a particular area. The optimal propensity is the optimal preference of each electric vehicle for each area, obtained through optimization using the evolutionary game model and the NSGA-II algorithm. Based on the optimal propensity, the area selected for discharge by each electric vehicle is determined. The optimal propensity can be expressed as a list or vector, where each element represents the electric vehicle's preference for a particular area.

[0117] In an embodiment of the present invention, a subsidy strategy is used to guide electric vehicles to discharge to power distribution areas during peak hours, thereby reducing the peak load of the power distribution area and improving the operating efficiency and stability of the power grid. Specifically, an evolutionary game model is used to dynamically adjust the subsidy amount for the power distribution area and the propensity of electric vehicles. The NSGA-II algorithm further optimizes these subsidies and guides electric vehicles to select the optimal power distribution area for discharge, improving the flexibility and adaptability of scheduling. This achieves a comprehensive optimization of the power distribution area's revenue, the revenue of electric vehicles, and carbon emissions, achieving a multi-objective balance. By optimizing the scheduling strategy, carbon emissions in the power distribution area are reduced, achieving environmental protection goals.

[0118] In other possible implementations, one or more stages in the evolutionary game model and the NSGA-II algorithm may adopt other forms. The present invention is mainly described by taking the evolutionary game model and the NSGA-II algorithm as examples.

[0119] In order to better understand the present invention, the above process is described in detail below with reference to a specific example. The numerical values ​​used in this example are only examples, and users can make corresponding changes according to actual needs.

[0120] The present invention uses the measured data of a certain city, including the total load of the substation, as well as meteorological data such as temperature, humidity, wind speed, wind direction, and rainfall. The data set covers 192 days from January 1 to July 11, 2023, with a sampling interval of 15 minutes (i.e., 96 sampling points per day). Two substations were selected, and their geographical location information was obtained from the open source map platform. The substation consumes more electricity during peak load, and the vehicle-grid interaction is used to reduce its peak power consumption.

[0121] According to the day-ahead forecast results, the peak load period of C1 and C2 is set to 9:00 to 14:00, and V2G dispatch is carried out in the substations during this period. The initial value of V2G subsidy is set to 0.8 yuan. The comparison of the load of the substations before and after dispatch is shown in the figure below. Figure 3a 、 Figure 3b After V2G dispatching, the load of C1 and C2 areas during peak load hours was reduced by an average of about 6%.

[0122] This paper dispatches the system with the purpose of reducing the load of the substation while reducing its own carbon emissions. Therefore, the carbon emission reduction of the substation can be regarded as a positive benefit. Calculate the carbon emissions under V2G dispatch and without dispatch, as follows: Figure 4a 、 Figure 4b After V2G dispatching, the carbon emissions of areas C1 and C2 were reduced by 6.55% and 5.97% respectively.

[0123] Under V2G dispatch, the cost of the substation is the sum of the electricity purchase fee and the subsidy fee, while in the absence of dispatch, the cost of the substation is only the electricity purchase fee. Figure 5a 、 Figure 5b The results show that after V2G scheduling, the costs of stations C1 and C2 increased by 1.31% and 1.19% respectively, which means that a smaller cost increase is exchanged for a reduction in load peak and carbon emissions.

[0124] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0125] The following are device embodiments of the present invention. For details not fully described therein, reference may be made to the corresponding method embodiments described above.

[0126] Figure 6 The following is a schematic diagram of the structure of a multi-zone scheduling device for vehicle-grid interaction based on fusion evolutionary game provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0127] like Figure 6As shown, the vehicle-grid interactive multi-station scheduling device 6 integrating evolutionary game includes:

[0128] The initial subsidy formulation module 61 is used to formulate a subsidy strategy for each substation based on the predicted power load; wherein the subsidy strategy includes a subsidy period and an initial subsidy amount for each substation;

[0129] Game module 62 is used to obtain the initial preference of electric vehicles for each substation during peak electricity consumption hours, input the initial subsidy amount and initial preference into the evolutionary game model, and optimize the game process using the NSGA-II algorithm to obtain the game results. The game results include the optimal subsidy amount for each substation and the optimal preference of each electric vehicle. The evolutionary game model uses maximizing the benefits of the substation, maximizing the benefits of the electric vehicles, and minimizing carbon emissions as its objective functions.

[0130] The scheduling module 63 is used to formulate the discharge price of electric vehicles in each area according to the optimal subsidy amount of each area, and determine the area where each electric vehicle chooses to discharge according to the optimal tendency of each electric vehicle.

[0131] In a possible implementation, the game module 62 may also be used to:

[0132] According to the evolutionary game model, the initial subsidy amount and initial propensity are updated;

[0133] The updated subsidy amount and updated propensity are optimized through the NSGA-Ⅱ algorithm;

[0134] Inputting the optimized subsidy amount and the optimized propensity into the evolutionary game model, and updating the optimized subsidy amount and the optimized propensity;

[0135] When the subsidy amounts for all substations no longer change, the game result is obtained.

[0136] In a possible implementation, the game module 62 may also be used to:

[0137] Encode the updated subsidy amount and the updated propensity to generate the initial population;

[0138] Calculate the fitness of each individual according to the objective function;

[0139] The replication dynamic equation is used to adjust the proportion of each subsidy amount and each preference degree;

[0140] Generate new populations through crossover and mutation operations;

[0141] Determine the Pareto front solution based on non-dominated sorting and crowding;

[0142] When the Pareto frontier solution no longer changes, the optimal subsidy amount and the optimal propensity are selected from the Pareto frontier solution to obtain the optimized subsidy amount and the optimized propensity.

[0143] In a possible implementation, the game module 62 may also be used to:

[0144] Calculate the number of electric vehicles required in each district based on the initial subsidy amount and the revenue of each district;

[0145] According to the initial preference of electric vehicles for each area, the number of electric vehicles that choose each area is determined;

[0146] When the number of electric vehicles in each district is insufficient, the initial subsidy amount will be increased;

[0147] The increased initial subsidy amount is sent to each electric vehicle, and a propensity of each electric vehicle determined according to the increased initial subsidy amount is obtained.

[0148] In a possible implementation, the game module 62 may also be used to:

[0149] Calculate the benefits of charging electric vehicles in each area based on the initial subsidy amount and rank the benefits of electric vehicles;

[0150] Sending the sorting results to the electric vehicle;

[0151] Obtain the initial inclination of electric vehicles for selecting each substation; wherein the initial inclination is determined by the electric vehicles according to the sorting results.

[0152] In a possible implementation, the initial subsidy formulation module 61 may also be used to:

[0153] Obtain the predicted power load; the power load is predicted by the Trans-LSTM module;

[0154] Determine the peak electricity consumption period based on the predicted electricity load;

[0155] The initial subsidy amount for each district will be determined based on the district’s revenue, the revenue of electric vehicles, and carbon emissions.

[0156] Figure 7 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 7 As shown, the electronic device 7 of this embodiment includes a processor 70 and a memory 71. The memory 71 stores a computer program 72. When the processor 70 executes the computer program 72, the steps of the above-described method embodiments are implemented. Alternatively, when the processor 70 executes the computer program 72, the functions of the modules / units in the above-described device embodiments are implemented.

[0157] Exemplarily, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 72 in the electronic device 7.

[0158] The electronic device 7 may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of the electronic device 7 and does not constitute a limitation of the electronic device 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 7 may also include input and output devices, network access devices, buses, etc.

[0159] For the sake of convenience and brevity, the division of the above functional modules / units is only used as an example. In actual applications, the above functions can be assigned to different functional modules / units as needed. The above modules / units can be implemented in the form of hardware, software, or a combination of hardware and software.

[0160] In the above embodiments, the descriptions of each embodiment have their own focus. For parts not described or recorded in detail in one embodiment, please refer to the relevant descriptions of other embodiments. Unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features of different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0161] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A multi-station scheduling method for vehicle-grid interaction based on fusion evolutionary game, characterized by: include: Formulate a subsidy strategy for each substation based on the predicted electricity load; wherein the subsidy strategy includes a subsidy period and an initial subsidy amount for each substation; During peak electricity consumption periods, the initial preference of electric vehicles for each substation is obtained, the initial subsidy amount and the initial preference are input into an evolutionary game model, and the game process is optimized using the NSGA-II algorithm to obtain a game result; wherein the game result includes the optimal subsidy amount for each substation and the optimal preference of each electric vehicle. The evolutionary game model takes maximizing the benefits of the substation, maximizing the benefits of the electric vehicles, and minimizing carbon emissions as its objective function; The discharge price of electric vehicles in each area is determined based on the optimal subsidy amount of each area, and the area where each electric vehicle chooses to discharge is determined based on the optimal tendency of each electric vehicle.

2. The vehicle-grid interactive multi-station scheduling method based on fusion evolutionary game according to claim 1 is characterized in that: The process of inputting the initial subsidy amount and the initial propensity into the evolutionary game model and optimizing the game process through the NSGA-II algorithm includes: updating the initial subsidy amount and the initial propensity according to the evolutionary game model to obtain an updated subsidy amount and an updated propensity; The updated subsidy amount and the updated propensity are optimized by the NSGA-Ⅱ algorithm to obtain the optimized subsidy amount and the optimized propensity; Inputting the optimized subsidy amount and the optimized propensity into the evolutionary game model, and updating the optimized subsidy amount and the optimized propensity; When the subsidy amounts for all substations no longer change, the game result is obtained.

3. The vehicle-grid interactive multi-station scheduling method based on fusion evolutionary game according to claim 2 is characterized in that: The process of optimizing the game process by the NSGA-II algorithm includes: Encode the updated subsidy amount and the updated propensity to generate the initial population; Calculate the fitness of each individual according to the objective function; The replication dynamic equation is used to adjust the proportion of each subsidy amount and each preference degree; Generate new populations through crossover and mutation operations; Determine the Pareto front solution based on non-dominated sorting and crowding; When the Pareto frontier solution no longer changes, the optimal subsidy amount and the optimal propensity are selected from the Pareto frontier solution to obtain the optimized subsidy amount and the optimized propensity.

4. The vehicle-grid interactive multi-station scheduling method based on fusion evolutionary game according to claim 2 is characterized in that: The process of updating the initial subsidy amount and the initial propensity according to the evolutionary game model includes: Calculate the number of electric vehicles required for each district based on the initial subsidy amount and the revenue of each district; According to the initial preference of electric vehicles for each area, the number of electric vehicles that choose each area is determined; When the number of electric vehicles in each area is insufficient, the initial subsidy amount will be increased; The increased initial subsidy amount is sent to each electric vehicle, and a propensity of each electric vehicle determined according to the increased initial subsidy amount is obtained.

5. The vehicle-grid interactive multi-station scheduling method based on fusion evolutionary game according to claim 1 is characterized in that: The process of obtaining the initial inclination of the electric vehicle to select each station area includes: Calculating the benefits of charging the electric vehicles in each charging area based on the initial subsidy amount, and ranking the benefits of the electric vehicles; sending the sorting result to the electric vehicle; An initial tendency of the electric vehicle to select each station area is obtained; wherein the initial tendency is determined by the electric vehicle according to the ranking result.

6. The vehicle-grid interactive multi-station scheduling method based on fusion evolutionary game according to claim 4 or 5 is characterized in that: The calculation formula for the revenue of the station area is: U i (s i ,x i )=β i s i -a i x i Where s i The amount of subsidy provided to station i, x i is the number of electric vehicles discharged in station i, α i and β i are the benefit coefficient and cost coefficient of area i respectively; The calculation formula for the benefits of electric vehicles is: U j (s i )=γ j s i -c j Where, γ j and c j are subsidy benefit coefficient and discharge cost respectively, s i The amount of subsidy provided to district i.

7. The vehicle-grid interaction multi-station scheduling method based on fusion evolutionary game according to claim 3 is characterized in that: The replication dynamic equation is: Where, is the average revenue of all electric vehicles, is the average revenue of all substations, x ij The proportion of electric vehicle j to select the discharge area i, y i Subsidy amount s provided to station i i The ratio of U i (s i , x i ) is the income of the area, U j (s i )Benefits of electric vehicles.

8. The vehicle-grid interaction multi-station scheduling method based on fusion evolutionary game according to claim 1 is characterized in that: The subsidy strategy for the substation area is formulated based on the predicted electricity load, including: Obtaining a predicted power load; wherein the power load is predicted by a Trans-LSTM module; Determine the peak electricity consumption period based on the predicted electricity load; The initial subsidy amount for each district will be determined based on the district’s revenue, the revenue of electric vehicles, and carbon emissions.

9. A vehicle-grid interactive multi-station dispatching device integrating evolutionary game, characterized in that: include: An initial subsidy formulation module is used to formulate a subsidy strategy for each substation based on the predicted electricity load; wherein the subsidy strategy includes a subsidy period and an initial subsidy amount for each substation; A game module is used to obtain the initial propensity of electric vehicles to select each substation during peak electricity consumption hours, input the initial subsidy amount and the initial propensity into an evolutionary game model, and optimize the game process using the NSGA-II algorithm to obtain a game result; wherein the game result includes the optimal subsidy amount for each substation and the optimal propensity for each electric vehicle. The evolutionary game model takes maximizing the benefits of the substation, maximizing the benefits of the electric vehicles, and minimizing carbon emissions as its objective function; The scheduling module is used to formulate the discharge price of electric vehicles in each area according to the optimal subsidy amount of each area, and to determine the area where each electric vehicle chooses to discharge according to the optimal tendency of each electric vehicle.

10. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images