Scheduling method for flexible resource cluster of electric vehicle charging station

Abstract

The embodiment of the invention discloses a scheduling method for a flexible resource cluster of an electric vehicle charging station, and relates to the technical field of electric vehicle V2G scheduling control, and the method comprises the steps: obtaining a grid-connected state of each electric vehicle and a scheduling power range which can be provided; calculating to obtain a scheduling power range which can be provided by each charging station in each historical time period; inputting historical data into the trained prediction model to obtain corresponding prediction data; sampling based on the historical data, the historical prediction data and the prediction data through a sampling method to obtain corresponding sampling data in the prediction time period; and calculating the scheduling power range of the plurality of charging stations in the flexible resource cluster in the target time period based on the sampling data. According to the method, the electric energy schedulable potential change condition of each charging station can be dynamically reflected, so that the electric vehicle charging station can better participate in the regional power load scheduling process, and the configuration efficiency of a power grid, electric vehicle energy storage, photovoltaic power generation and wind power generation is improved.

Description

Technical Field

[0001] This application relates to the technical field of electric vehicle V2G scheduling control, and particularly to a scheduling method for a flexible resource cluster of an electric vehicle charging station. Background Art

[0002] The two-way interaction technology between electric vehicles and the power grid (V2G, Vehicle-to-Grid) is a new type of power grid technology. Through V2G technology, electric vehicles can be scheduled to charge by the power grid during the low load period of the power grid to store the excess power generation of the power grid, and electric vehicles can feed power to the power grid during the high load period of the power grid.

[0003] With the wide application of V2G technology and the wide access of distributed renewable energy, electric vehicle charging stations can aggregate flexible resources such as distributed photovoltaics and small wind turbines into a flexible resource cluster. As a distributed energy storage system, it can then transform from a single electric energy consumer to a prosumer that can interact bidirectionally with the outside world. While the flexible resource cluster provides wider schedulable potential for the charging station, its strong randomness and unpredictability also pose challenges to the safe operation of the charging station.

[0004] Currently, through the way of energy sharing, while ensuring the benefits of the charging station, the energy storage of the flexible resource cluster can be fully allocated. Users with surplus electric energy resources can transfer electric energy for users with tight electric energy resources to use, thereby optimizing the allocation of electric energy resources. In order to make the energy sharing transaction decision of the charging station safe and reasonable, it is necessary to predict and calculate the energy sharing uncertainty schedulable potential of the flexible resource cluster of the charging station, that is, the maximum upward regulation power and the maximum downward regulation power of each flexible resource cluster. Although the traditional calculation method can quickly and simply calculate the electric energy schedulable potential of each flexible resource cluster, the results calculated by this method have problems of insufficient accuracy and excessive conservatism, which further affect the economy and safety of subsequent transaction decisions.

[0005] Therefore, there is currently a lack of a method that can dynamically reflect the change of the electric energy schedulable potential of each charging station, enabling V2G technology to better participate in the process of regional power load scheduling and improving the configuration efficiency of the power grid, electric vehicle energy storage, photovoltaic power generation, and wind power generation. Summary of the Invention

[0006] The embodiments of this application provide a scheduling method for a flexible resource cluster of an electric vehicle charging station to solve the defects of the above related technologies. It has the advantages of being able to accurately calculate the schedulable potential of the flexible resource cluster of the charging station, improving resource utilization rate, and realizing coordinated and optimized scheduling of multiple charging stations. The technical solution is as follows:

[0007] In a first aspect, an embodiment of the present application provides a scheduling method for a flexible resource cluster of an electric vehicle charging station. The flexible resource cluster includes multiple charging stations, and the method includes:

[0008] Obtain the grid connection status of each electric vehicle connected to the grid through any charging pile in any charging station during each historical period, and calculate the range of scheduling power that each electric vehicle can provide during each historical period;

[0009] Based on the range of scheduling power of each electric vehicle, calculate the range of scheduling power that each charging station can provide during each historical period;

[0010] Obtain the historical flexible energy generation power data of the flexible energy device in each charging station during each historical period, input the historical data including the range of scheduling power of the charging station and the historical flexible energy generation power data into a trained prediction model, and obtain the prediction data corresponding to each item of historical data output by the prediction model during the target period;

[0011] Based on the historical data of each charging station, obtain the historical prediction data during the historical period, and sample the corresponding sampling data during the prediction period based on the historical data, the historical prediction data, and the prediction data through a sampling method;

[0012] Based on the sampling data, calculate the range of scheduling power of multiple charging stations in the flexible resource cluster during the target period.

[0013] In an optional solution of the first aspect, the obtaining the grid connection status of each electric vehicle connected to the grid through any charging pile in any charging station during each historical period includes:

[0014] Calculate the grid connection status of an electric vehicle connected to the grid through the j-th charging pile in the i-th charging station during any historical period, and apply the formula:

[0015]

[0016] where i>0, j>0, and both i and j are integers; S i,j (t) represents the grid connection status of the electric vehicle. When S i,j (t) is 1, the electric vehicle occupies the charging pile and is in the grid connection status with the grid; when S i,j (t) is 0, the electric vehicle does not occupy the charging pile and is in the grid disconnection status with the grid; is the expected departure time of the electric vehicle; kΔt represents the initial moment of the k-th historical period; kΔt + Δt represents the end moment of the k-th historical period.

[0017] In an alternative embodiment of the first aspect, calculating the range of dispatchable power that each electric vehicle can provide during each historical time period includes:

[0018] Calculating the maximum downward regulation power that each electric vehicle can provide during each historical time period, using the formula:

[0019]

[0020] Where is the actual maximum discharge power of the electric vehicle; is the planned charge-discharge power of the electric vehicle;

[0021] The calculation process of the actual maximum discharge power uses the following formula:

[0022]

[0023] Where is the maximum charging power; is the maximum discharge power; represents the difference between the minimum state of charge at the end of the historical time period and the state of charge at the initial moment; is the minimum state of charge at the end of the historical time period, E i,j (kΔt) is the state of charge at the initial moment of the historical time period;

[0024] The calculation process of uses the following formula:

[0025]

[0026] Where is the expected state of charge of the electric vehicle, is the minimum state of charge of the electric vehicle; C ij is the battery capacity of the electric vehicle;

[0027] Calculating the maximum downward regulation power that each electric vehicle can provide during each historical time period, using the formula:

[0028]

[0029] Where is the maximum charging power that the electric vehicle can actually provide, and the calculation process uses the following formula:

[0030]

[0031] Where represents the state of charge upward adjustment margin of the electric vehicle at the kΔt moment, is the expected state of charge of the electric vehicle.

[0032] In an alternative embodiment of the first aspect, calculating the dispatch power range that each charging station can provide in each historical period based on the dispatch power range of each electric vehicle includes:

[0033] Calculating the maximum upward regulation power and the maximum downward regulation power that each charging station can provide at time t in each historical period, using the formula:

[0034]

[0035] where is the total number of charging piles at the i-th charging station.

[0036] In an alternative embodiment of the first aspect, a flexible energy generation device is configured in the charging station of the flexible resource cluster, and the flexible energy generation device includes a photovoltaic power generation device and / or a wind power generation device;

[0037] Inputting the historical data including the dispatch power range of the charging station and the historical flexible energy generation power data into the trained prediction model to obtain the prediction data corresponding to each item of the historical data output by the prediction model in the target period, including:

[0038] The upper limit of the dispatch power range is the maximum upward regulation power of the charging station in the corresponding historical period, and the lower limit of the dispatch power range is the maximum downward regulation power of the charging station in the corresponding historical period. The historical flexible energy generation power data includes historical photovoltaic power generation data and / or historical wind power generation data;

[0039] Taking the maximum upward regulation power, the maximum downward regulation power, the historical photovoltaic power generation data and / or the historical wind power generation data of the charging station in the historical period as the historical data and inputting them into the trained prediction model;

[0040] Obtaining the prediction data output by the prediction model includes the predicted maximum upward regulation power, the predicted maximum downward regulation power, the predicted photovoltaic power generation data and / or the predicted wind power generation data of the charging station in the target period.

[0041] In an alternative embodiment of the first aspect, obtaining historical prediction data in a historical period based on the historical data of each charging station includes:

[0042] Inputting the historical data of each charging station in the first historical period into the trained prediction model to obtain the historical prediction data of the charging station in the second historical period output by the prediction model; where the end time of the first historical period is earlier than the start time of the second historical period;

[0043] The sampling data corresponding to the prediction period is obtained by sampling based on the historical data, the historical prediction data, and the prediction data, including:

[0044] Calculate the multivariate Gaussian distribution covariance matrix R according to the historical data, and apply the formula:

[0045]

[0046] where z is an intermediate parameter, t = 1, 2, 3, …, T; T is the total length of the target period; represents the inverse of the cumulative distribution function Φ0 of the standard Gaussian distribution; F is the cumulative distribution function, F x,t (x t ) and F y,t (y t ) are calculated from the historical data; ρ(z x,i , z y,j ) = 2sin(ρ r (z x,i , z y,j )π / 6), ρ and ρ r are the linear correlation coefficient and the Spearman correlation coefficient respectively; x is one of the maximum upward power, maximum downward power, historical photovoltaic power generation data, and historical wind power generation data of the charging station in the historical period, and y is the predicted data corresponding to the historical data; in the multivariate covariance matrix, R xx is the binary covariance matrix between the historical data x of a certain type of data; R yy is the binary covariance matrix between the predicted data y of a certain type of data; R xy is the binary covariance matrix between the historical data x and the predicted data y of a certain type of data; ρ(variable1, variable2) is the linear correlation coefficient between two variables;

[0047] Further, calculate the expected value of the conditional probability distribution and the covariance matrix and apply the formula:

[0048]

[0049] where z x = [z x,1 , z x,2 , …, z x,T T , z y = [z y,1 , z y,2 , …, z y,T T ;​​

[0050] Based on the predicted data, calculate

[0051] By sampling z x |z y , to obtain the z within the target period c samples, to obtain the sampling data, and apply the formula:

[0052]

[0053] where, x s is the sequence of the sampling data obtained by sampling, including the sampling data corresponding to one of the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station within the target period.

[0054] In an alternative solution of the first aspect, calculating the scheduling power range of multiple charging stations in the flexible resource cluster within the target period based on the sampling data includes:

[0055] Based on the sampling data corresponding to the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station obtained by sampling, establish an ellipsoidal uncertainty set of the energy sharing potential of the flexible resource cluster of electric vehicle charging stations;

[0056] Intercept a two-dimensional ellipsoidal uncertainty set from the ellipsoidal uncertainty set according to the time range of the target period;

[0057] Extract feasible solutions from the two-dimensional ellipsoidal uncertainty set; where, the ordinate of each feasible solution corresponds to the maximum downward regulation power of the charging station within the target period, and the abscissa corresponds to the maximum downward regulation power of the charging station within the target period;

[0058] Configure the scheduling power range of the charging station based on the maximum downward regulation power and maximum downward regulation power corresponding to the feasible solution.

[0059] In a second aspect, an embodiment of the present application further provides a scheduling device for a flexible resource cluster of electric vehicle charging stations, including:

[0060] An electric vehicle schedulable capacity evaluation module, configured to obtain the grid connection status of each electric vehicle connected to the grid through any charging pile in any charging station in each historical period, and calculate the schedulable power range that each electric vehicle can provide in each historical period;

[0061] A charging station schedulable capacity evaluation module, configured to calculate the schedulable power range that each charging station can provide in each historical period based on the schedulable power range of each electric vehicle;

[0062] A data prediction module, configured to obtain historical flexible energy generation power data of flexible energy devices in each charging station at each historical time period, input historical data including the scheduling power range of the charging station and the historical flexible energy generation power data into a trained prediction model, and obtain prediction data corresponding to each item of the historical data output by the prediction model within a target time period;

[0063] A data sampling module, configured to obtain historical prediction data within a historical time period based on the historical data of each charging station, and sample to obtain corresponding sampling data within the prediction time period based on the historical data, the historical prediction data, and the prediction data through a sampling method;

[0064] A scheduling module, configured to calculate the scheduling power range of multiple charging stations in the flexible resource cluster within a target time period based on the sampling data.

[0065] In an alternative solution of the second aspect, the electric vehicle schedulability evaluation module is configured to obtain the grid connection status of each electric vehicle connected to the power grid through any charging pile in any charging station in each historical time period, specifically including:

[0066] The electric vehicle schedulability evaluation module calculates the grid connection status of an electric vehicle connected to the power grid through the j-th charging pile in the i-th charging station in any historical time period, and applies the formula:

[0067]

[0068] where i > 0, j > 0, and both i and j are integers; S i,j (t) represents the grid connection status of the electric vehicle. When S o,j (t) is 1, the electric vehicle occupies the charging pile and is in a grid-connected state; when S o,j (t) is 0, the electric vehicle does not occupy the charging pile and is in a grid-disconnected state; is the expected departure time of the electric vehicle; kΔt represents the initial moment of the k-th historical time period; kΔt + Δt represents the end moment of the k-th historical time period.

[0069] In an alternative solution of the second aspect, the electric vehicle schedulability evaluation module is configured to calculate the schedulable power range that each electric vehicle can provide in each historical time period, including:

[0070] The electric vehicle schedulability evaluation module calculates the maximum downward regulation power that each electric vehicle can provide in each historical time period, and applies the formula:

[0071]

[0072] where is the actual maximum discharge power of the electric vehicle; is the planned charge and discharge power of the electric vehicle;

[0073] The calculation process of the actual maximum discharge power applies the following formula:

[0074]

[0075] Among them, is the maximum charging power; is the maximum discharge power; represents the difference between the minimum state of charge at the end of the historical period and the state of charge at the initial moment; is the minimum state of charge at the end of the historical period, E i,j (kΔt) is the state of charge at the initial moment of the historical period;

[0076] The calculation process of applies the following formula:

[0077]

[0078] Among them, is the expected state of charge of the electric vehicle, is the lowest state of charge of the electric vehicle; C i,j is the battery capacity of the electric vehicle;

[0079] The electric vehicle schedulability evaluation module calculates the maximum downward regulation power that each electric vehicle can provide in each historical period, and applies the formula:

[0080]

[0081] Among them, is the maximum charging power that the electric vehicle can actually provide, and the calculation process applies the following formula:

[0082]

[0083] Among them, represents the state of charge upward adjustment margin of the electric vehicle at the kΔt moment, is the expected state of charge of the electric vehicle.

[0084] In an alternative solution of the second aspect, the charging station schedulability evaluation module is used to calculate the schedulable power range that each charging station can provide in each historical period based on the scheduling power range of each electric vehicle, specifically including:

[0085] The schedulable capacity evaluation module of the charging station calculates the maximum upward regulation power and the maximum downward regulation power that each charging station can provide at time t in each historical period, and applies the formula:

[0086]

[0087] where is the total number of charging piles at the i-th charging station.

[0088] In an alternative solution of the second aspect, a flexible energy generation device is configured in the charging station of the flexible resource cluster, and the flexible energy generation device includes a photovoltaic power generation device and / or a wind power generation device;

[0089] The data prediction module is used to input historical data including the scheduling power range of the charging station and the historical flexible energy generation power data into the trained prediction model, and obtain the prediction data corresponding to each item of historical data output by the prediction model in the target period, specifically including:

[0090] The upper limit of the scheduling power range is the maximum upward regulation power of the charging station in the corresponding historical period, the upper limit of the scheduling power range is the maximum downward regulation power of the charging station in the corresponding historical period, and the historical flexible energy generation power data includes historical photovoltaic power generation data and / or historical wind power generation data;

[0091] The data prediction module is used to input the maximum upward regulation power, the maximum downward regulation power, the historical photovoltaic power generation data and / or the historical wind power generation data of the charging station in the historical period as the historical data into the trained prediction model;

[0092] The data prediction module obtains the prediction data output by the prediction model, including the predicted maximum upward regulation power, the predicted maximum downward regulation power, the predicted photovoltaic power generation data and / or the predicted wind power generation data of the charging station in the target period.

[0093] In an alternative solution of the second aspect, the data sampling module is used to obtain historical prediction data in the historical period based on the historical data of each charging station, specifically including:

[0094] The data sampling module inputs the historical data of each charging station in the first historical period into the trained prediction model, and obtains the historical prediction data of the charging station in the second historical period output by the prediction model; wherein, the end time of the first historical period is earlier than the start time of the second historical period;

[0095] The data sampling module samples the sampling data corresponding to the prediction period based on the historical data, the historical prediction data, and the prediction data through a sampling method, specifically including:

[0096] The data sampling module calculates the multivariate Gaussian distribution covariance matrix R according to the historical data, using the formula:

[0097]

[0098] Among them, z is the intermediate parameter, t=1,2,3,…,T; T is the total length of the target period; represents the inverse of the cumulative distribution function of the standard Gaussian distribution Φ0; F is the cumulative distribution function, F x,t (x t ) and F y,t (y t ) is calculated from the historical data; ρ(z x,i ,z y,j )=2sin(ρ r (z x,i ,z y,j )π / 6), ρ and ρ r are the linear correlation coefficient and the Spearman correlation coefficient respectively; x is one of the maximum upward power adjustment, maximum downward power adjustment, historical photovoltaic power generation data and historical wind power generation data of the charging station in the historical period, and y is the predicted data corresponding to the historical data; in the multivariate covariance matrix, R xx is the binary covariance matrix between the historical data x of a certain type of data; R yy is the binary covariance matrix between the predicted data y of a certain type of data; R xy is the binary covariance matrix between the historical data x and the predicted data y of a certain type of data; ρ(variable 1, variable 2) is the linear correlation coefficient between the two variables;

[0099] Furthermore, the data sampling module is also used to calculate the conditional probability distribution Expected value And the covariance matrix Application formula:

[0100]

[0101] Among them, z x =[z x,1 ,z x,2 ,…,z x,T ] T , z y =[z y,1 ,z y,2 ,…,z y,T ] T ;

[0102] The data sampling module calculates based on the predicted data

[0103] The data sampling module samples z x |z y to obtain the z x samples within the target period, obtains the sampling data, and applies the formula:

[0104]

[0105] where x s is the sequence of the sampling data obtained by sampling, including the sampling data corresponding to one of the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station within the target period.

[0106] In an alternative solution of the second aspect, the scheduling module is used to calculate the scheduling power range of multiple charging stations in the flexible resource cluster within the target period based on the sampling data, specifically including:

[0107] The scheduling module establishes an ellipsoidal uncertainty set of the energy sharing potential of the flexible resource cluster of electric vehicle charging stations based on the sampling data corresponding to the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station obtained by sampling within the target period;

[0108] The scheduling module intercepts a two-dimensional ellipsoidal uncertainty set from the ellipsoidal uncertainty set according to the time range of the target period;

[0109] The scheduling module extracts feasible solutions from the two-dimensional ellipsoidal uncertainty set; where the ordinate of each feasible solution corresponds to the maximum downward regulation power of the charging station within the target period, and the abscissa corresponds to the maximum downward regulation power of the charging station within the target period;

[0110] The scheduling module configures the scheduling power range of the charging station based on the maximum downward regulation power and maximum downward regulation power corresponding to the feasible solutions.

[0111] In a third aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method provided in the first aspect or any implementation manner of the first aspect of the embodiment of the present application is implemented.

[0112] In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method provided in the first aspect or any implementation manner of the first aspect of the embodiment of the present application is implemented.

[0113] The beneficial effects brought by the technical solutions provided in some embodiments of the present application at least include:

[0114] A scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application can dynamically reflect the change in the power dispatch potential of each charging station by obtaining the grid-connected status and the dispatch power range of electric vehicles, and can provide more accurate data support for the scheduling and energy management of electric vehicle charging stations, avoiding the problems of insufficient accuracy and excessive conservatism in the calculation results of traditional methods; by calculating the dispatch power range of the charging station, the change in the power dispatch potential of each charging station can be dynamically reflected; further, by combining historical data and a prediction model, the present application can more accurately predict the dispatch power range of the flexible resource cluster of the electric vehicle charging station. Through the sampling method, more sampling data can be obtained, thereby improving the representativeness of the data; finally, the entire method can dynamically reflect the change in the power dispatch potential of each charging station, enabling the electric vehicle charging station to better participate in the process of regional power load dispatch and improving the configuration efficiency of the power grid, electric vehicle energy storage, photovoltaic power generation, and wind power generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0115] In order to more clearly illustrate the technical solutions in the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0116] Figure 1 is a flowchart of a scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application;

[0117] Figure 2 is a schematic diagram of predicted data of the upward and downward adjustment powers of a scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application;

[0118] Figure 3 is a schematic diagram of predicted data of the photovoltaic power generation of a scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application;

[0119] Figure 4 is a schematic diagram of predicted data of the wind power generation of a scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application;

[0120] Figure 5 is a schematic diagram of a two-dimensional ellipsoidal uncertainty set of a scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application;

[0121] Figure 6 It is a schematic structural diagram of a scheduling device for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application;

[0122] Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Specific embodiments

[0123] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts fall within the scope of protection of the present application.

[0124] The terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned accompanying drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally further includes steps or modules not listed, or optionally further includes other steps or modules inherent to these processes, methods, products or devices.

[0125] It should be noted that the terms "first" and "second" involved in the present application are only used to distinguish similar objects and do not represent a specific order for the objects. Understandably, "first" and "second" can be interchanged in a specific order or sequence when permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged appropriately so that the embodiments of the present application described here can be implemented in an order other than those described or illustrated here.

[0126] The present application will be described in detail below with reference to specific embodiments.

[0127] It should be noted that the flexible resource cluster in the embodiments of the present application can be aggregated from an electric vehicle charging station and other flexible resources, specifically including electric vehicles connected to the power grid through charging piles in the electric vehicle charging station and flexible resource power generation devices configured in the charging station, such as photovoltaic power generation devices, wind power generation devices, etc. Thus, during the low grid load period, the electric vehicles can be scheduled by the grid for charging to store the excess power generation of the grid, and during the high grid load period, the electric vehicles can feed power to the grid. By integrating renewable energy resources such as photovoltaic (PV) and wind power generation, more flexible and sustainable energy management can be achieved.

[0128] Next, in combination with Figure 1 , a scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application will be introduced. For details, please refer toFigure 1 , Figure 1 shows a schematic flow chart of a scheduling method for a flexible resource cluster of an electric vehicle charging station provided by an embodiment of the present application. As Figure 1 shown, the method includes the following steps:

[0129] S101. Obtain the grid-connected status of each electric vehicle connected to the grid through any charging pile in any charging station in each historical period, and calculate the range of scheduling power that each electric vehicle can provide in each historical period;

[0130] S102. Calculate the range of scheduling power that each charging station can provide in each historical period based on the range of scheduling power of each electric vehicle;

[0131] S103. Obtain the historical flexible energy generation power data of the flexible energy device in each charging station in each historical period, input the historical data including the scheduling power range of the charging station and the historical flexible energy generation power data into the trained prediction model, and obtain the prediction data corresponding to each item of historical data output by the prediction model in the target period;

[0132] S104. Obtain the historical prediction data in the historical period based on the historical data of each charging station, and sample to obtain the corresponding sampling data in the prediction period based on the historical data, the historical prediction data, and the prediction data through a sampling method;

[0133] S105. Calculate the range of scheduling power of multiple charging stations in the flexible resource cluster in the target period based on the sampling data.

[0134] Specifically, in S101, the obtaining of the grid-connected status of each electric vehicle connected to the grid through any charging pile in any charging station in each historical period includes:

[0135] Calculate the grid-connected status of an electric vehicle connected to the grid through the jth charging pile in the ith charging station in any historical period, and apply the formula:

[0136]

[0137] where i > 0, j > 0, and both i and j are integers; S i,j (t) represents the grid-connected status of the electric vehicle. When S i,j (t) is 1, the electric vehicle occupies the charging pile and is in the grid-connected status of being connected to the grid; when S i,j (t) is 0, the electric vehicle does not occupy the charging pile and is in the grid-connected status of being disconnected from the grid; is the expected departure time of the electric vehicle; \(k\Delta t\) represents the initial moment of the \(k\)th historical period; \(k\Delta t+\Delta t\) represents the end moment of the \(k\)th historical period.

[0138] Specifically, in S101, calculating the range of dispatchable power that each electric vehicle can provide within each historical period, the upper limit of the dispatchable power range is the maximum upward regulation power, and the lower limit of the dispatchable power range is the maximum downward regulation power.

[0139] It can be understood that the maximum upward regulation power refers to the maximum electric energy output power that an electric vehicle can provide to the power grid, and the maximum downward regulation power refers to the maximum power input capacity for the power grid to charge the electric vehicle. The maximum upward regulation power and the maximum downward regulation power are not fixed and will be dynamically adjusted according to real-time conditions (such as the current state of the battery, grid demand, etc.).

[0140] Specifically include:

[0141] Calculating the maximum downward regulation power that each electric vehicle can provide within each historical period, applying the formula:

[0142]

[0143] Wherein, is the actual maximum discharge power of the electric vehicle; is the planned charge-discharge power of the electric vehicle;

[0144] It can be understood that the actual discharge power refers to the amount of power actually released by the electric vehicle battery to the power grid at a specific time point, and the planned discharge power is determined based on prediction and planning, which is the expected discharge power value that the electric vehicle can provide within a certain period of time. The planned discharge power can also be understood as the discharge power value set artificially or limited by the device.

[0145] The calculation process of the actual maximum discharge power applies the following formula:

[0146]

[0147] Wherein, is the maximum charging power; is the maximum discharge power; represents the difference between the minimum state of charge at the end moment of the historical period and the state of charge at the initial moment; is the minimum state of charge at the end moment of the historical period, \(E\) i,j \(E(k\Delta t)\) is the state of charge at the initial moment of the historical period;

[0148] The calculation process of applies the following formula:

[0149]

[0150] Among them, is the expected state of charge of the electric vehicle, is the minimum state of charge of the electric vehicle; C i,j is the battery capacity of the electric vehicle;

[0151] Calculate the maximum downward power that each electric vehicle can provide in each historical period, and apply the formula:

[0152]

[0153] Among them, is the maximum charging power that the electric vehicle can actually provide, and the following formula is applied in the calculation process:

[0154]

[0155] Among them, represents the upward margin of the state of charge of the electric vehicle at the moment of kΔt, is the expected state of charge of the electric vehicle.

[0156] It can be understood that the state of charge (State of Charge, abbreviated as SOC) refers to the percentage of the current stored electricity in the battery to its maximum storage capacity, and can be used to measure the remaining energy of the battery. The upward margin can be understood as the amount of power output that the vehicle can safely increase currently without affecting the battery life or system safety. For example, when accelerating or climbing a slope, if the battery and motor system have enough upward margin, additional power support can be provided.

[0157] In some embodiments, in S102, calculating the scheduling power range that each charging station can provide in each historical period based on the scheduling power range of each electric vehicle includes:

[0158] Calculate the maximum upward power and maximum downward power that each charging station can provide at the moment t in each historical period, and apply the formula:

[0159]

[0160] Among them, is the total number of charging piles at the i-th charging station, is the maximum upward power that the charging station can provide at the moment t in each historical period, is the maximum downward power that the charging station can provide at the moment t in each historical period.

[0161] Understandably, there may be several electric vehicles connected to the power grid through charging piles in a charging station. The charging station can be regarded as equivalent to an electric vehicle cluster in the charging station. The battery of each vehicle in the electric vehicle cluster can be used as an energy unit, which can discharge power to the power grid through the connected charging piles, and determine the grid connection status, upward regulation power, and downward regulation power in each time period through step S101. By calculating the grid connection status, upward regulation power, and downward regulation power of each electric vehicle in the electric vehicle cluster, the maximum upward regulation power and maximum downward regulation power that the corresponding charging station can provide can be calculated.

[0162] In some embodiments, in S103, a flexible energy generation device is configured in the charging station in the flexible resource cluster, and the flexible energy generation device includes a photovoltaic power generation device and / or a wind power generation device;

[0163] Inputting the historical data including the scheduling power range of the charging station and the historical flexible energy generation power data into the trained prediction model, and obtaining the prediction data corresponding to each item of historical data output by the prediction model in the target time period, including:

[0164] The upper limit of the scheduling power range is the maximum upward regulation power of the charging station in the corresponding historical time period, the lower limit of the scheduling power range is the maximum downward regulation power of the charging station in the corresponding historical time period, and the historical flexible energy generation power data includes historical photovoltaic power generation data and / or historical wind power generation data;

[0165] Taking the maximum upward regulation power, maximum downward regulation power, historical photovoltaic power generation data, and / or historical wind power generation data of the charging station in the historical time period as the historical data and inputting them into the trained prediction model;

[0166] Obtaining the prediction data output by the prediction model includes the predicted maximum upward regulation power, predicted maximum downward regulation power, predicted photovoltaic power generation data, and / or predicted wind power generation data of the charging station in the target time period.

[0167] Specifically, the prediction can be performed through the Informer prediction model, and the embodiments of the present application do not limit this.

[0168] Exemplarily, as Figure 2 shown, Figure 2 it exemplifies the predicted maximum upward regulation power, predicted maximum downward regulation power, actual maximum upward regulation power, and actual maximum downward regulation power obtained by prediction. As Figure 3 shown, Figure 3 it exemplifies the predicted photovoltaic power generation data and actual photovoltaic power generation data obtained by prediction. Figure 4 shown, Figure 4Illustrates the predicted wind power generation power data and the actual wind power generation power data obtained by prediction. The actual data can be collected in real time, such as Figures 2 - 4 As shown, the prediction model provided by the embodiments of the present application can accurately predict data.

[0169] In some embodiments, in S104, obtaining historical prediction data within a historical period based on the historical data of each charging station includes:[[]]

[0170] Inputting the historical data of each charging station within the first historical period into the trained prediction model to obtain the historical prediction data of the charging station within the second historical period output by the prediction model; wherein, the end time of the first historical period is earlier than the start time of the second historical period;

[0171] Sampling the corresponding sampling data within the prediction period based on the historical data, the historical prediction data, and the prediction data through a sampling method, including:[[]]

[0172] Calculating the multivariate Gaussian distribution covariance matrix R according to the historical data, and applying the formula:[[]]

[0173]

[0174] where z is an intermediate parameter, t = 1, 2, 3, …, T; T is the total length of the target period; represents the inverse of the cumulative distribution function Φ0 of the standard Gaussian distribution; F is the cumulative distribution function, F x,t (x t ) and F y,t (y t ) are calculated from the historical data; ρ(z x,i , z y,j ) = 2sin(ρ r (z x,i , z y,j )π / 6), ρ and ρ r are the linear correlation coefficient and the Spearman correlation coefficient respectively; x is one of the maximum upward regulation power, the maximum downward regulation power, the historical photovoltaic power generation power data, and the historical wind power generation power data of the charging station within the historical period, y is the predicted data corresponding to the historical data; in the multivariate covariance matrix, R xx is the binary covariance matrix between the historical data x of a certain type of data; R yy is the binary covariance matrix between the predicted data y of a certain type of data; R xy is the binary covariance matrix between the historical data x and the predicted data y of a certain type of data; ρ(variable1, variable2) is the linear correlation coefficient between two variables;

[0175] Furthermore, calculate the expected value of the conditional probability distribution and the covariance matrix Apply the formula: Apply the formula:

[0176]

[0177] where z x =[z x,1 , z x,2 , …, z x,T T , z y =[z y,1 , z y,2 , …, z y,T T ;

[0178] Based on the prediction data, calculate

[0179] By sampling z x |z y , obtain the z x samples within the target time period to obtain sampling data, and apply the formula:

[0180]

[0181] where x s is the sequence of sampling data obtained by sampling, including the sampling data corresponding to one of the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station within the target time period.

[0182] In some embodiments, in S104, calculating the scheduling power range of multiple charging stations in the flexible resource cluster within the target time period based on the sampling data includes:

[0183] Based on the sampling data corresponding to the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station obtained by sampling, establish an ellipsoidal uncertainty set of the energy sharing potential of the electric vehicle charging station flexible resource cluster;

[0184] Intercept a two-dimensional ellipsoidal uncertainty set from the ellipsoidal uncertainty set according to the time range of the target time period;

[0185] Extract the feasible solutions from the two-dimensional ellipsoidal uncertainty set; where the ordinate of each feasible solution corresponds to the maximum downward regulation power of the charging station within the target time period, and the abscissa corresponds to the maximum downward regulation power of the charging station within the target time period;

[0186] ​​Based on the maximum downward regulation power corresponding to the feasible solution and the maximum downward regulation power, configure the scheduling power range of the charging station.

[0187] Specifically, the process of establishing the ellipsoidal uncertainty set of the flexible resource cluster energy sharing potential of the electric vehicle charging station includes the following steps:

[0188] First, the target time period T can be decomposed into several sub-time periods, and the length of each sub-time period is T D , and the number of sub-time periods is Sn, then Sn = T - T D + 1, then x s = [x s,s1 , x s,s2 ,..., x s,sn T . Replace x s,sn with , which respectively represent the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation, and wind power generation of the charging station i within the Sn-th sub-time period.

[0189] In some embodiments, the time period during which the electric vehicle can discharge to the power grid can be adjusted by setting the target time period. For example, the peak time periods 8:00 - 12:00 and 14:00 - 18:00 can be set as the target time periods, and the embodiments of the present application do not limit this.

[0190] Furthermore, use a set to include the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation, and wind power generation of the electric vehicle cluster of the charging station i within the Sn-th sub-time period:

[0191]

[0192] Among them:

[0193]

[0194] Furthermore, construct the ellipsoidal set problem formula to determine the characteristic quantities c and A of the ellipsoidal set E:

[0195]

[0196] Among them, c represents the center point of the ellipsoidal set, determining the position of the ellipsoidal set; A is a symmetric positive definite matrix, representing the shape of the ellipsoidal set; v is the unit ellipsoid volume constant, and its value is independent of the problem solution.

[0197] Next, solve the problem formula to obtain the ellipsoidal uncertainty set and the extreme scenario coordinates. Translate and rotate the ellipsoidal set E so that its center and symmetry axis coincide with the origin and the coordinate axes, which is convenient for solving the extreme scenario coordinates. Apply the formula:

[0198] ​

[0199] where ω′ i is the transformed ellipsoid, P is the orthogonal decomposition matrix of A, i.e., A = P T DP, D is the diagonal matrix composed of the eigenvalues λ1, λ2,..., λ n of A. ω′ e is the extreme scenario coordinate of the transformed ellipsoid. By performing the inverse transformation on the ω′ e coordinates, the extreme scenario coordinates ω e of the original ellipsoid E can be obtained. Applying the formula:

[0200] ω e = c + P -1 ω′ e ;

[0201] Up to this point, the ellipsoidal uncertainty set of the flexible resource cluster energy sharing potential of the electric vehicle charging station can be expressed by the following formula:

[0202]

[0203] Thus, an ellipsoidal uncertainty set composed of the feasible region is obtained.

[0204] It should be noted that the uncertainty set calculated in this application can be used not only for the establishment of the feasible region in the subsequent energy sharing robust optimization process, but also as a basis for other optimization decisions. Its advantages are that it combines historical data and prediction data, establishes the correlation between the predicted value and the actual value through the Gaussian distribution, and further constructs a more accurate scheduling feasible region for the maximum upward regulation power and the maximum downward regulation power through the ellipsoidal uncertainty set, which can reduce the conservatism of subsequent decisions and improve the economic benefits of decision-makers.

[0205] In some embodiments, a two-dimensional ellipsoidal uncertainty set can be obtained by intercepting in the ellipsoidal uncertainty set according to the time range of the target period. Specifically, a corresponding ellipsoidal plane can be intercepted in the three-dimensional ellipsoid corresponding to the ellipsoidal uncertainty set. As Figure 5 shown, it is a schematic diagram of the two-dimensional ellipsoidal uncertainty set. The range of the red ellipse in the figure is the range of the feasible region, and each blue point is a feasible solution in the feasible region. Extracting the coordinates of each feasible solution can obtain the maximum downward regulation power and the maximum upward regulation power of the charging station.

[0206] Based on this, a scheduling plan for each period can be obtained by intercepting from the ellipsoidal uncertainty set, and the maximum downward regulation power and the maximum upward regulation power of each charging station can be configured according to the extracted feasible solutions.

[0207] The following is the device embodiment of this application, which can be used to execute the method embodiment of this application. For the details not disclosed in the device embodiment of this application, please refer to the method embodiment of this application.

[0208] Next, please refer to Figure 6 , which is a schematic structural diagram of a scheduling device for a flexible resource cluster of an electric vehicle charging station provided for an exemplary embodiment of the present application. This device can be implemented as all or part of a terminal through software, hardware, or a combination of both, and can also be integrated as an independent module on a server. A scheduling device for a flexible resource cluster of an electric vehicle charging station in an embodiment of the present application can be applied to a terminal or the cloud. The device 60 includes an electric vehicle schedulable capacity evaluation module 601, a charging station schedulable capacity evaluation module 602, a data prediction module 603, a data sampling module 604, and a scheduling module 605, where:

[0209] The electric vehicle schedulable capacity evaluation module 601 is configured to obtain the grid connection status of each electric vehicle connected to the grid through any charging pile in any charging station in each historical period, and calculate the range of schedulable power that each electric vehicle can provide in each historical period;

[0210] The charging station schedulable capacity evaluation module 602 is configured to calculate the range of schedulable power that each charging station can provide in each historical period based on the schedulable power range of each electric vehicle;

[0211] The data prediction module 603 is configured to obtain the historical flexible energy generation power data of the flexible energy device in each charging station in each historical period, input the historical data including the schedulable power range of the charging station and the historical flexible energy generation power data into a trained prediction model, and obtain the prediction data corresponding to each item of historical data output by the prediction model in the target period;

[0212] The data sampling module 604 is configured to obtain historical prediction data in a historical period based on the historical data of each charging station, and sample to obtain the sampling data corresponding to the prediction period based on the historical data, the historical prediction data, and the prediction data through a sampling method;

[0213] The scheduling module 605 is configured to calculate the range of schedulable power of multiple charging stations in the flexible resource cluster in the target period based on the sampling data.

[0214] In some embodiments, the electric vehicle schedulable capacity evaluation module 601 is configured to obtain the grid connection status of each electric vehicle connected to the grid through any charging pile in any charging station in each historical period, specifically including:

[0215] The electric vehicle schedulable capacity evaluation module 601 calculates the grid connection status of an electric vehicle connected to the grid through the j-th charging pile in the i-th charging station in any historical period, and applies the formula:

[0216]

[0217] where i > 0, j > 0, and both i and j are integers; S i,j (t) represents the grid-connected state of the electric vehicle, and when S i,j (t) is 1, the electric vehicle occupies the charging pile and is in a grid-connected state connected to the power grid; when S i,j (t) is 0, the electric vehicle does not occupy the charging pile and is in a grid-connected state disconnected from the power grid; is the expected departure time of the electric vehicle; kΔt represents the initial moment of the k-th historical period; kΔt + Δt represents the end moment of the k-th historical period.

[0218] In some embodiments, the electric vehicle schedulability evaluation module 601 is used to calculate the range of schedulable power that each electric vehicle can provide within each historical period, including:

[0219] The electric vehicle schedulability evaluation module 601 calculates the maximum downward regulation power that each electric vehicle can provide within each historical period, using the formula:

[0220]

[0221] where is the actual maximum discharge power of the electric vehicle; is the planned charge-discharge power of the electric vehicle;

[0222] The calculation process of the actual maximum discharge power uses the following formula:

[0223]

[0224] where is the maximum charging power; is the maximum discharge power; represents the difference between the minimum state of charge at the end moment of the historical period and the state of charge at the initial moment; is the minimum state of charge at the end moment of the historical period, and E i,j (kΔt) is the state of charge at the initial moment of the historical period;

[0225] The calculation process of uses the following formula:

[0226]

[0227] where is the expected state of charge of the electric vehicle, is the minimum state of charge of the electric vehicle; C i,j is the battery capacity of the electric vehicle;

[0228] The dispatchable capacity evaluation module 601 of the electric vehicle calculates the maximum downward regulation power that each electric vehicle can provide in each historical period, and applies the formula:

[0229]

[0230] where, is the maximum charging power that the electric vehicle can actually provide, and the calculation process applies the following formula:

[0231]

[0232] where, represents the state of charge upward regulation margin of the electric vehicle at the moment of kΔt, is the expected state of charge of the electric vehicle.

[0233] In some embodiments, the dispatchable capacity evaluation module 602 of the charging station is used to calculate the dispatchable power range that each charging station can provide in each historical period based on the dispatch power range of each electric vehicle, specifically including:

[0234] The dispatchable capacity evaluation module 602 of the charging station calculates the maximum upward regulation power and the maximum downward regulation power that each charging station can provide at the moment t in each historical period, and applies the formula:

[0235]

[0236] where, is the total number of charging piles at the i-th charging station.

[0237] In some embodiments, a flexible energy generation device is configured in the charging station in the flexible resource cluster, and the flexible energy generation device includes a photovoltaic power generation device and / or a wind power generation device;

[0238] The data prediction module 603 is used to input the historical data including the dispatch power range of the charging station and the historical flexible energy generation power data into the trained prediction model, and obtain the prediction data corresponding to each item of historical data output by the prediction model in the target period, specifically including:

[0239] The upper limit of the dispatch power range is the maximum upward regulation power of the charging station in the corresponding historical period, the upper limit of the dispatch power range is the maximum downward regulation power of the charging station in the corresponding historical period, and the historical flexible energy generation power data includes historical photovoltaic power generation data and / or historical wind power generation data;

[0240] The data prediction module 603 is configured to use the maximum upward regulation power, the maximum downward regulation power, the historical photovoltaic power generation data, and / or the historical wind power generation data of the charging station within the historical period as the historical data and input the historical data into the trained prediction model;

[0241] The data prediction module 603 obtains the prediction data output by the prediction model, including the predicted maximum upward regulation power, the predicted maximum downward regulation power, the predicted photovoltaic power generation data, and / or the predicted wind power generation data of the charging station within the target period.

[0242] In some embodiments, the data sampling module 604 is configured to obtain historical prediction data within the historical period based on the historical data of each charging station, specifically including:

[0243] The data sampling module 604 inputs the historical data of each charging station within the first historical period into the trained prediction model and obtains the historical prediction data of the charging station within the second historical period output by the prediction model; wherein, the end time of the first historical period is earlier than the start time of the second historical period;

[0244] The data sampling module 604 samples the corresponding sampling data within the prediction period based on the historical data, the historical prediction data, and the prediction data through a sampling method, specifically including:

[0245] The data sampling module 604 calculates the multivariate Gaussian distribution covariance matrix R according to the historical data, and applies the formula:

[0246]

[0247]

[0248] where z is an intermediate parameter, t = 1, 2, 3, …, T; T is the total length of the target period; represents the inverse of the cumulative distribution function Φ0 of the standard Gaussian distribution; F is the cumulative distribution function, F x,t (x t ) and F y,t (y t ) are calculated from the historical data; ρ(z x,i , z y,j ) = 2sin(ρ r (z x,i , z y,j )π / 6), ρ and ρ rare the linear correlation coefficient and the Spearman correlation coefficient respectively; x is one of the maximum upward power adjustment, maximum downward power adjustment, historical photovoltaic power generation data and historical wind power generation data of the charging station in the historical period, and y is the predicted data corresponding to the historical data; in the multivariate covariance matrix, R xx is the binary covariance matrix between the historical data x of a certain type of data; R yy is the binary covariance matrix between the predicted data y of a certain type of data; R xy is the binary covariance matrix between the historical data x and the predicted data y of a certain type of data; ρ(variable 1, variable 2) is the linear correlation coefficient between the two variables;

[0249] Furthermore, the data sampling module 604 is also used to calculate the conditional probability distribution Expected value And the covariance matrix Application formula:

[0250]

[0251] Among them, z x =[z x,1 ,z x,2 ,…,z x,T ] T , z y =[z y,1 ,z y,2 ,…,z y,T ] T ;

[0252] The data sampling module 604 calculates based on the predicted data

[0253] The data sampling module 604 samples z x |z y , get z within the target period x Sample, get the sampled data, apply the formula:

[0254]

[0255] Among them, x s The sequence of sampled data obtained by sampling includes sampled data corresponding to one of the maximum upward power adjustment, the maximum downward power adjustment, the photovoltaic power generation data and the wind power generation data of the charging station within the target period.

[0256] In some embodiments, the scheduling module 605 is used to calculate the scheduling power range of multiple charging stations in the flexible resource cluster within the target time period based on the sampled data, specifically including:

[0257] The scheduling module 605 establishes an ellipsoidal uncertainty set of the flexible resource cluster energy sharing potential of the electric vehicle charging station based on the sampling data corresponding to the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation power data, and wind power generation power data of the charging station within the target period.

[0258] The scheduling module 605 intercepts a two-dimensional ellipsoidal uncertainty set from the ellipsoidal uncertainty set according to the time range of the target period.

[0259] The scheduling module 605 extracts feasible solutions from the two-dimensional ellipsoidal uncertainty set; wherein, the ordinate of each feasible solution corresponds to the maximum downward regulation power of the charging station within the target period, and the abscissa corresponds to the maximum downward regulation power of the charging station within the target period.

[0260] The scheduling module 605 configures the scheduling power range of the charging station based on the maximum downward regulation power and maximum upward regulation power corresponding to the feasible solutions.

[0261] It should be noted that when the device 60 provided in the above embodiment executes a scheduling method for a flexible resource cluster of an electric vehicle charging station, only the above division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device provided in the above embodiment and an embodiment of a scheduling method for a flexible resource cluster of an electric vehicle charging station belong to the same concept, and the implementation process is shown in detail in the method embodiment, which will not be elaborated here.

[0262] The embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps of the method in any of the above embodiments.

[0263] Please refer to Figure 7 for the structural block diagram of an electronic device provided by an embodiment of the present application.

[0264] As Figure 7 shown, the electronic device 700 includes a processor 701 and a memory 702.

[0265] In the embodiments of the present application, the processor 701 is the control center of the computer system, which can be the processor of a physical machine or the processor of a virtual machine. The processor 701 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. The processor 701 may be implemented in at least one of the following hardware forms: DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array).

[0266] The processor 701 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state.

[0267] The memory 702 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 702 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments of the present application, the non-transitory computer-readable storage media in the memory 702 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 701 to implement the method in the embodiments of the present application.

[0268] In some embodiments, the electronic device 700 further includes: a peripheral device interface 703 and at least one peripheral device 704. The processor 701, the memory 702, and the peripheral device interface 703 may be connected through a bus or signal lines. Each peripheral device 704 may be connected to the peripheral device interface 703 through a bus, signal lines, or a circuit board. Specifically, the peripheral device 704 includes: a display screen, a camera, and an audio circuit. The peripheral device interface 703 may be used to connect at least one I / O (Input / Output) related peripheral device to the processor 701 and the memory 702.

[0269] In some embodiments of the present application, the processor 701, the memory 702, and the peripheral device interface 703 are integrated on the same chip or circuit board; in some other embodiments of the present application, any one or two of the processor 701, the memory 702, and the peripheral device interface 703 may be implemented on a separate chip or circuit board. The embodiments of the present application do not make specific limitations in this regard.

[0270] The block diagram of the electronic device shown in the embodiments of the present application does not limit the electronic device 700. The electronic device 700 may include more or fewer components than shown in the figure, combine certain components, or adopt different component arrangements.

[0271] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the method in any of the foregoing embodiments are implemented. Among them, the computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0272] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the related technology, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disks, optical disks, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0273] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A scheduling method for a flexible resource cluster of an electric vehicle charging station, characterized in that The flexible resource cluster includes multiple charging stations, and the method includes: Obtain the grid connection status of each electric vehicle connected to the grid through any charging pile in any charging station during each historical period, and calculate the range of dispatchable power that each electric vehicle can provide during each historical period; Calculate the range of dispatchable power that each charging station can provide during each historical period based on the dispatchable power range of each electric vehicle; Obtain the historical flexible energy generation power data of the flexible energy device in each charging station during each historical period, input the historical data including the dispatchable power range of the charging station and the historical flexible energy generation power data into the trained prediction model, and obtain the prediction data corresponding to each item of historical data output by the prediction model during the target period; Obtain the historical prediction data during the historical period based on the historical data of each charging station, and sample the historical data, the historical prediction data, and the prediction data based on the sampling method to obtain the corresponding sampling data during the prediction period; Calculate the range of dispatchable power of multiple charging stations in the flexible resource cluster during the target period based on the sampling data.

2. The scheduling method of a flexible resource cluster of an electric vehicle charging station according to claim 1, characterized in that, The obtaining the grid connection status of each electric vehicle connected to the grid through any charging pile in any charging station during each historical period includes: Calculate the grid connection status of an electric vehicle connected to the grid through the j-th charging pile in the i-th charging station during any historical period, and apply the formula: Wherein, i > 0, j > 0, both i and j are integers; S i,j (t) represents the grid-connected state of the electric vehicle, and when S i,j (t) is 1, the electric vehicle occupies the charging pile and is in the grid-connected state connected to the grid; when S i,j (t) is 0, the electric vehicle does not occupy the charging pile and is in the grid-connected state disconnected from the grid; is the expected departure time of the electric vehicle; kΔt represents the initial moment of the k-th historical period; kΔt + Δt represents the end moment of the k-th historical period.

3. The scheduling method of a flexible resource cluster of an electric vehicle charging station according to claim 2, characterized in that, The calculating the range of dispatchable power that each electric vehicle can provide during each historical period includes: Calculate the maximum downward regulation power that each electric vehicle can provide during each historical period, and apply the formula: Among them, is the actual maximum discharge power of the electric vehicle; is the planned charge and discharge power of the electric vehicle; The calculation process of the actual maximum discharge power applies the following formula: Among them, is the maximum charging power; is the maximum discharging power; represents the difference between the minimum state of charge at the end of the historical period and the state of charge at the initial moment; is the minimum state of charge at the end of the historical period, and E i,j (kΔt) is the state of charge at the initial moment of the historical period; The calculation process applies the following formula: wherein, is the expected state of charge of the electric vehicle, is the minimum state of charge of the electric vehicle; C i,j is the battery capacity of the electric vehicle; Calculate the maximum downward regulation power that each electric vehicle can provide during each historical period, and apply the formula: Among them, is the maximum charging power that the electric vehicle can actually provide, and the following formula is applied in the calculation process: Among them, represents the charging state up-regulation margin of the electric vehicle at the moment of kΔt, is the expected charging state of the electric vehicle.

4. A scheduling method for a flexible resource cluster of an electric vehicle charging station according to claim 3, characterized in that, The calculating the range of dispatchable power that each charging station can provide during each historical period based on the dispatchable power range of each electric vehicle includes: Calculate the maximum upward regulation power and the maximum downward regulation power that each charging station can provide at time t during each historical period, and apply the formula: Among them, is the total number of charging piles at the i-th charging station.

5. A scheduling method for a flexible resource cluster of an electric vehicle charging station according to claim 4, characterized in that The charging stations in the flexible resource cluster are configured with flexible energy generation devices, and the flexible energy generation devices include photovoltaic power generation devices and / or wind power generation devices; The inputting the historical data including the dispatchable power range of the charging station and the historical flexible energy generation power data into the trained prediction model, and obtaining the prediction data corresponding to each item of historical data output by the prediction model during the target period includes: The upper limit of the dispatchable power range is the maximum upward regulation power of the charging station during the corresponding historical period, the lower limit of the dispatchable power range is the maximum downward regulation power of the charging station during the corresponding historical period, and the historical flexible energy generation power data includes historical photovoltaic power generation power data and / or historical wind power generation power data; Take the maximum upward regulation power, the maximum downward regulation power, the historical photovoltaic power generation power data and / or the historical wind power generation power data of the charging station during the historical period as the historical data and input them into the trained prediction model; Obtaining the predicted data output by the prediction model includes the predicted maximum upward regulation power, predicted maximum downward regulation power, predicted photovoltaic power generation data, and / or predicted wind power generation data of the charging station during the target period.

6. A scheduling method for a flexible resource cluster of an electric vehicle charging station according to claim 5, characterized in that Obtaining the historical prediction data within the historical period based on the historical data of each charging station includes: Inputting the historical data of each charging station within the first historical period into the trained prediction model to obtain the historical prediction data of the charging station within the second historical period output by the prediction model; wherein, the end time of the first historical period is earlier than the start time of the second historical period; Sampling the corresponding sampling data within the prediction period based on the historical data, the historical prediction data, and the predicted data through a sampling method includes: Calculating the multivariate Gaussian distribution covariance matrix R according to the historical data and applying the formula: where z is an intermediate parameter, T is the total length of the target time period; represents the inverse of the cumulative distribution function Φ0 of the standard Gaussian distribution; F is the cumulative distribution function, F x,t (x t ) and F y,t (y t ) are calculated from the historical data; ρ(z x,i , z y,j ) = 2sin(ρ r (z x,i , z y,j )π / 6), ρ and ρ r are the linear correlation coefficient and the Spearman correlation coefficient respectively; x is one of the maximum upward regulation power, maximum downward regulation power, historical photovoltaic power generation data, and historical wind power generation data of the charging station during the historical period, and y is the predicted data corresponding to the historical data; in the multivariate covariance matrix, R xx is the binary covariance matrix between the historical data x of a certain type of data; R yy is the binary covariance matrix between the predicted data y of a certain type of data; R xy is the binary covariance matrix between the historical data x and the predicted data y of a certain type of data; ρ(variable1, variable2) is the linear correlation coefficient between two variables; Further, calculate the expected value of the conditional probability distribution and the covariance matrix using the formula: Apply the formula: where z x =[z x,1 , z x,2 , …, z x,T T , z y =[z y,1 , z y,2 , …, z y,T T ;​​ Calculate based on the predicted data By sampling z x |z y to obtain the z x samples within the target period, obtaining sampling data, and applying the formula: where x s is a sequence of sampled data obtained by sampling, including sampled data corresponding to one of the maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station within the target period.

7. A scheduling method for a flexible resource cluster of an electric vehicle charging station according to claim 6, characterized in that, Calculating the scheduling power range of multiple charging stations within the flexible resource cluster during the target period based on the sampling data includes: Establishing an ellipsoidal uncertainty set of the energy sharing potential of the flexible resource cluster of electric vehicle charging stations based on the sampled maximum upward regulation power, maximum downward regulation power, photovoltaic power generation data, and wind power generation data of the charging station during the target period; Intercepting a two-dimensional ellipsoidal uncertainty set from the ellipsoidal uncertainty set according to the time range of the target period; Extracting feasible solutions from the two-dimensional ellipsoidal uncertainty set; wherein, the ordinate of each feasible solution corresponds to the maximum downward regulation power of the charging station during the target period, and the abscissa corresponds to the maximum downward regulation power of the charging station during the target period; Configuring the scheduling power range of the charging station based on the maximum downward regulation power and maximum downward regulation power corresponding to the feasible solution.

8. A scheduling device for a flexible resource cluster of an electric vehicle charging station, characterized in that, Including: An electric vehicle schedulability evaluation module, configured to obtain the grid connection status of each electric vehicle connected to the power grid through any charging pile in any charging station within each historical period, and calculate the schedulable power range that each electric vehicle can provide within each historical period; A charging station schedulability evaluation module, configured to calculate the schedulable power range that each charging station can provide within each historical period based on the schedulable power range of each electric vehicle; A data prediction module, configured to obtain the historical flexible energy generation power data of the flexible energy device in each charging station within each historical period, input the historical data including the schedulable power range of the charging station and the historical flexible energy generation power data into the trained prediction model, and obtain the predicted data corresponding to each item of the historical data within the target period output by the prediction model; A data sampling module, configured to obtain the historical prediction data within the historical period based on the historical data of each charging station, and sample the corresponding sampling data within the prediction period based on the historical data, the historical prediction data, and the predicted data through a sampling method; A scheduling module, configured to calculate the scheduling power range of multiple charging stations within the flexible resource cluster during the target period based on the sampling data.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 7.

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

Images