Electric vehicle charging and discharging scheduling methods, servers, and storage media

Abstract

This application provides a method, server, and storage medium for electric vehicle charging and discharging scheduling. The method includes: constructing a multi-objective optimization model and constraints on the decision variables in the multi-objective optimization model for electric vehicle charging and discharging scheduling tasks within a smart park; wherein the multi-objective optimization model includes a first optimization model for the power grid within the smart park, a second optimization model for charging stations within the smart park, and a third optimization model for electric vehicles contracted with charging stations; minimizing the net load variance of the power grid, the operating cost of the charging stations, and the total charging cost of the electric vehicles as optimization objectives, and solving the multi-objective optimization model in conjunction with the constraints to obtain the game equilibrium solution of the decision variables in the multi-objective optimization model; and executing the electric vehicle charging and discharging scheduling task based on the game equilibrium solution of the decision variables in the multi-objective optimization model to achieve a win-win situation for the "grid-station-vehicle" tripartite equilibrium.

Description

Technical Field

[0001] This application relates to the field of charge and discharge scheduling technology, and in particular to a charge and discharge scheduling method, server and storage medium for electric vehicles. Background Technology

[0002] New energy electric vehicles are being widely promoted and applied due to their advantages such as high efficiency, environmental friendliness, and energy conservation. The large-scale construction of charging piles and stations to match them is imperative. Smart parks, as micro-units of cities, are an important entry point for new infrastructure construction, providing convenient "parking and charging integration" services within their parking lots.

[0003] Currently, the task of scheduling electric vehicle charging in smart parks faces significant challenges: the charging load of electric vehicles is spatiotemporally random and intermittent, and the disorderly charging behavior of electric vehicles can have a negative impact on the power grid in smart parks. Summary of the Invention

[0004] In view of this, this application provides a charging and discharging scheduling method for electric vehicles, a server, and a storage medium.

[0005] Specifically, this application is implemented through the following technical solution: According to a first aspect of this application, a charging and discharging scheduling method for an electric vehicle is provided, comprising: For the electric vehicle charging and discharging scheduling task in a smart park, a multi-objective optimization model and constraints on the decision variables in the multi-objective optimization model are constructed; wherein, the multi-objective optimization model includes a first optimization model for the power grid in the smart park, a second optimization model for the charging stations in the smart park, and a third optimization model for the electric vehicles that have signed contracts with the charging stations; With the optimization objectives of minimizing the net load variance of the power grid in the first optimization model, the operating cost of charging stations in the second optimization model, and the total charging cost of electric vehicles in the third optimization model, the multi-objective optimization model is solved in combination with the constraints to obtain the game equilibrium solution of the decision variables in the multi-objective optimization model. The electric vehicle charging and discharging scheduling task is executed based on the game equilibrium solution of the decision variables in the multi-objective optimization model.

[0006] This application addresses the electric vehicle charging and discharging scheduling task within a smart park. By establishing contracts between charging stations and electric vehicles within the smart park, the disorderly charging behavior of electric vehicles is transformed into a coordinated and orderly charging and discharging behavior. Furthermore, it considers the balance of interests among the power grid, charging stations, and electric vehicles contracted with charging stations within the smart park. A multi-objective optimization model is constructed at the "network-station-vehicle" level, along with constraints on the decision variables within this model. Specifically, the multi-objective optimization model includes a first optimization model for the power grid within the smart park, a second optimization model for the charging stations within the smart park, and a third optimization model for the electric vehicles contracted with the charging stations.

[0007] Then, with the optimization objectives of minimizing the net load variance of the power grid in the first optimization model, the operating cost of charging stations in the second optimization model, and the total charging cost of electric vehicles in the third optimization model, the multi-objective optimization model is solved in combination with the constraints to obtain the game equilibrium solution of the decision variables in the multi-objective optimization model. Based on the game equilibrium solution of the decision variables in the multi-objective optimization model, the electric vehicle charging and discharging scheduling task is executed to effectively suppress the net load fluctuation of the power grid, reduce the operating cost of charging stations, and reduce the charging fees of electric vehicles that have signed contracts with charging stations, thereby achieving a win-win situation for the "grid-station-vehicle" tripartite equilibrium.

[0008] Optionally, the method further includes: Based on the historical load data of the power grid in the smart park, the historical charging and discharging data of the charging stations, and the historical charging and discharging data of the electric vehicles that have signed contracts with the charging stations, the values ​​of the decision variables in the multi-objective optimization model are predicted to obtain the predicted value set of the decision variables. Solving the multi-objective optimization model includes: According to the constraints of the decision variables in the multi-objective optimization model, multiple solutions for the decision variables are randomly selected from the predicted value set; Multiple rounds of iterative updates are performed based on multiple solutions to the decision variables to obtain a game equilibrium solution that satisfies the optimization objective of the multi-objective optimization model; wherein, the optimization objective of the multi-objective optimization model is to minimize the weighted sum of the following three factors: the net load variance of the power grid in the first optimization model, the operating cost of the charging station in the second optimization model, and the total charging cost of electric vehicles in the third optimization model.

[0009] In this application, the possible values ​​are predicted based on relevant historical data, and multiple solutions of the decision variable are randomly selected from the predicted value set according to the constraints for iterative solution, which helps to improve the solution efficiency.

[0010] Optionally, the step of performing multiple rounds of iterative updates based on multiple solutions to the decision variables includes: The population is initialized using multiple sets of solutions to the randomly selected decision variables; the population consists of multiple individuals, and the position vector of each individual represents a set of solutions to the decision variables. Repeat the following steps during each iteration until the preset number of iterations is reached: For an individual in the current population, the fitness value of that individual is determined based on the optimization objective value of the multi-objective optimization model corresponding to that individual; Select the best and second-best individuals based on the fitness values ​​of each individual in the current population; The position vectors of individuals in the current population are updated using the position vector of the optimal individual to obtain a new population; and / or, the position vectors of individuals in the current population are updated using the position vectors of the optimal individual and the position vectors of the second-best individual to obtain a recombined population; wherein, the population obtained by combining at least one of the new population and the recombined population with the optimal individual is the current population in the next iteration process.

[0011] In this application, through an iterative optimization process based on newly added populations and / or recombined populations, the solution process of the multi-objective optimization model can approach global equilibrium from local equilibrium.

[0012] Optionally, updating the position vectors of individuals in the current population using the position vector of the optimal individual to obtain a new population includes: Based on the first position vector difference between the position vector of the optimal individual and the position vector of the individual in the current population during the current iteration, update the velocity vector of the individual in the current population during the current iteration. The position vector of the newly added individual in the new population is obtained by updating the velocity vector of the individual in the current population with the updated velocity vector of the individual. Optionally, the updated velocity vector of the individual in the current population is determined by a weighted sum of the velocity vector of the individual in the current iteration process and a first product, where the first product is the product of the difference in the first velocity vector and a preset random number; the position vector of the newly added individual is the sum of the updated velocity vector of the individual in the current population and the position vector of the individual in the current iteration process.

[0013] In this application, during each iteration, the position vector of the optimal individual can be used to perform a random search to obtain a new population, so as to enable the population to find the best among the best after multiple iterations.

[0014] Optionally, updating the position vectors of individuals in the current population using the position vectors of the best and second-best individuals to obtain a recombined population includes: The position vectors of the optimal individual and the second-best individual are fused to obtain a recombined position vector. The recombined position vector represents a set of recombined solutions for the decision variable, one part of which comes from the optimal individual and the other part comes from the second-best individual. Based on the second position vector difference between the recombined position vector and the position vector of the individual in the current population during the current iteration process, and the Gaussian distribution probability of the individual, update the velocity vector of the individual in the current population during the current iteration process; The position vector of an individual is updated using the updated velocity vector of an individual in the current population to obtain the position vector of the recombined individual in the recombined population. Optionally, the updated velocity vector of an individual in the current population is determined by a weighted sum of the velocity vector of that individual in the current iteration process and the second product, where the second product is the product of the difference in the second velocity vector and the Gaussian probability of that individual; the position vector of the recombined individual is the sum of the updated velocity vector of an individual in the current population and the position vector of that individual in the current iteration process.

[0015] In this application, during each iteration, the position vectors of the optimal individual and the second-best individual can be recombined to obtain a recombined population. This avoids ignoring other potential second-best individuals in the population besides the optimal individual, increases the diversity of the population, and improves the solution capability.

[0016] Optionally, the game equilibrium solution is determined based on the position vector of the individual with the largest fitness value in the current population during the optimal round of iteration; wherein the fitness value is negatively correlated with the optimization objective value of the multi-objective optimization model.

[0017] Optionally, the decision variables in the multi-objective optimization model include at least one of the following: Net load power of the power grid in the first optimization model; The second optimization model includes the electricity purchase cost of the charging station, the electricity saving cost of electric vehicles contracted with the charging station from disordered charging to orderly charging and discharging, and the electricity saving cost of distributed power generation connected to the charging station. The third optimization model includes the electricity consumption cost of electric vehicles contracted with the charging station traveling from the park parking lot to the charging station, the charging service cost of the charging station, the electricity consumption cost of electric vehicles contracted with the charging station traveling from the charging station to the park parking lot, and the revenue from selling the stored electricity contracted with the charging station. If the smart park combines the parking lot and the charging station into one, achieving "parking and charging integration", then this cost is negligible.

[0018] This application considers the balance of interests among the power grid, charging stations, and electric vehicles that have signed contracts with the charging stations in a smart park. It determines the decision variables of a multi-objective optimization model from the three levels of "grid-station-vehicle" to solve the problem, so as to achieve a win-win situation for all three parties.

[0019] Optionally, the third optimization model may also include target coefficients that influence the decision variables in the third optimization model; The target coefficient includes at least one of the following: a discount coefficient and a tiered reward coefficient for the charging service cost of the charging station, and a tiered reward coefficient for the number of times the electricity is sold; wherein the discount coefficient and the tiered reward coefficient for the number of times the electricity is sold are both less than 1, and the tiered reward coefficient for the number of times the electricity is sold is greater than 1.

[0020] In this embodiment, electric vehicles are compensated by setting discount coefficients and reward coefficients to reduce the charging cost of electric vehicles.

[0021] The constraints on the decision variables in the multi-objective optimization model include at least one of the following: The power generation of the power grid at any given moment is equal to the algebraic sum of the power consumption and the stored power; wherein, the stored power is a positive value when the energy storage module connected to the charging station is in the charging state, and a negative value when the energy storage module is in the discharging state; The charging and discharging power of the electric vehicle is within the preset power range; The total power of disorderly charging of electric vehicles under contract in the smart park is the same as the total power of orderly charging and discharging of electric vehicles under contract in the smart park indicated by the game equilibrium solution. The energy storage module connected to the charging station stores electricity within a preset range; The current drawn by the electric vehicle when it connects to the charging station is less than the preset allowable current value. The voltage deviation of the charging station connected to the power grid is within the preset range; The maximum active power of the power supply line is less than the preset power threshold. And the local load peak-valley difference of the power grid is less than the preset local load peak-valley difference threshold.

[0022] This application considers the balance of interests among the power grid, charging stations, and electric vehicles that have signed contracts with the charging stations in a smart park. It determines the constraints of the multi-objective optimization model from the three levels of "network-station-vehicle" to meet the needs of the three parties.

[0023] According to a second aspect of this application, a server is provided, including a memory, a processor, and executable instructions stored in the memory and executable on the processor; Wherein, when the processor executes the executable instructions, it implements the steps in the method as described in any one of the first aspects.

[0024] According to a third aspect of this application, a computer-readable storage medium is provided, having stored thereon computer instructions that, when executed by a processor, implement the steps of the method described in any one of the first aspects.

[0025] It should be understood that the above general description and the following detailed description are explanatory only and do not limit this application. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this application.

[0027] Figure 1 This is a schematic flowchart illustrating a charging and discharging scheduling method for an electric vehicle as shown in this application.

[0028] Figure 2 This is a schematic diagram of the optimization objectives corresponding to the first optimization model, the second optimization model, and the third optimization model shown in this application.

[0029] Figure 3 This is a schematic diagram of the process for solving a multi-objective optimization model as shown in this application.

[0030] Figure 4 This is a schematic diagram of the structure of a server shown in this application. Detailed Implementation

[0031] This application will now be described in detail, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described below do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0032] The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0033] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0034] The promotion of electric vehicles helps alleviate problems such as the energy crisis, environmental pollution, and global warming. Smart parks, as micro-units of cities, are an important entry point for new infrastructure construction, providing convenient "parking and charging integration" services within their parking lots. Currently, the scheduling of electric vehicle charging within smart parks faces significant challenges: the spatiotemporal randomness and intermittency of electric vehicle charging loads also cause randomness and intermittency in the discharge of distributed power sources connected to charging stations. Disorderly charging behavior by electric vehicles can negatively impact the power grid within smart parks. For example, large-scale integration of electric vehicles and distributed power sources can lead to increased grid load capacity, a larger peak-to-valley difference in electricity consumption, or exacerbated load imbalances, all of which may threaten the safe operation of the power grid.

[0035] To address the problems in related technologies, this application provides a charging and discharging scheduling method for electric vehicles. Specifically, for electric vehicle charging and discharging scheduling tasks within a smart park, this method transforms the disorderly charging behavior of electric vehicles into a coordinated and orderly charging and discharging behavior by having charging stations in the smart park sign contracts with electric vehicles. Furthermore, it considers the balance of interests among the power grid, charging stations, and electric vehicles that have signed contracts with charging stations in the smart park. A multi-objective optimization model is constructed from three levels: "network-station-vehicle," along with constraints on the decision variables in the multi-objective optimization model. The multi-objective optimization model includes a first optimization model for the power grid within the smart park, a second optimization model for the charging stations within the smart park, and a third optimization model for the electric vehicles that have signed contracts with the charging stations.

[0036] Then, with the optimization objectives of minimizing the net load variance of the power grid in the first optimization model, the operating cost of charging stations in the second optimization model, and the total charging cost of electric vehicles in the third optimization model, the multi-objective optimization model is solved in combination with the constraints to obtain the game equilibrium solution of the decision variables in the multi-objective optimization model. Based on the game equilibrium solution of the decision variables in the multi-objective optimization model, the electric vehicle charging and discharging scheduling task is executed to effectively suppress the net load fluctuation of the power grid, reduce the operating cost of charging stations, and reduce the charging fees of electric vehicles that have signed contracts with charging stations, thereby achieving a win-win situation for the "grid-station-vehicle" tripartite equilibrium.

[0037] The electric vehicle charging and discharging scheduling method provided in this application can be executed by a server. In one example, the server includes a memory and a processor. The memory stores executable instructions for the electric vehicle charging and discharging scheduling method, so that the processor can implement the electric vehicle charging and discharging scheduling method when executing the executable instructions. In another example, the electric vehicle charging and discharging scheduling method can be packaged into a computer program product and integrated into the server.

[0038] The server can be located within a smart park. It can acquire load data related to the power grid, charging and discharging data related to charging stations, and charging and discharging data of electric vehicles charging within the smart park. This data is used to schedule the charging and discharging of electric vehicles. In one example, the server can communicate with both electric vehicles and charging stations, enabling it to schedule the charging and discharging process of electric vehicles. For instance, if a charging station has multiple charging piles, the server can schedule electric vehicles to charge at an idle charging pile, improving the utilization rate of the charging piles.

[0039] Please see Figure 1 , Figure 1 This application provides a flowchart illustrating a charging and discharging scheduling method for an electric vehicle, assuming the method is executed by a server in a smart park. The method includes: In step 101, for the electric vehicle charging and discharging scheduling task carried out in the smart park, a multi-objective optimization model and constraints on the decision variables in the multi-objective optimization model are constructed; wherein, the multi-objective optimization model includes a first optimization model for the power grid in the smart park, a second optimization model for the charging stations in the smart park, and a third optimization model for the electric vehicles that have signed contracts with the charging stations.

[0040] In step 102, the optimization objectives are to minimize the net load variance of the power grid in the first optimization model, the operating cost of the charging station in the second optimization model, and the total charging cost of electric vehicles in the third optimization model. The multi-objective optimization model is solved in combination with the constraints to obtain the game equilibrium solution of the decision variables in the multi-objective optimization model.

[0041] In step 103, the electric vehicle charging and discharging scheduling task is executed based on the game equilibrium solution of the decision variables in the multi-objective optimization model.

[0042] In this application, by having charging stations in smart parks sign contracts with electric vehicles, the disorderly charging behavior of electric vehicles is transformed into a coordinated and orderly charging and discharging behavior. This approach considers the balance of interests among the power grid, charging stations, and electric vehicles that have signed contracts with charging stations in the smart park. A multi-objective optimization model is constructed from the three levels of "network-station-vehicle". By solving the multi-objective optimization model, a game equilibrium solution is obtained that can effectively suppress the net load fluctuation of the power grid, reduce the operating costs of charging stations, and reduce the charging fees of electric vehicles that have signed contracts with charging stations. This solution is then used to execute the electric vehicle charging and discharging scheduling task in the smart park, achieving a win-win situation for the "network-station-vehicle" tripartite balance.

[0043] The multi-objective optimization model includes a first optimization model for the power grid within the smart park, a second optimization model for the charging stations within the smart park, and a third optimization model for electric vehicles that have signed contracts with the charging stations. It is understood that the number of the first, second, and third optimization models can be specifically set according to the actual application scenario of the smart park, and this embodiment does not impose any restrictions on this.

[0044] Smart parks include, but are not limited to, different scenarios such as industrial parks, commercial parks, or residential areas.

[0045] The multi-objective optimization model is a weighted sum of the first, second, and third optimization models. The optimization objective of the multi-objective optimization model is to minimize the weighted sum.

[0046] In one example, Equation (1) shows a multi-objective optimization model for electric vehicle charging and discharging scheduling tasks in a smart park, which considers the three levels of the power grid, charging stations, and electric vehicles that have signed contracts with charging stations.

[0047] (1).

[0048] Where F represents a multi-objective optimization model. This represents the set of first-order optimization models at the power grid level, which may include multiple different first-order optimization models for the power grid within a smart park. , Indicates the first The first optimization model takes values ​​in the range [1, n]. This represents a set of third-order optimization models at the electric vehicle level, which may include multiple different third-order optimization models for electric vehicles contracted with the charging station. , Indicates the first A third optimization model, with values ​​in the range [1, m]. This represents a set of second-order optimization models at the charging station level, which may include multiple different second-order optimization models for charging stations within a smart park. , Indicates the first A second optimization model, with values ​​in the range [1, l].

[0049] At the power grid level, considering the need for stable power supply, a first optimization model is constructed with the goal of minimizing the net load variance of the power grid. The decision variable of the first optimization model is the net load power of the power grid.

[0050] In one example, Equation (2) shows the representation of the first optimization model constructed with the goal of minimizing the net load variance of the power grid: (2).

[0051] Where t is a certain moment when the electric vehicle participates in the coordinated scheduling, and T is a coordinated scheduling period, which is the charging and discharging period of the electric vehicle. This represents the first optimization model with the objective of minimizing the net load variance of the power grid. for Net load power of the power grid at any time for The average value of the net load power of the power grid at any given time.

[0052] At the charging station level, considering the need for operating costs, a second optimization model is constructed with the goal of minimizing the operating costs of the charging station. The decision variables of the second optimization model are the electricity purchase cost of the charging station, the electricity saving cost of electric vehicles that have signed contracts with the charging station from disordered charging to orderly charging and discharging, and the electricity saving cost of distributed power generation connected to the charging station.

[0053] In one example, Equation (3) shows the representation of the second optimization model with the goal of minimizing the operating cost of the charging station: (3).

[0054] in, This represents the second optimization model with the objective of minimizing the operating cost of charging stations. The cost of purchasing electricity from the power grid; Cost savings from distributed power generation connected to charging stations; Electricity costs saved by electric vehicles that have signed contracts with the charging stations, transitioning from disordered charging to orderly charging and discharging.

[0055] At the electric vehicle level, considering the charging cost requirements of electric vehicles, a third optimization model is constructed with the goal of minimizing the total charging cost of electric vehicles through a contract compensation incentive mechanism. The decision variables in the third optimization model include the electricity consumption cost of an electric vehicle contracted with the charging station traveling to the charging station, the charging service cost of the charging station, the electricity consumption cost of an electric vehicle contracted with the charging station traveling from the charging station to its destination, and the revenue from selling the electricity stored under the contract with the charging station.

[0056] The third optimization model, based on a contractual compensation incentive mechanism, further includes target coefficients influencing the decision variables within the model. These target coefficients include at least one of the following: a discount coefficient and a tiered reward coefficient for charging service costs at charging stations, and a tiered reward coefficient for electricity sales revenue. Both the discount coefficient and the tiered reward coefficient for charging frequency are less than 1, while the tiered reward coefficient for electricity sales frequency is greater than 1. By signing contracts with charging stations within the park, electric vehicles can charge at discounted prices, participate in demand response, and reduce charging costs.

[0057] In one example, Equation (4) shows the representation of the third optimization model constructed with minimizing the total charging cost of electric vehicles as the optimization objective: (4).

[0058] in, This represents the third optimization model with the objective of minimizing the total charging cost of electric vehicles. To take into account the electricity consumption cost of electric vehicles during their journey to charging stations; The cost of charging services at charging stations. The discount coefficient for electric vehicles that have signed contracts with the charging station ( <1), The tiered reward coefficient for the number of charging sessions for electric vehicles that have signed contracts with the charging stations ( <1); The cost of electricity consumed by an electric vehicle to travel from a charging station to its destination; The revenue generated from selling the electricity stored by electric vehicles that have signed contracts with the charging stations during their idle state. The tiered reward coefficient for the number of times electric vehicles that have signed contracts with the charging stations sell electricity ( >1).

[0059] The constraints on the decision variables in the multi-objective optimization model include equality constraints and / or inequality constraints. The constraints on the decision variables in the multi-objective optimization model include at least one of the following: 1. The power generation and power consumption of the power grid at any given moment are the same. In other words, the power generation of the power grid at any given moment is equal to the algebraic sum of the power consumption and the stored power; wherein, the stored power is a positive value when the energy storage module connected to the charging station is in a charging state, and a negative value when the energy storage module is in a discharging state.

[0060] Equation (5) shows the equality constraints between the power generation, power consumption, and power storage of the power grid at the same time: (5).

[0061] in, for Net load power of the power grid at any time The power of the basic load (the load of air conditioning, lighting, and management equipment in the smart park) at time t. Let be the total power generation of the distributed generation source at time t. Let be the power of the energy storage module at time t (negative for discharging, positive for charging). The total power of the electric vehicles that have signed a contract with the charging station at time t (discharge is a negative value, charging is a positive value).

[0062] 2. The charging and discharging power of the electric vehicle is within the preset power range.

[0063] The charging and discharging power limits for electric vehicles contracted with the charging station are shown in Equation (6): (6). Among them, and These represent the lower and upper limits of the charging / discharging / electrical power of electric vehicles, respectively.

[0064] 3. The total power of disorderly charging of electric vehicles registered in the smart park is the same as the total power of orderly charging and discharging of electric vehicles registered in the smart park indicated by the game equilibrium solution.

[0065] Equation (7) shows the equality constraint that the total power of disordered charging of electric vehicles is equal to the total power of ordered charging of electric vehicles indicated by the game equilibrium solution: (7). Among them, This represents the total power of unordered charging of electric vehicles. This represents the total power of the orderly charging of electric vehicles as indicated by the game equilibrium solution. When the contracted electric vehicles are not in use, they are treated as energy storage devices and discharged in an orderly manner; the discharge power is then included in the total power of the energy storage module.

[0066] 4. The energy storage module connected to the charging station stores electricity within the preset range.

[0067] Equation (8) shows the equality and inequality constraints of the energy storage module: (8).

[0068] in, This indicates the energy storage module's capacity, where This indicates its charging efficiency. This indicates its discharge efficiency. and These are the lower and upper limits for the energy storage module's capacity. An energy storage module can only discharge or charge per unit of time. , A binary variable representing its charging and discharging state.

[0069] 5. The current of the electric vehicle connected to the charging station is less than the preset allowable current value.

[0070] As shown in equation (9), the inequality constraint for current is: (9). Among them, any access of electric vehicles to charging stations The current value at each point must not exceed the maximum allowable current value. The electric vehicle access point is one of the three phases (A, B, and C) of the charging station. , , These are the currents connected to each phase, for The current value of the midline.

[0071] 6. The voltage deviation of the charging station connected to the power grid is within the preset range.

[0072] To ensure power quality, connecting charging stations to the power grid may cause voltage deviations in the grid; therefore, these voltage deviations must be limited to a certain range. Equation (10) illustrates the inequality constraint on voltage deviations: (10). Among them, For charging stations The voltage; The rated voltage of the power distribution network; This represents the maximum permissible voltage offset.

[0073] 7. The maximum active power (i.e. peak power) of the power supply line is less than the preset power threshold.

[0074] To ensure stable power supply, the active power of the power supply lines must not exceed the maximum allowable power flow through the lines. Equation (11) shows the inequality constraint regarding the active power of the lines: (11). Among them, Let be the active power of line l; This represents the maximum power that is allowed to flow through line l.

[0075] 8. The local load peak-to-valley difference of the power grid is less than the preset local load peak-to-valley difference threshold.

[0076] This application addresses the issue of potential new peak loads during off-peak charging periods by adding local peak-valley difference constraints to the power grid, thereby suppressing new load spikes during off-peak charging periods. Equation (12) illustrates the inequality constraints related to suppressing local load spikes: (12). Among them, Let t be the load peak-to-valley difference. This represents the maximum net load power of the power grid at time t. This represents the minimum net load power of the power grid at time t. To achieve the optimal local load peak-to-valley difference, This is the local peak-valley difference constraint coefficient, and >l.

[0077] After constructing the multi-objective optimization model and the constraints of the decision variables in the multi-objective optimization model, please refer to Figure 2 The server aims to minimize the net load variance of the power grid in the first optimization model, the operating cost of charging stations in the second optimization model, and the total charging cost of electric vehicles in the third optimization model. It solves the multi-objective optimization model by combining the constraints to obtain the game equilibrium solution of the decision variables in the multi-objective optimization model, thus achieving balance among the three optimization models. The multi-objective optimization model is a weighted sum of the first, second, and third optimization models; please refer to formula (1). The optimization objective of the multi-objective optimization model is to minimize the weighted sum.

[0078] Based on the historical load data of the power grid in the smart park, the historical charging and discharging data of the charging stations, and the historical charging and discharging data of the electric vehicles that have signed contracts with the charging stations, the values ​​of the decision variables in the multi-objective optimization model can be predicted to obtain the predicted value set of the decision variables.

[0079] From the power grid perspective, the basic load (air conditioning, lighting, management equipment) of the power grid in the smart park can be analyzed based on historical load data during different time periods (e.g., different seasons or different months). Furthermore, the maximum load increase power of the power grid within a specific unit of time (e.g., 24 hours a day) can be analyzed to obtain power grid load analysis results. Subsequently, based on the power grid load analysis results, several possible values ​​of the power grid's net load power can be predicted, resulting in a predicted set of values ​​for the power grid's net load power.

[0080] At the charging station level, the power supply patterns of distributed power sources connected to the charging station can be analyzed based on historical charging and discharging data, as well as the changes in charging and discharging power of energy storage modules connected to the charging station, to obtain charging and discharging analysis results. Then, based on these results, several possible values ​​can be predicted for the charging station's electricity purchase cost, the energy savings for electric vehicles contracted with the charging station from disordered charging to orderly charging and discharging, and the energy savings for distributed power generation connected to the charging station. This yields a set of predicted values ​​for the charging station's electricity purchase cost, the energy savings for electric vehicles contracted with the charging station from disordered charging to orderly charging and discharging, and the energy savings for distributed power generation connected to the charging station.

[0081] From the perspective of electric vehicles, the charging and discharging historical data of electric vehicles contracted with the charging station can be used to analyze the charging and discharging patterns of these vehicles, as well as the peak load power patterns of disordered charging, thus obtaining electric vehicle charging and discharging analysis results. Furthermore, based on these results, several possible values ​​corresponding to multiple decision variables in the third optimization model can be predicted, resulting in a predicted set of values ​​for the electricity consumption cost of electric vehicles contracted with the charging station traveling from the parking lot to the charging station, a predicted set of values ​​for the charging service cost of the charging station, a predicted set of values ​​for the electricity consumption cost of electric vehicles contracted with the charging station traveling from the charging station to the parking lot, and a predicted set of values ​​for the revenue from selling the stored electricity contracted with the charging station.

[0082] In solving a multi-objective optimization model, the server can randomly select multiple solutions for the decision variables from the predicted value set according to the constraints of the decision variables in the multi-objective optimization model. These multiple solutions satisfy the constraints. Then, multiple rounds of iterative updates are performed based on the multiple solutions to obtain a game equilibrium solution that satisfies the optimization objective of the multi-objective optimization model. The optimization objective of the multi-objective optimization model is to minimize the weighted sum of the net load variance of the power grid in the first optimization model, the operating cost of charging stations in the second optimization model, and the total charging cost of electric vehicles in the third optimization model. In this application, predicting possible values ​​based on relevant historical data and randomly selecting multiple solutions for the decision variables from the predicted value set according to the constraints for iterative solving improves the solution efficiency.

[0083] In one possible implementation, please refer to Figure 3 , Figure 3 A flowchart illustrating the solution of a multi-objective optimization model is shown.

[0084] In step 201, the multi-objective optimization model is initialized.

[0085] The server randomly selects multiple solutions for the decision variables from the predicted value set according to the constraints of the decision variables in the multi-objective optimization model, and initializes the population using the randomly selected multiple solutions for the decision variables. The population includes multiple individuals, and the position vector of each individual represents a set of solutions for the decision variables. The initial value of the velocity vector of each individual is 0.

[0086] In step 202, for an individual in the current population, the fitness value of that individual is determined based on the optimization objective value of the multi-objective optimization model corresponding to that individual.

[0087] Please refer to formula (1). The optimization objective of the multi-objective optimization model is to minimize the weighted sum of the optimization objectives of the first optimization model (net load variance of the power grid), the optimization objective of the second optimization model (operating cost of charging stations), and the optimization objective of the third optimization model (total charging cost of electric vehicles).

[0088] For any given individual, the server calculates the objective value of the multi-objective optimization model based on a set of solutions to the decision variables corresponding to that individual, and then determines the fitness value of that individual based on the calculated objective value. In one example, the fitness value is the reciprocal of the objective value, in which case the fitness value and the objective value are negatively correlated. In another example, the fitness value is the objective value, in which case the fitness value and the objective value are positively correlated.

[0089] In step 203, the best and second-best individuals are selected based on the fitness values ​​of each individual in the current population.

[0090] The individuals in the current population can be sorted according to their fitness values ​​to select the best and second-best individuals. For example, individuals with fitness values ​​in the first interval can be identified as the best individuals, and individuals with fitness values ​​in the second interval can be identified as the second-best individuals. The specific values ​​of the first and second intervals can be set according to the actual application scenario.

[0091] In one example, the fitness value is the reciprocal of the optimization objective value, let the fitness value be... Then there is =1 / F, where F is the optimization objective value obtained by solving formula (1). Based on the fitness values ​​of each individual in the current population, individuals with fitness values ​​below 0.5 can be discarded; individuals with fitness values ​​between 0.5 and 0.8 can be considered as suboptimal individuals; and individuals with fitness values ​​between 0.8 and 1 can be considered as optimal individuals.

[0092] It is understandable that there is no limit to the number of the best and second-best individuals determined in step 203, and the specific settings can be made according to the actual application scenario.

[0093] In step 204, the position vectors of individuals in the current population are updated using the position vector of the optimal individual to obtain a new population; and / or, the position vectors of individuals in the current population are updated using the position vectors of the optimal individual and the position vectors of the second-best individual to obtain a recombined population; wherein, at least one of the new population and the recombined population, combined with the optimal individual, forms the current population in the next iteration process.

[0094] During the iterative solution process, new populations and / or recombined populations are generated to find game equilibrium solutions and avoid getting trapped in local optima. New populations are added based on the best individual in each iteration to avoid local optima and increase global diversity. Recombined populations are generated by recombining the best and second-best individuals in each iteration to integrate richer population information, improve solution capabilities, quickly find game equilibrium solutions, and achieve global convergence.

[0095] It is understandable that updating an individual's position vector is the process of updating a set of solutions for the decision variables corresponding to that individual.

[0096] In step 205, determine whether the current iteration number has reached the preset iteration number; if not, repeat steps 202 to 204 in each iteration; if yes, execute step 206.

[0097] In step S06, the game equilibrium solution of the decision variables in the multi-objective optimization model is output based on the position vector of the best individual in the current population.

[0098] In this embodiment, through an iterative optimization process based on the newly added population and / or recombined population, the solution process of the multi-objective optimization model can approach the global equilibrium from local equilibrium.

[0099] Here is an explanation of the new population: In each iteration, the position vector of the best individual can be used to perform a random search to obtain the new population, so as to achieve the goal of finding the best among the best after multiple iterations.

[0100] The server can update the velocity vector of the individual in the current population during the current iteration process based on the first position vector difference between the position vector of the optimal individual and the position vector of the individual in the current population during the current iteration process; then, it uses the updated velocity vector of the individual in the current population to update the position vector of that individual, thereby obtaining the position vector of the newly added individual in the new population.

[0101] In one example, the updated velocity vector of an individual in the current population is determined by a weighted sum of the velocity vector of that individual in the current iteration process and a first product, wherein the first product is the product of the difference in the first velocity vector and a preset random number, wherein the preset random number is greater than 0 and less than 1; the position vector of the newly added individual is the sum of the updated velocity vector of the individual in the current population and the position vector of that individual in the current iteration process.

[0102] The recombined population is explained below: In each iteration, the position vectors of the optimal and suboptimal individuals can be recombined to obtain a recombined population. This avoids ignoring other potential suboptimal individuals besides the optimal one, increasing population diversity and improving solution capability. The server fuses the position vectors of the optimal and suboptimal individuals to obtain a recombined position vector. This recombined position vector represents a set of recombined solutions for the decision variable, with one part coming from the optimal individual and the other from the suboptimal individual. Then, based on the second position vector difference between the recombined position vector and the position vector of an individual in the current population during the current iteration, and the Gaussian distribution probability of that individual, the velocity vector of the individual in the current population during the current iteration is updated. Finally, the updated velocity vector of the individual in the current population is used to update the position vector of that individual, resulting in the position vector of the recombined individual in the recombined population. In this embodiment, the optimal and suboptimal individuals are recombined based on a Gaussian distribution probability model in each iteration to generate a recombined population for the next iteration, which can integrate richer population information and improve solution capability.

[0103] In one example, the updated velocity vector of an individual in the current population is determined by a weighted sum of the individual's velocity vector and the second product during the current iteration, where the second product is the product of the difference in the second velocity vector and the individual's Gaussian probability; the position vector of the recombined individual is the sum of the updated velocity vector of the individual in the current population and the individual's position vector during the current iteration.

[0104] In one example, at the k-th iteration, the current population P(k) = (P1(k), P2(k), ..., P2(k)) with n individuals in the w-dimensional solution space. n (k)), Pi(k)=[P i1 (k), P i2 (k), ..., P iw (k)] T v represents the position vector of the i-th individual; i (k)=[v i1 (k), v i2 (k), ...,v iw (k)] T S represents the velocity vector of the i-th individual. i (k)=[S i1 (k),S i2 (k), ..., S iw (k)] T This represents the position vector of the optimal individual. The current population in the (k+1)th iteration includes the newly added population determined based on the optimal individual in the kth iteration, and the recombined population determined based on the optimal and second-best individuals in the kth iteration.

[0105] The position vector and velocity vector of the newly added individuals in the new population can be calculated based on the following formulas (13) and (15), and the position vector and velocity vector of the recombined individuals in the recombined population can be calculated based on the following formulas (14) and (15).

[0106] (13); (14); (15).

[0107] in, , , This represents the weight; r is a random number between 0 and 1; Let v be the Gaussian distribution probability of the position vector of the i-th individual; v be the velocity vector. iwIt reflects an individual's ability to search and traverse in w-dimensional space, and affects the step size for updating an individual's position. This represents the recombined position vector after the fusion of the optimal and suboptimal individuals in the k-th iteration. For example, the recombined position vector represents a set of recombined solutions for the decision variable, where 50% of the recombined solutions come from the optimal individual and the other 50% come from the suboptimal individual.

[0108] In step 206, after reaching the required number of iterations, the server outputs the game equilibrium solution for the decision variables in the multi-objective optimization model based on the position vector of the optimal individual in the current population. In one example, if the fitness value is negatively correlated with the objective value of the multi-objective optimization model, the server outputs the game equilibrium solution for the decision variables based on the position vector of the individual with the highest fitness value in the current population. In another example, if the fitness value is positively correlated with the objective value of the multi-objective optimization model, the server outputs the game equilibrium solution for the decision variables based on the position vector of the individual with the lowest fitness value in the current population.

[0109] After obtaining the game equilibrium solution of the decision variables in the multi-objective optimization model, the server can execute the electric vehicle charging and discharging scheduling task based on the game equilibrium solution of the decision variables in the multi-objective optimization model. This effectively suppresses the net load fluctuation of the power grid, reduces the operating costs of charging stations, and reduces the charging fees of electric vehicles that have signed contracts with charging stations, achieving a win-win situation for the "grid-station-vehicle" tripartite balance. At the power grid level, the orderly charging and discharging of electric vehicles that have signed contracts with charging stations alleviates the negative impact on the power grid caused by the randomness and intermittency of distributed power generation and the disorderly charging behavior of electric vehicles, reducing net load fluctuations and peak-valley differences, and improving the load characteristics of the power grid. At the park charging station level, the charging behavior of electric vehicles that have signed contracts with charging stations at off-peak prices can reduce electricity purchase and operation and maintenance costs. At the level of contracted electric vehicles, by signing contracts with park charging stations, they can charge at preferential low prices and participate in demand response, reducing charging costs.

[0110] Taking a residential area as an example, the smart park involves not only the charging and discharging of electric vehicles but also the electricity consumption of residents. This can be achieved through optimized scheduling of the controllable loads of contracted residents in the smart park, enabling orderly charging during off-peak hours and peak-hour discharge. When contracted electric vehicles have discharge capabilities, they are treated as energy storage loads, combined with interruptible loads (such as air conditioners, electric heaters, radiators, and fans) and movable loads (such as washing machines, disinfection cabinets, and robot vacuums) to form the controllable loads for residents. This allows contracted residents to actively participate in demand response and engage in multi-party game-theoretic scheduling. Ultimately, this maximizes the renewable energy absorption rate, minimizes electricity costs for residents, and reduces peak-valley load differences within the smart park, while ensuring residents' electricity comfort.

[0111] For the electricity consumption tasks of residents in smart parks, a target optimization model and constraints on the decision variables in the target optimization model can be constructed. The target optimization model includes a first model for the power grid in the smart park, a second model for contracted residents in the smart park, and a third model for electric vehicles contracted with charging stations. The optimization objective is to minimize the net load variance of the power grid in the first model, the electricity cost of contracted residents in the second model, and the total charging cost of electric vehicles in the third model. The target optimization model is solved in conjunction with the constraints to obtain the game equilibrium solution of the decision variables in the target optimization model. Based on the game equilibrium solution of the decision variables in the target optimization model, the contracted vehicle charging task in the smart park is executed, achieving the minimum total charging cost of contracted electric vehicles, the minimum operating cost of charging stations, and the minimum net load variance of the power grid, while ensuring the comfort of contracted vehicle owners.

[0112] It is easy to understand that the above-described solutions can be combined when there is no conflict, and these will not be listed one by one in this application.

[0113] In some embodiments, please refer to Figure 4 This application also provides a server, including a memory 10, a processor 20, and executable instructions stored on the memory 10 and executable on the processor 20; Wherein, when the processor 20 executes the executable instructions, it is used to: For the electric vehicle charging and discharging scheduling task in a smart park, a multi-objective optimization model and constraints on the decision variables in the multi-objective optimization model are constructed; wherein, the multi-objective optimization model includes a first optimization model for the power grid in the smart park, a second optimization model for the charging stations in the smart park, and a third optimization model for the electric vehicles that have signed contracts with the charging stations; With the optimization objectives of minimizing the net load variance of the power grid in the first optimization model, the operating cost of charging stations in the second optimization model, and the total charging cost of electric vehicles in the third optimization model, the multi-objective optimization model is solved in combination with the constraints to obtain the game equilibrium solution of the decision variables in the multi-objective optimization model. The electric vehicle charging and discharging scheduling task is executed based on the game equilibrium solution of the decision variables in the multi-objective optimization model.

[0114] The processor 20 includes, but is not limited to, a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or a field-programmable gate array (FPGA).

[0115] The memory 10 may include at least one type of storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc.

[0116] The processor 20 is also used for: Based on the historical load data of the power grid in the smart park, the historical charging and discharging data of the charging stations, and the historical charging and discharging data of the electric vehicles that have signed contracts with the charging stations, the values ​​of the decision variables in the multi-objective optimization model are predicted to obtain the predicted value set of the decision variables. According to the constraints of the decision variables in the multi-objective optimization model, multiple solutions for the decision variables are randomly selected from the predicted value set; Multiple rounds of iterative updates are performed based on multiple solutions to the decision variables to obtain a game equilibrium solution that satisfies the optimization objective of the multi-objective optimization model; wherein, the optimization objective of the multi-objective optimization model is to minimize the weighted sum of the following three factors: the net load variance of the power grid in the first optimization model, the operating cost of the charging station in the second optimization model, and the total charging cost of electric vehicles in the third optimization model.

[0117] The processor 20 is specifically used for: The population is initialized using multiple sets of solutions to the randomly selected decision variables; the population consists of multiple individuals, and the position vector of each individual represents a set of solutions to the decision variables. Repeat the following steps during each iteration until the preset number of iterations is reached: For an individual in the current population, the fitness value of that individual is determined based on the optimization objective value of the multi-objective optimization model corresponding to that individual; Select the best and second-best individuals based on the fitness values ​​of each individual in the current population; The position vectors of individuals in the current population are updated using the position vector of the optimal individual to obtain a new population; and / or, the position vectors of individuals in the current population are updated using the position vectors of the optimal individual and the position vectors of the second-best individual to obtain a recombined population; wherein, the population obtained by combining at least one of the new population and the recombined population with the optimal individual is the current population in the next iteration process.

[0118] The processor 20 is specifically used to: update the velocity vector of the individual in the current population during the current iteration process based on the first difference between the position vector of the optimal individual and the position vector of the individual in the current population during the current iteration process; and update the position vector of the individual using the updated velocity vector of the individual in the current population to obtain the position vector of the newly added individual in the newly added population.

[0119] The updated velocity vector of an individual in the current population is determined by a weighted sum of the velocity vector of that individual in the current iteration process and a first product, where the first product is the product of the first difference and a preset random number; the position vector of the newly added individual is the sum of the updated velocity vector of the individual in the current population and the position vector of that individual in the current iteration process.

[0120] The processor 20 is specifically configured to: fuse the position vectors of the optimal individual and the second-best individual to obtain a recombined position vector, wherein the recombined position vector represents a set of recombined solutions for the decision variable, a portion of which comes from the optimal individual and the other portion from the second-best individual; update the velocity vector of the individual in the current population during the current iteration process based on the second difference between the recombined position vector and the position vector of the individual in the current population during the current iteration process, and the Gaussian distribution probability of the individual; and update the position vector of the individual using the updated velocity vector of the individual in the current population to obtain the position vector of the recombined individual in the recombined population.

[0121] The updated velocity vector of an individual in the current population is determined by a weighted sum of the velocity vector of that individual in the current iteration process and the second product, where the second product is the product of the second difference and the Gaussian probability of that individual; the position vector of the recombined individual is the sum of the updated velocity vector of the individual in the current population and the position vector of that individual in the current iteration process.

[0122] The game equilibrium solution is determined based on the position vector of the individual with the largest fitness value in the current population during the optimal iteration process; wherein, the fitness value is negatively correlated with the optimization objective value of the multi-objective optimization model.

[0123] The decision variables in the multi-objective optimization model include at least one of the following: the net load power of the power grid in the first optimization model; the electricity purchase cost of the charging station, the electricity saving cost of electric vehicles contracted with the charging station from disordered charging to orderly charging and discharging, and the electricity saving cost of distributed power generation connected to the charging station in the second optimization model; the electricity consumption cost of electric vehicles contracted with the charging station traveling to the charging station, the charging service cost of the charging station, the electricity consumption cost of electric vehicles contracted with the charging station traveling from the charging station to their destination, and the electricity sales revenue of the stored electricity contracted with the charging station in the third optimization model.

[0124] The third optimization model also includes target coefficients that affect the decision variables in the third optimization model; the target coefficients include at least one of the following: a discount coefficient and a tiered reward coefficient for the charging service cost of the charging station, and a tiered reward coefficient for the number of times the electricity is sold; wherein the discount coefficient and the tiered reward coefficient for the number of times the electricity is sold are both less than 1, and the tiered reward coefficient for the number of times the electricity is sold is greater than 1.

[0125] The constraints of the decision variables in the multi-objective optimization model include at least one of the following: (1) the power generation of the power grid at the same time is equal to the algebraic sum of the power consumption and the power storage; (2) the charging and discharging power of the electric vehicle is within the preset power range; (3) the total power of the disordered charging of the electric vehicle is the same as the total power of the orderly charging of the electric vehicle indicated by the game equilibrium solution; (4) the amount of electricity stored in the energy storage module connected to the charging station is within the preset amount of electricity; (5) the current of the electric vehicle connected to the charging station is less than the preset allowable current value; (6) the voltage deviation of the charging station connected to the power grid is within the preset range; (7) the maximum active power (i.e. peak power) of the line used for power supply is less than the preset power threshold; and (8) the local load peak-valley difference of the power grid is less than the preset local load peak-valley difference threshold.

[0126] The specific implementation process of the functions and roles of each component in the above-mentioned equipment can be found in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0127] Accordingly, this application also provides a computer program product, including a computer program that, when executed by a processor, is used to implement the above-described method.

[0128] Accordingly, this application also provides a non-transitory computer-readable storage medium including instructions, such as a memory including instructions that can be executed by a processor of a device to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0129] A non-transitory computer-readable storage medium that, when the instructions in the storage medium are executed by the processor of a terminal, enables a server to perform the above-described method.

[0130] The embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, the program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0131] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0132] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0133] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0134] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0135] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0136] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0137] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A charging and discharging scheduling method for an electric vehicle, characterized in that, include: For the electric vehicle charging and discharging scheduling task in a smart park, a multi-objective optimization model and constraints on the decision variables in the multi-objective optimization model are constructed; wherein, the multi-objective optimization model includes a first optimization model for the power grid in the smart park, a second optimization model for the charging stations in the smart park, and a third optimization model for the electric vehicles that have signed contracts with the charging stations; Based on the analysis of the historical load data of the power grid in the smart park, the basic load of the power grid in different time periods is analyzed, and the maximum load growth power of the power grid in a certain unit time in different time periods is analyzed. Based on the analysis results, the values ​​of the decision variables in the first optimization model are predicted to obtain the predicted value set of the decision variables. Based on the analysis of the charging and discharging historical data of the charging station, the power supply pattern of the distributed power source connected to the charging station is analyzed, and the charging and discharging power change of the energy storage module connected to the charging station is analyzed. Based on the analysis results, the values ​​of the decision variables in the second optimization model are predicted to obtain the predicted value set of the decision variables. Based on the analysis of historical charging and discharging data of electric vehicles contracted with the charging station, the charging and discharging patterns of these vehicles are analyzed, as well as the peak load power patterns of disordered charging of these vehicles. The values ​​of decision variables in the third optimization model are predicted based on the analysis results, resulting in a set of predicted values ​​for these decision variables. With the optimization objective of minimizing the net load variance of the power grid in the first optimization model, the operating cost of the charging station in the second optimization model, and the total charging cost of electric vehicles in the third optimization model, multiple solutions to the decision variables are randomly selected from the set of predicted values ​​in the multi-objective optimization model, according to the constraints of the decision variables in the multi-objective optimization model. Multiple rounds of iterative updates are performed based on these multiple solutions to obtain a game equilibrium solution that satisfies the optimization objective of the multi-objective optimization model. The electric vehicle charging and discharging scheduling task is executed based on the game equilibrium solution of the decision variables in the multi-objective optimization model.

2. The method according to claim 1, characterized in that, The optimization objective of the multi-objective optimization model is to minimize the dynamic adaptive weighted sum of the following three factors: the net load variance of the power grid in the first optimization model, the operating cost of charging stations in the second optimization model, and the total charging cost of electric vehicles in the third optimization model.

3. The method according to claim 2, characterized in that, The step of performing multiple rounds of iterative updates based on multiple solutions to the decision variables includes: The population is initialized using multiple sets of solutions to the randomly selected decision variables; the population consists of multiple individuals, and the position vector of each individual represents a set of solutions to the decision variables. Repeat the following steps during each iteration until the preset number of iterations is reached: For an individual in the current population, the fitness value of that individual is determined based on the optimization objective value of the multi-objective optimization model corresponding to that individual; Select the best and second-best individuals based on the fitness values ​​of each individual in the current population; The position vectors of individuals in the current population are updated using the position vector of the optimal individual to obtain a new population; and / or, the position vectors of individuals in the current population are updated using the position vectors of the optimal individual and the position vectors of the second-best individual to obtain a recombined population; wherein, the population obtained by combining at least one of the new population and the recombined population with the optimal individual is the current population in the next iteration process.

4. The method according to claim 3, characterized in that, The step of updating the position vectors of individuals in the current population using the position vector of the optimal individual to obtain a new population includes: Based on the first position vector difference between the position vector of the optimal individual and the position vector of the individual in the current population during the current iteration, update the velocity vector of the individual in the current population during the current iteration. The position vector of an individual is updated using the updated velocity vector of an individual in the current population, thus obtaining the position vector of the newly added individual in the new population.

5. The method according to claim 4, characterized in that, The updated velocity vector of an individual in the current population is determined by the weighted sum of the velocity vector of that individual in the current iteration process and the first product, where the first product is the product of the difference in the first velocity vector and a preset random number. The position vector of the newly added individual is the sum of the updated velocity vector of the individual in the current population and the position vector of that individual in the current iteration process.

6. The method according to claim 3, characterized in that, The step of updating the position vectors of individuals in the current population using the position vectors of the best and second-best individuals to obtain a recombined population includes: The position vectors of the optimal individual and the second-best individual are fused to obtain a recombined position vector. The recombined position vector represents a set of recombined solutions for the decision variable, one part of which comes from the optimal individual and the other part comes from the second-best individual. Based on the second position vector difference between the recombined position vector and the position vector of the individual in the current population during the current iteration process, and the Gaussian distribution probability of the individual, update the velocity vector of the individual in the current population during the current iteration process; The position vector of an individual is updated using the updated velocity vector of that individual in the current population, thus obtaining the position vector of the recombined individual in the recombined population.

7. The method according to claim 6, characterized in that, The updated velocity vector of an individual in the current population is determined based on the weighted sum of the velocity vector and the second product of the individual in the current iteration process. The second product is the product of the difference in the second velocity vector and a preset random number. The position vector of the recombined individual is the sum of the updated velocity vector of the individual in the current population and the position vector of that individual during the current iteration.

8. The method according to claim 3, characterized in that, The game equilibrium solution is determined based on the position vector of the individual with the largest fitness value in the current population during the optimal iteration process; wherein, the fitness value is negatively correlated with the optimization objective value of the multi-objective optimization model.

9. The method according to claim 1, characterized in that, The decision variables in the multi-objective optimization model include at least one of the following: Net load power of the power grid in the first optimization model; The second optimization model includes the electricity purchase cost of the charging station, the electricity saving cost of electric vehicles contracted with the charging station from disordered charging to orderly charging and discharging, and the electricity saving cost of distributed power generation connected to the charging station. The third optimization model includes the electricity consumption cost of an electric vehicle that has signed a contract with the charging station to travel to the charging station, the charging service cost of the charging station, the electricity consumption cost of an electric vehicle that has signed a contract with the charging station to travel from the charging station to its destination, and the revenue from selling the electricity stored in the contract with the charging station.

10. The method according to claim 9, characterized in that, The third optimization model also includes target coefficients that affect the decision variables in the third optimization model; The target coefficients include at least one of the following: a discount coefficient for the charging service cost of the charging station and a tiered reward coefficient for the number of charging sessions, and a tiered reward coefficient for the number of electricity sales for the electricity sales revenue. The discount coefficient and the tiered reward coefficient for charging times are both less than 1, while the tiered reward coefficient for selling electricity times is greater than 1.

11. The method according to claim 1, characterized in that, The constraints on the decision variables in the multi-objective optimization model include at least one of the following: The power generation of the power grid at any given moment is equal to the algebraic sum of the power consumption and the stored power; wherein, the stored power is positive when the energy storage module connected to the charging station is in the charging state, and the stored power is negative when the energy storage module is in the discharging state; The charging and discharging power of the electric vehicle is within the preset power range; The total power of disorderly charging of electric vehicles under contract in the smart park is the same as the total power of orderly charging and discharging of electric vehicles under contract in the smart park indicated by the game equilibrium solution. The energy storage module connected to the charging station stores electricity within a preset range; The current drawn by the electric vehicle when it connects to the charging station is less than the preset allowable current value. The voltage deviation of the charging station connected to the power grid is within the preset range; The maximum active power of the power supply line is less than the preset power threshold. And the local load peak-valley difference of the power grid is less than the preset local load peak-valley difference threshold.

12. A server, characterized in that, This includes memory, processor, and executable instructions stored in memory and capable of running on the processor; Wherein, when the processor executes the executable instructions, it implements the steps in the method as described in any one of claims 1 to 11.

13. A computer-readable storage medium storing computer instructions thereon, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 11.

Images