Electric vehicle scheduling method and device, computer equipment, medium and program product

Abstract

The invention relates to an electric vehicle scheduling method and device, computer equipment, a medium and a program product. The method comprises the following steps: determining expected network access time and expected off-network time of each electric vehicle according to historical travel data of each electric vehicle in an electric vehicle cluster in an area to which a power system belongs; on the basis of a first scheduling prediction model, according to the expected network access time, the expected off-network time and the current operation data of each electric vehicle and the system operation data of the power system, determining the cluster charging and discharging power of the electric vehicle cluster in the future time period; wherein the first scheduling prediction model comprises a first objective function for describing the load change condition of the power system in a future time period; and according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle, determining a scheduling strategy of each electric vehicle in the future time period. By adopting the method, intelligent scheduling and synchronization of the electric vehicle cluster are realized, the power grid loss is reduced, and the power grid load is stabilized.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to an electric vehicle scheduling method, apparatus, computer equipment, medium, and program product. Background Art

[0002] As a new type of controllable load, electric vehicles can serve as mobile energy storage devices after grid connection. They can both draw power from the grid and provide energy to the grid through price incentives, enabling a connected vehicle network. However, as the number of electric vehicles increases, the disorderly charging of large numbers of electric vehicles will impact the grid, increasing load and voltage fluctuations, and affecting its normal operation.

[0003] At present, the traditional technical solution is to directly summarize and dispatch the needs of each electric vehicle. This method will result in a large amount of statistical data storage and computing requirements, which can easily cause a "dimensional disaster" and make it impossible to achieve intelligent scheduling and synchronization of electric vehicle clusters, increasing grid losses and causing grid load fluctuations. Summary of the Invention

[0004] Based on this, it is necessary to provide an electric vehicle scheduling method, device, computer equipment, medium and program product to address the above technical problems, so as to realize intelligent scheduling and synchronization of electric vehicle clusters, reduce power grid losses and stabilize power grid load.

[0005] In a first aspect, the present application provides an electric vehicle scheduling method, comprising:

[0006] Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area;

[0007] Based on a first scheduling prediction model, determining the cluster charge and discharge power of the electric vehicle cluster in a future time period according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system; wherein the first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster;

[0008] The scheduling strategy of each electric vehicle in the future time period is determined according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle.

[0009] In one embodiment, the determining of the cluster charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model and the expected grid connection time, expected grid disconnection time, and current operation data of each electric vehicle, as well as the system operation data of the power system, includes:

[0010] Determine the responsiveness of each electric vehicle based on its expected grid connection time, expected grid disconnection time, and current operating data;

[0011] The electric vehicle with a response degree greater than a response degree threshold among all electric vehicles is regarded as the first vehicle to participate in the dispatch;

[0012] Determining a unified network entry time and a unified network exit time for the first vehicle according to the expected network entry time and the expected network exit time of the first vehicle;

[0013] Based on the first scheduling prediction model, the future charging and discharging power of the electric vehicle cluster in a future time period is determined according to the unified grid-connection time, unified grid-off time and current operation data of the first vehicle, and the system operation data of the power system.

[0014] In one embodiment, the current operating data of each electric vehicle scheduling includes at least battery capacity, desired state of charge, current state of charge, and maximum power;

[0015] The step of determining the responsiveness of each electric vehicle based on the expected grid connection time, the expected grid disconnection time, and the current operating data of each electric vehicle includes:

[0016] For each electric vehicle, determining a minimum charging time for the electric vehicle based on the battery capacity, desired state of charge, current state of charge, and maximum power of the electric vehicle;

[0017] The difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time;

[0018] The ratio between the expected on-grid time and the shortest charging time is used as the responsiveness of the electric vehicle.

[0019] In one embodiment, determining the future charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model according to the unified grid connection time, unified grid disconnection time, and current operating data of the first vehicle, as well as system operating data of the power system, includes:

[0020] Using the unified grid-connection time, unified grid-off time, and current operating data of the first vehicle, as well as the system operating data of the power system, respectively updating the first objective function and the first constraint function to obtain an updated first objective function and an updated first constraint function;

[0021] Taking the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future period.

[0022] In one embodiment, before or simultaneously determining the future charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model and according to the unified grid connection time, unified grid disconnection time, and current operating data of the first vehicle, as well as the system operating data of the power system, the method further includes:

[0023] The electric vehicles whose responsiveness is less than the responsiveness threshold among the electric vehicles are regarded as the second vehicles that do not participate in the scheduling;

[0024] The charging of the second vehicle is controlled according to the current operating data, the expected grid-entry time, and the expected grid-off time of the second vehicle, so that the charging power of the second vehicle remains consistent during a period between the corresponding expected grid-entry time and the expected grid-off time.

[0025] In one embodiment, determining the scheduling strategy for each electric vehicle in the future period based on the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle includes:

[0026] Obtaining a second scheduling prediction model; wherein the second scheduling prediction model includes a second objective function describing the operating cost of each electric vehicle and a second constraint function constraining the charge and discharge balance of each electric vehicle;

[0027] Using the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle, respectively updating the second objective function and the second constraint function to obtain an updated second objective function and an updated second constraint function;

[0028] Taking the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, the updated second objective function is solved to obtain the scheduling strategy of each electric vehicle in the future period.

[0029] In a second aspect, the present application further provides an electric vehicle dispatching device, comprising:

[0030] A time determination module is used to determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster in the area to which the power system belongs;

[0031] a first prediction module, configured to determine, based on a first scheduling prediction model and according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system, the cluster charge and discharge power of the electric vehicle cluster in a future time period; wherein the first scheduling prediction model includes a first objective function describing the load variation of the power system in the future time period, and a first constraint function constraining the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster;

[0032] The second prediction module is used to determine the scheduling strategy of each electric vehicle in the future time period according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle.

[0033] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area;

[0035] Based on a first scheduling prediction model, determining the cluster charge and discharge power of the electric vehicle cluster in a future time period according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system; wherein the first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster;

[0036] The scheduling strategy of each electric vehicle in the future time period is determined according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0038] Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area;

[0039] Based on a first scheduling prediction model, determining the cluster charge and discharge power of the electric vehicle cluster in a future time period according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system; wherein the first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster;

[0040] The scheduling strategy of each electric vehicle in the future time period is determined according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle.

[0041] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0042] Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area;

[0043] Based on a first scheduling prediction model, determining the cluster charge and discharge power of the electric vehicle cluster in a future time period according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system; wherein the first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster;

[0044] The scheduling strategy of each electric vehicle in the future time period is determined according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle.

[0045] The above-mentioned electric vehicle scheduling method, device, computer equipment, medium and program product determine the expected grid-connection time and expected off-grid time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the area to which the power system belongs, thereby ensuring that the determined expected grid-connection time and expected off-grid time can fully consider the wishes and capabilities of the electric vehicle owners; further, based on the first scheduling prediction model including a first objective function that describes the load changes of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster, according to the expected grid-connection time, expected off-grid time and current operation data of each electric vehicle, as well as the system operation data of the power system, the accuracy of the cluster charge and discharge power of the electric vehicle cluster in the determined future time period is guaranteed; finally, according to the cluster charge and discharge power of the electric vehicle cluster and the current operation data of each electric vehicle, the scheduling strategy of each electric vehicle in the determined future time period is guaranteed, which can not only ensure the stable operation of the power grid, but also fully consider the economic benefits of the electric vehicle owners. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 A diagram showing an application environment of an electric vehicle scheduling method in one embodiment;

[0048] Figure 2 1 is a flow chart of an electric vehicle scheduling method according to an embodiment;

[0049] Figure 3 A schematic diagram of a process for determining cluster charging and discharging efficiency in one embodiment;

[0050] Figure 4 FIG1 is a schematic diagram of a process for determining the responsiveness of each electric vehicle in one embodiment;

[0051] Figure 5 FIG1 is a schematic diagram of a flow chart of controlling charging of a second vehicle in one embodiment;

[0052] Figure 6 A schematic diagram of a flow chart for determining a scheduling strategy for each electric vehicle in a future time period in one embodiment;

[0053] Figure 7 A schematic flow chart of an electric vehicle scheduling method according to another embodiment;

[0054] Figure 8 This is a structural block diagram of an electric vehicle dispatching device in one embodiment;

[0055] Figure 9 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0057] The electric vehicle scheduling method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the electric vehicle cluster management system 101 is used to manage the electric vehicle cluster and collect data on each electric vehicle in the electric vehicle cluster; the power system 102 is used to supply power to the electric vehicle cluster; and the electric vehicle cluster 103 is a cluster of electric vehicles within the area to which the power system 102 belongs. Optionally, the electric vehicle cluster management system 101 determines the expected grid connection time and expected grid disconnection time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster 103 within the area to which the power system 102 belongs; based on a first scheduling prediction model, the cluster charge and discharge power of the electric vehicle cluster in a future time period is determined based on the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system; wherein the first scheduling prediction model includes a first objective function that describes the load changes of the power system in the future time period, and a first constraint function that constrains the system operating balance of the power system and the charge and discharge balance of the electric vehicle cluster; and based on the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle, a scheduling strategy for each electric vehicle in the future time period is determined.

[0058] In an exemplary embodiment, Figure 2 As shown, a method for dispatching electric vehicles is provided, which is applied to Figure 1 The electric vehicle cluster management system 101 in FIG. 1 is used as an example to illustrate the present invention, which specifically includes the following steps:

[0059] S201 , determining an expected grid-connection time and an expected grid-offset time for each electric vehicle based on historical travel data of each electric vehicle in an electric vehicle cluster within an area to which the power system belongs.

[0060] The historical travel data for each electric vehicle represents the travel history of the electric vehicle over a historical period. For example, the historical travel data includes, but is not limited to, historical off-grid time, historical on-grid time, historical charging data, and historical travel distance. The expected on-grid time for each electric vehicle is the time when the electric vehicle is expected to be connected to the grid; the expected off-grid time for each electric vehicle is the time when the electric vehicle is expected to leave the grid.

[0061] Optionally, for each electric vehicle, the usage habits, commonly used charging facilities, battery power and other data of the electric vehicle can be analyzed based on the historical travel data of the electric vehicle; further, the distribution function obeyed by the expected grid-connection time and expected off-grid time of the electric vehicle can be analyzed based on the usage habits, commonly used charging facilities and battery power and other data of the electric vehicle.

[0062] For example, if it is determined that the expected network access time and the expected network disconnection time respectively obey the following Gaussian distribution:

[0063] (1)

[0064] (2)

[0065] in, For the The time an electric vehicle leaves home at the start of the journey; For the The time it takes for an electric car to return home after its last trip, and is a random variable; and Respectively The expected and variance of the time it takes for an electric vehicle to be connected to the grid; and Respectively The mean and variance of the expected time for an electric vehicle to go off the grid.

[0066] Furthermore, if it is assumed that the electric vehicle is connected to the grid immediately after returning home, the expected grid connection time is , the expected off-grid time is .

[0067] It should be noted that the historical travel data of each electric vehicle in the electric vehicle cluster within the area to which the power system belongs can be obtained from the storage system of the electric vehicle cluster management system.

[0068] S202 , based on the first scheduling prediction model, according to the expected grid connection time, expected grid disconnection time and current operation data of each electric vehicle, and the system operation data of the power system, determine the cluster charging and discharging power of the electric vehicle cluster in the future time period.

[0069] Among them, the first scheduling prediction model is used to predict the cluster charging and discharging power of the electric vehicle cluster in the future time period; in an embodiment of the present application, the first scheduling prediction model includes a first objective function that describes the load changes of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charging and discharging balance of the electric vehicle cluster.

[0070] Optionally, the first scheduling prediction model, based on the perspective of the electric vehicle cluster, is used to coordinate the charging and discharging power of the electric vehicle cluster in each time period, minimizing the variance of the power system load curve within the scheduling time interval. Therefore, a first objective function can be constructed in advance based on the load variation pattern in the power system; further, a first constraint function can be constructed based on the system operation balance rules within the power system and the charging and discharging balance rules of the electric vehicle cluster.

[0071] Furthermore, the expected grid-connection time, expected grid-off time and current operating data of each electric vehicle, as well as the system operating data of the power system, can be substituted into the first objective function and the first constraint function to update the first objective function and the second objective function in the first scheduling prediction model; finally, with the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future time period.

[0072] S203 , determining a scheduling strategy for each electric vehicle in a future time period based on the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle.

[0073] Alternatively, the current operating data of each electric vehicle can be combined to reasonably distribute the determined cluster charge and discharge power of the electric vehicle cluster to each electric vehicle while minimizing the dispatch cost of each electric vehicle. In other words, a dispatch strategy for each electric vehicle in the future can be formulated based on the current operating data of each electric vehicle, while satisfying the cluster charge and discharge power of the electric vehicle cluster.

[0074] In the above-mentioned electric vehicle scheduling method, the expected grid-connection time and the expected off-grid time of each electric vehicle are determined based on the historical travel data of each electric vehicle in the electric vehicle cluster in the area to which the power system belongs, thereby ensuring that the determined expected grid-connection time and the expected off-grid time can fully consider the wishes and capabilities of the owners of the electric vehicles; further, based on the first scheduling prediction model including the first objective function that describes the load changes of the power system in the future time period, and the first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster, according to the expected grid-connection time, the expected off-grid time and the current operation data of each electric vehicle, as well as the system operation data of the power system, the accuracy of the cluster charge and discharge power of the electric vehicle cluster in the determined future time period is guaranteed; finally, according to the cluster charge and discharge power of the electric vehicle cluster and the current operation data of each electric vehicle, the scheduling strategy of each electric vehicle in the determined future time period is guaranteed, which can not only ensure the stable operation of the power grid, but also fully consider the economic benefits of the owners of the electric vehicles.

[0075] Optionally, in order to accurately determine the cluster charging and discharging power of the electric vehicle cluster, in an exemplary embodiment, as Figure 3 As shown, a method for determining cluster charging and discharging efficiency is provided, which specifically includes the following steps:

[0076] S301 , determining the responsiveness of each electric vehicle according to its expected grid-connection time, expected grid-off time, and current operating data.

[0077] Among them, the responsiveness of each electric vehicle represents the participation degree and enthusiasm of the electric vehicle in grid dispatching.

[0078] Optionally, a responsiveness analysis model may be constructed in advance, and the expected time to join the grid, the expected time to leave the grid, and the current operating data of each electric vehicle may be input into the responsiveness analysis model, so that the responsiveness analysis model calculates the expected time to join the grid, the expected time to leave the grid, and the current operating data of each electric vehicle according to a preset calculation method to obtain the responsiveness of each electric vehicle.

[0079] S302: An electric vehicle with a responsiveness greater than a responsiveness threshold among the electric vehicles is selected as a first vehicle to participate in the scheduling.

[0080] The first vehicle is an electric vehicle in the electric vehicle cluster that participates in grid dispatching; and the response threshold is a pre-set response threshold.

[0081] Optionally, in an embodiment of the present application, taking into account the subsequent travel needs of the electric vehicle owners, 1.2 is used as the responsiveness threshold; further, electric vehicles with responsiveness greater than the responsiveness threshold among all electric vehicles are regarded as electric vehicles that can participate in grid scheduling.

[0082] S303 : Determine a unified network entry time and a unified network exit time of the first vehicle according to the expected network entry time and the expected network exit time of the first vehicle.

[0083] Among them, the unified network entry time is the unified network entry time of First Auto; the unified off-grid time is the unified off-grid time of First Auto.

[0084] Optionally, a statistical analysis can be performed on the expected network entry time and expected network exit time of the first car. For example, the average or earliest time of the expected network entry time of the first car can be used as the unified network entry time, and the average or latest time of the expected network exit time of the first car can be used as the unified network exit time.

[0085] S304 , based on the first scheduling prediction model, according to the unified grid-connection time, unified grid-off time and current operation data of the first vehicle, and the system operation data of the power system, determine the future charging and discharging power of the electric vehicle cluster in the future time period.

[0086] It should be noted that after the electric vehicle cluster is divided and the first vehicle participating in the dispatch is obtained, dispatching needs to be performed for the first vehicle. Furthermore, the first vehicles can be clustered so that the number of electric vehicles in each clustered subgroup is similar. In this embodiment of the present application, the first vehicles can be divided into "equal integral" groups based on probability within an 80% confidence level. It is understood that the first objective function and the second constraint function in the first dispatch prediction model can be constructed by comprehensively considering the first vehicle.

[0087] In the embodiment of the present application, the first objective function in the first scheduling prediction model can be expressed by the following formula:

[0088] (3)

[0089] (4)

[0090] in, Indicates unified off-grid time; Indicates unified network access time; It is the basic load in the power system except for the charging and discharging of electric vehicles; is the average load of the power system during the entire period; For the The charge and discharge power of all first cars in a subgroup at time t.

[0091] Furthermore, the first constraint function includes a power system power balance constraint function, a power system voltage deviation constraint function, and an electric vehicle cluster charge and discharge power constraint function. The power system power balance constraint function can be expressed by the following formula:

[0092] (5)

[0093] (6)

[0094] in, is the total number of nodes in the power system; and Node Active power and reactive power; and are the active power and reactive power of electric vehicle charging and discharging respectively; and are the active power and reactive power required by the basic load in the power system excluding the charging and discharging of electric vehicles; and is the voltage amplitude; is the voltage phase angle difference; and are the real and imaginary parts of the node conduction matrix, respectively.

[0095] The power system voltage deviation constraint function can be expressed by the following formula:

[0096] (7)

[0097] (8)

[0098] in, For transmission lines The maximum active power; and They are the maximum voltage constraint and the minimum voltage constraint respectively.

[0099] The charging and discharging power constraint function of the electric vehicle cluster describes that the sum of the charging and discharging power of each electric vehicle cannot exceed the total charging demand of the electric vehicle cluster in any period starting from the start of the scheduling period. It can be expressed as:

[0100] (9)

[0101] (10)

[0102] (11)

[0103] (12)

[0104] in, is the battery capacity of the electric vehicle; The charging and discharging efficiency of the electric vehicle cluster; is the total charging and discharging demand of the electric vehicle cluster during optimal scheduling; and These are the upper and lower limits of the charge and discharge power that electric vehicle batteries can withstand, to ensure safe operation of the batteries.

[0105] Furthermore, the first objective function and the first constraint function are updated using the unified grid-connection time, unified grid-off time, and current operating data of the first vehicle, as well as the system operating data of the power system, respectively, to obtain an updated first objective function and an updated first constraint function; with the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future period. In other words, the unified grid-connection time, unified grid-off time, and current operating data of the first vehicle, as well as the system operating data of the power system, can be substituted into the above formulas (3)-(12) to update the first objective function and the first constraint function, to obtain an updated first objective function and an updated first constraint function.

[0106] In this embodiment, by specifying a unified grid connection time and grid disconnection time for the first vehicle, the variability of the grid connection time and grid disconnection time of each electric vehicle is eliminated under certain circumstances. Furthermore, based on the first scheduling prediction model, the accuracy of the future charging and discharging power of the electric vehicle cluster in a determined future time period is guaranteed.

[0107] Optionally, the current operation data of each electric vehicle scheduling includes at least battery capacity, expected state of charge, current state of charge and maximum power; in one embodiment, as Figure 4 As shown, a method for determining the responsiveness of each electric vehicle is provided, which specifically includes the following steps:

[0108] S401 , for each electric vehicle, determining the shortest charging time of the electric vehicle according to the battery capacity, expected charging state, current charging state and maximum power of the electric vehicle.

[0109] Among them, the shortest charging time of an electric vehicle is the shortest charging time for the electric vehicle from maximum power to full charge.

[0110] Optionally, for each electric vehicle, the process of determining the shortest charging time of the electric vehicle based on the battery capacity, desired state of charge, current state of charge, and maximum power of the electric vehicle can be expressed by the following formula:

[0111] (13)

[0112] in, For the The shortest charging time for an electric vehicle; For the The expected state of charge of the electric vehicle; For the The current charging status of the electric vehicle; For the Battery capacity of electric vehicles; For the The maximum power of an electric vehicle.

[0113] S402: The difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time.

[0114] Optionally, the expected off-grid time and the expected on-grid time of the electric vehicle can be subtracted, and the difference obtained is used as the expected on-grid time. Specifically, it can be expressed by the following formula:

[0115] (14)

[0116] in, Indicates expected online time; For the The expected off-grid time of an electric vehicle; For the The expected time for electric vehicles to join the grid.

[0117] S403 , taking the ratio between the expected on-grid time and the shortest charging time as the responsiveness of the electric vehicle.

[0118] Alternatively, the ratio between the expected on-grid time and the minimum charging time can be used as the responsiveness of the electric vehicle, which can be expressed by the following formula:

[0119] (15)

[0120] in, For responsiveness.

[0121] In this embodiment, by introducing the shortest charging time of the electric vehicle and the expected on-grid time of the electric vehicle, the on-grid, off-grid and charging conditions of the electric vehicle are fully considered, thereby ensuring the accuracy of the determined responsiveness of the electric vehicle.

[0122] It should be noted that, in the electric vehicle cluster, after the first vehicle participating in the scheduling is screened out and the first vehicle is scheduled, it is also necessary to limit the power of the electric vehicles not participating in the scheduling. Optionally, in one embodiment, Figure 5 As shown, a method for controlling charging of a second vehicle is provided, which specifically includes the following steps:

[0123] S501: An electric vehicle with a response degree less than a response degree threshold among the electric vehicles is regarded as a second vehicle that does not participate in the scheduling.

[0124] Optionally, electric vehicles in the electric vehicle cluster whose responsiveness is less than a responsiveness threshold may be screened out, and the screened out electric vehicles are used as second vehicles that do not participate in scheduling.

[0125] S502 , controlling charging of the second vehicle according to current operating data, expected grid-connection time, and expected grid-off time of the second vehicle, so that the charging power of the second vehicle remains consistent during a period between the corresponding expected grid-connection time and expected grid-off time.

[0126] Optionally, in the embodiment of the present application, a direct charging method is adopted for the second car that does not participate in the scheduling, and the charging power is kept consistent when connected to the grid, which can be specifically expressed as:

[0127] (16)

[0128] in, Charging power for the second car; is the maximum charging power.

[0129] In this embodiment, for the second car that does not participate in the scheduling, the charging process of the second car is controlled so that the charging power of the second car remains consistent during the period between the corresponding expected grid access time and the expected grid disconnection time, thereby ensuring that the second car does not affect the scheduling of the power grid when it does not participate in the scheduling.

[0130] Optionally, in one embodiment, Figure 6 As shown, a method for determining the scheduling strategy of each electric vehicle in a future period is provided, which specifically includes the following steps:

[0131] S601: Obtain a second scheduling prediction model.

[0132] Among them, the second scheduling prediction model includes a second objective function that describes the operating cost of each electric vehicle, and a second constraint function that constrains the charge and discharge balance of each electric vehicle; the second objective function includes the electric vehicle's response cost function, charging cost function, battery loss cost function and discharge benefit function; the second constraint function includes the electric vehicle's charge and discharge power constraint function, the electric vehicle's battery constraint function, the electric vehicle's charge and discharge state constraint function and the electric vehicle's charge and discharge time constraint function.

[0133] Optionally, the second scheduling prediction model can be a lower-level model of the first scheduling prediction model. In the embodiment of the present application, the second scheduling prediction model solves the economic cost problem of each electric vehicle owner in the electric vehicle cluster from the perspective of optimal allocation of charging and discharging power of a single electric vehicle. The first objective function takes the minimum cost of each electric vehicle in the electric vehicle cluster as the optimization goal and formulates the charging and discharging strategy of a single electric vehicle under the premise of meeting the needs of the owners. Specifically, the first objective function can be expressed as:

[0134] (17)

[0135] (18)

[0136] (19)

[0137] (20)

[0138] in, is the second objective function; For the Charging cost function for an electric vehicle; For the The battery loss cost function of an electric vehicle; For the The discharge benefit function of an electric vehicle; For the Electric vehicles during the period Internal charge and discharge power; for The electricity price at the time; is the battery loss coefficient; is the penalty factor for scheduling deviation.

[0139] When an electric vehicle is connected to an AC charger, the charging and discharging power and battery temperature changes are small. In this case, Depth of discharge and charge-discharge cycle frequency The function of is used to establish the power battery loss model. Specifically:

[0140] (twenty one)

[0141] (twenty two)

[0142] in, The purchase cost of each battery capacity; To update the budget; No. Electric vehicles in State of Charge (SOC) during the time period.

[0143] No. Electric vehicles in The SOC of a time period is expressed as:

[0144] (twenty three)

[0145] in, For the Charging efficiency of electric vehicles; For the The discharge efficiency of an electric vehicle.

[0146] By fitting the experimental data, and There is a linear relationship between The greater the depth, The smaller the number, that is:

[0147] (twenty four)

[0148] The second constraint function includes the electric vehicle charging and discharging power constraint function, the electric vehicle battery constraint function, the electric vehicle charging and discharging state constraint function, and the electric vehicle charging and discharging time constraint function. Among them, the electric vehicle battery constraint function can be expressed as:

[0149] (25)

[0150] (26)

[0151] The charging and discharging power constraint function of electric vehicles can be expressed as:

[0152] (27)

[0153] (28)

[0154] in, and Respectively The upper and lower limits of charging power and the upper and lower limits of charging power of electric vehicles; and Respectively Electric vehicles in The charging and discharging state and the non-charging and discharging state at all times; When the electric vehicle is in charging state, When , the electric vehicle is in a discharging state.

[0155] The constraint function of electric vehicle charging and discharging state can be expressed as:

[0156] (29)

[0157] The charging and discharging time constraint function of electric vehicles can be expressed as:

[0158] (30)

[0159] S602 , using the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle, respectively updating the second objective function and the second constraint function to obtain an updated second objective function and an updated second constraint function.

[0160] Optionally, the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle can be input into the above formulas (17)-(30) to update the second objective function and the second constraint function to obtain an updated second objective function and an updated second constraint function.

[0161] S603 , taking the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, solving the updated second objective function to obtain the scheduling strategy of each electric vehicle in the future time period.

[0162] Optionally, an optimization algorithm can be used to solve the updated second objective function with the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, and the result of the solution can be used as the scheduling strategy for each electric vehicle in the future time period.

[0163] In this embodiment, by introducing the second scheduling prediction model as the lower model of the first scheduling prediction model, the cost of each electric vehicle is fully considered on the basis of meeting the charging and discharging power of the electric vehicle cluster, thereby ensuring the accuracy and economy of the scheduling strategy of each electric vehicle in a determined future time period.

[0164] Figure 7 FIG1 is a flow chart of an electric vehicle scheduling method in another embodiment. Based on the above embodiment, this embodiment provides an optional example of an electric vehicle scheduling method. Figure 7 The specific implementation process is as follows:

[0165] S701 , determining an expected grid-connection time and an expected grid-offset time for each electric vehicle based on historical travel data of each electric vehicle in an electric vehicle cluster within an area to which the power system belongs.

[0166] S702: Determine the shortest charging time of each electric vehicle based on the current operating data of each electric vehicle.

[0167] S703: The difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time.

[0168] S704 , the ratio between the expected on-grid time and the shortest charging time is used as the responsiveness of the electric vehicle.

[0169] S705 : The electric vehicle with a responsiveness greater than a responsiveness threshold among the electric vehicles is selected as the first vehicle to participate in the scheduling.

[0170] S706 , determining a unified network entry time and a unified network exit time of the first vehicle according to the expected network entry time and the expected network exit time of the first vehicle.

[0171] S707, based on the first scheduling prediction model, according to the unified grid-connection time, unified grid-off time and current operation data of the first vehicle, and the system operation data of the power system, determine the future charging and discharging power of the electric vehicle cluster in the future time period.

[0172] Among them, the first scheduling prediction model includes a first objective function that describes the load changes of the power system in the future period, and a first constraint function that constrains the system operation balance of the power system and the charging and discharging balance of the electric vehicle cluster.

[0173] Optionally, the unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system, are used to update the first objective function and the first constraint function respectively to obtain an updated first objective function and an updated first constraint function; with the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future time period.

[0174] S708: The electric vehicle with a response degree less than a response degree threshold among the electric vehicles is regarded as a second vehicle that does not participate in the scheduling.

[0175] S709 , controlling charging of the second vehicle according to the current operating data, the expected grid-connection time, and the expected grid-off time of the second vehicle, so that the charging power of the second vehicle remains consistent during a period between the corresponding expected grid-connection time and the expected grid-off time.

[0176] S710: Obtain a second scheduling prediction model.

[0177] The second scheduling prediction model includes a second objective function that describes the operating cost of each electric vehicle and a second constraint function that constrains the charge and discharge balance of each electric vehicle.

[0178] S711, using the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle, respectively update the second objective function and the second constraint function in the second scheduling prediction model to obtain an updated second objective function and an updated second constraint function.

[0179] S712 , taking the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, solving the updated second objective function to obtain the scheduling strategy for each electric vehicle in the future time period.

[0180] The specific process of the above S701-S712 can be found in the description of the above method embodiment. The implementation principle and technical effects are similar and will not be repeated here.

[0181] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0182] Based on the same inventive concept, the present application also provides an electric vehicle dispatching device for implementing the above-mentioned electric vehicle dispatching method. The solution provided by this device is similar to the solution described in the above-mentioned method. Therefore, the specific limitations of one or more electric vehicle dispatching device embodiments provided below can be found in the above-mentioned limitations of the electric vehicle dispatching method and will not be repeated here.

[0183] In an exemplary embodiment, Figure 8 As shown, an electric vehicle scheduling device 800 is provided, comprising: a time determination module 810, a first prediction module 820 and a second prediction module 830, wherein:

[0184] The time determination module 810 is used to determine the expected grid connection time and expected grid disconnection time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the area to which the power system belongs.

[0185] The first prediction module 820 is used to determine the cluster charging and discharging power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, according to the expected grid-connection time, expected grid-off time and current operating data of each electric vehicle, and the system operating data of the power system; wherein the first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charging and discharging balance of the electric vehicle cluster.

[0186] The second prediction module 830 is used to determine the scheduling strategy of each electric vehicle in a future time period according to the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle.

[0187] The above-mentioned electric vehicle scheduling device determines the expected grid-connection time and expected off-grid time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster in the area to which the power system belongs, thereby ensuring that the determined expected grid-connection time and expected off-grid time can fully consider the wishes and capabilities of the owners of the electric vehicles; further, based on the first scheduling prediction model including the first objective function that describes the load changes of the power system in the future time period, and the first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster, according to the expected grid-connection time, expected off-grid time and current operation data of each electric vehicle, as well as the system operation data of the power system, the accuracy of the cluster charge and discharge power of the electric vehicle cluster in the determined future time period is guaranteed; finally, according to the cluster charge and discharge power of the electric vehicle cluster and the current operation data of each electric vehicle, the scheduling strategy of each electric vehicle in the determined future time period is guaranteed, which can not only ensure the stable operation of the power grid, but also fully consider the economic benefits of the owners of the electric vehicles.

[0188] In one embodiment, the first prediction module 820 includes:

[0189] The responsiveness determination unit is used to determine the responsiveness of each electric vehicle according to the expected grid-connection time, expected grid-off time and current operation data of each electric vehicle.

[0190] The vehicle screening unit is used to select an electric vehicle whose responsiveness is greater than a responsiveness threshold among the electric vehicles as the first vehicle to participate in the scheduling.

[0191] The time determination unit is used to determine a unified network entry time and a unified network exit time of the first vehicle according to the expected network entry time and the expected network exit time of the first vehicle.

[0192] The first prediction unit is used to determine the future charging and discharging power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, the unified grid-connection time, the unified grid-offtime and current operation data of the first vehicle, and the system operation data of the power system.

[0193] In one embodiment, the current operation data of each electric vehicle scheduling includes at least battery capacity, expected state of charge, current state of charge, and maximum power; the responsiveness determination unit is specifically configured to:

[0194] For each electric vehicle, the shortest charging time of the electric vehicle is determined based on the battery capacity, expected charging state, current charging state and maximum power of the electric vehicle; the difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time; and the ratio between the expected on-grid time and the shortest charging time is used as the responsiveness of the electric vehicle.

[0195] In one embodiment, the first prediction unit is specifically configured to:

[0196] The unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system, are used to update the first objective function and the first constraint function, respectively, to obtain an updated first objective function and an updated first constraint function; with the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future time period.

[0197] In one embodiment, the first prediction unit is further configured to:

[0198] The electric vehicles whose responsiveness is less than the responsiveness threshold among the electric vehicles are regarded as the second vehicles that do not participate in the scheduling; and the charging of the second vehicles is controlled according to the current operating data, the expected grid-on time and the expected grid-off time of the second vehicles, so that the charging power of the second vehicles remains consistent during the period between the corresponding expected grid-on time and the expected grid-off time.

[0199] In one embodiment, the second prediction module 830 is specifically configured to:

[0200] A second scheduling prediction model is obtained; wherein the second scheduling prediction model includes a second objective function that describes the operating cost of each electric vehicle, and a second constraint function that constrains the charge and discharge balance of each electric vehicle; the second objective function and the second constraint function are updated respectively using the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle to obtain an updated second objective function and an updated second constraint function; with the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, the updated second objective function is solved to obtain a scheduling strategy for each electric vehicle in the future time period.

[0201] Each module in the above-mentioned electric vehicle dispatching device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0202] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an electric vehicle scheduling method is implemented.

[0203] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0204] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0205] Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area;

[0206] Based on the first scheduling prediction model, the cluster charge and discharge power of the electric vehicle cluster in a future time period is determined according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system. The first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster.

[0207] According to the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle, the scheduling strategy of each electric vehicle in the future time period is determined.

[0208] In one embodiment, when the processor executes the computer program to determine the cluster charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, the expected grid connection time, the expected grid disconnection time, and the current operating data of each electric vehicle, as well as the system operating data of the power system, the processor further implements the following steps:

[0209] The responsiveness of each electric vehicle is determined based on the expected grid-connection time, expected grid-off time and current operating data of each electric vehicle; the electric vehicle with a responsiveness greater than a responsiveness threshold among the electric vehicles is used as the first vehicle to participate in scheduling; the unified grid-connection time and unified grid-off time of the first vehicle are determined based on the expected grid-connection time and expected grid-off time of the first vehicle; based on the first scheduling prediction model, the future charging and discharging power of the electric vehicle cluster in the future time period is determined based on the unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system.

[0210] In one embodiment, the current operating data of each electric vehicle includes at least battery capacity, expected state of charge, current state of charge, and maximum power. When the processor executes the computer program to determine the responsiveness of each electric vehicle based on the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, the processor further implements the following steps:

[0211] For each electric vehicle, the shortest charging time of the electric vehicle is determined based on the battery capacity, expected charging state, current charging state and maximum power of the electric vehicle; the difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time; and the ratio between the expected on-grid time and the shortest charging time is used as the responsiveness of the electric vehicle.

[0212] In one embodiment, when the processor executes the computer program to determine the future charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, the unified grid connection time, the unified grid disconnection time, and the current operating data of the first vehicle, and the system operating data of the power system, the processor further implements the following steps:

[0213] The unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system, are used to update the first objective function and the first constraint function, respectively, to obtain an updated first objective function and an updated first constraint function; with the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future time period.

[0214] In one embodiment, the processor executes a computer program to determine, based on the first scheduling prediction model, the unified grid connection time, unified grid disconnection time, and current operating data of the first vehicle, as well as the system operating data of the power system, the future charging and discharging power of the electric vehicle cluster in the future time period before or simultaneously. The following steps are also implemented:

[0215] The electric vehicles whose responsiveness is less than the responsiveness threshold among the electric vehicles are regarded as the second vehicles that do not participate in the scheduling; and the charging of the second vehicles is controlled according to the current operating data, the expected grid-on time and the expected grid-off time of the second vehicles, so that the charging power of the second vehicles remains consistent during the period between the corresponding expected grid-on time and the expected grid-off time.

[0216] In one embodiment, when the processor executes the computer program to determine the scheduling strategy for each electric vehicle in a future time period based on the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle, the processor further implements the following steps:

[0217] A second scheduling prediction model is obtained; wherein the second scheduling prediction model includes a second objective function that describes the operating cost of each electric vehicle, and a second constraint function that constrains the charge and discharge balance of each electric vehicle; the second objective function and the second constraint function are updated respectively using the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle to obtain an updated second objective function and an updated second constraint function; with the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, the updated second objective function is solved to obtain a scheduling strategy for each electric vehicle in the future time period.

[0218] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0219] Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area;

[0220] Based on the first scheduling prediction model, the cluster charge and discharge power of the electric vehicle cluster in a future time period is determined according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system. The first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster.

[0221] According to the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle, the scheduling strategy of each electric vehicle in the future time period is determined.

[0222] In one embodiment, when the processor executes the computer program to determine the cluster charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, the expected grid connection time, the expected grid disconnection time, and the current operating data of each electric vehicle, as well as the system operating data of the power system, the processor further implements the following steps:

[0223] The responsiveness of each electric vehicle is determined based on the expected grid-connection time, expected grid-off time and current operating data of each electric vehicle; the electric vehicle with a responsiveness greater than a responsiveness threshold among the electric vehicles is used as the first vehicle to participate in scheduling; the unified grid-connection time and unified grid-off time of the first vehicle are determined based on the expected grid-connection time and expected grid-off time of the first vehicle; based on the first scheduling prediction model, the future charging and discharging power of the electric vehicle cluster in the future time period is determined based on the unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system.

[0224] In one embodiment, the current operating data of each electric vehicle includes at least battery capacity, expected state of charge, current state of charge, and maximum power. When the processor executes the computer program to determine the responsiveness of each electric vehicle based on the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, the processor further implements the following steps:

[0225] For each electric vehicle, the shortest charging time of the electric vehicle is determined based on the battery capacity, expected charging state, current charging state and maximum power of the electric vehicle; the difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time; and the ratio between the expected on-grid time and the shortest charging time is used as the responsiveness of the electric vehicle.

[0226] In one embodiment, when the processor executes the computer program to determine the future charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, the unified grid connection time, the unified grid disconnection time, and the current operating data of the first vehicle, and the system operating data of the power system, the processor further implements the following steps:

[0227] The unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system, are used to update the first objective function and the first constraint function, respectively, to obtain an updated first objective function and an updated first constraint function; with the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future time period.

[0228] In one embodiment, the processor executes a computer program to determine, based on the first scheduling prediction model, the unified grid connection time, unified grid disconnection time, and current operating data of the first vehicle, as well as the system operating data of the power system, the future charging and discharging power of the electric vehicle cluster in the future time period before or simultaneously. The following steps are also implemented:

[0229] The electric vehicles whose responsiveness is less than the responsiveness threshold among the electric vehicles are regarded as the second vehicles that do not participate in the scheduling; and the charging of the second vehicles is controlled according to the current operating data, the expected grid-on time and the expected grid-off time of the second vehicles, so that the charging power of the second vehicles remains consistent during the period between the corresponding expected grid-on time and the expected grid-off time.

[0230] In one embodiment, when the processor executes the computer program to determine the scheduling strategy for each electric vehicle in a future time period based on the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle, the processor further implements the following steps:

[0231] A second scheduling prediction model is obtained; wherein the second scheduling prediction model includes a second objective function that describes the operating cost of each electric vehicle, and a second constraint function that constrains the charge and discharge balance of each electric vehicle; the second objective function and the second constraint function are updated respectively using the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle to obtain an updated second objective function and an updated second constraint function; with the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, the updated second objective function is solved to obtain a scheduling strategy for each electric vehicle in the future time period.

[0232] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0233] Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area;

[0234] Based on the first scheduling prediction model, the cluster charge and discharge power of the electric vehicle cluster in a future time period is determined according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system. The first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster.

[0235] According to the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle, the scheduling strategy of each electric vehicle in the future time period is determined.

[0236] In one embodiment, when the processor executes the computer program to determine the cluster charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, the expected grid connection time, the expected grid disconnection time, and the current operating data of each electric vehicle, as well as the system operating data of the power system, the processor further implements the following steps:

[0237] The responsiveness of each electric vehicle is determined based on the expected grid-connection time, expected grid-off time and current operating data of each electric vehicle; the electric vehicle with a responsiveness greater than a responsiveness threshold among the electric vehicles is used as the first vehicle to participate in scheduling; the unified grid-connection time and unified grid-off time of the first vehicle are determined based on the expected grid-connection time and expected grid-off time of the first vehicle; based on the first scheduling prediction model, the future charging and discharging power of the electric vehicle cluster in the future time period is determined based on the unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system.

[0238] In one embodiment, the current operating data of each electric vehicle includes at least battery capacity, expected state of charge, current state of charge, and maximum power. When the processor executes the computer program to determine the responsiveness of each electric vehicle based on the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, the processor further implements the following steps:

[0239] For each electric vehicle, the shortest charging time of the electric vehicle is determined based on the battery capacity, expected charging state, current charging state and maximum power of the electric vehicle; the difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time; and the ratio between the expected on-grid time and the shortest charging time is used as the responsiveness of the electric vehicle.

[0240] In one embodiment, when the processor executes the computer program to determine the future charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model, the unified grid connection time, the unified grid disconnection time, and the current operating data of the first vehicle, and the system operating data of the power system, the processor further implements the following steps:

[0241] The unified grid-connection time, unified grid-off time and current operating data of the first vehicle, as well as the system operating data of the power system, are used to update the first objective function and the first constraint function, respectively, to obtain an updated first objective function and an updated first constraint function; with the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future time period.

[0242] In one embodiment, the processor executes a computer program to determine, based on the first scheduling prediction model, the unified grid connection time, unified grid disconnection time, and current operating data of the first vehicle, as well as the system operating data of the power system, the future charging and discharging power of the electric vehicle cluster in the future time period before or simultaneously. The following steps are also implemented:

[0243] The electric vehicles whose responsiveness is less than the responsiveness threshold among the electric vehicles are regarded as the second vehicles that do not participate in the scheduling; and the charging of the second vehicles is controlled according to the current operating data, the expected grid-on time and the expected grid-off time of the second vehicles, so that the charging power of the second vehicles remains consistent during the period between the corresponding expected grid-on time and the expected grid-off time.

[0244] In one embodiment, when the processor executes the computer program to determine the scheduling strategy for each electric vehicle in a future time period based on the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle, the processor further implements the following steps:

[0245] A second scheduling prediction model is obtained; wherein the second scheduling prediction model includes a second objective function that describes the operating cost of each electric vehicle, and a second constraint function that constrains the charge and discharge balance of each electric vehicle; the second objective function and the second constraint function are updated respectively using the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle to obtain an updated second objective function and an updated second constraint function; with the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, the updated second objective function is solved to obtain a scheduling strategy for each electric vehicle in the future time period.

[0246] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0247] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0248] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0249] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for dispatching electric vehicles, characterized in that: The method comprises: Determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster within the power system area; Based on a first scheduling prediction model, determining the cluster charge and discharge power of the electric vehicle cluster in a future time period according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system; wherein the first scheduling prediction model includes a first objective function that describes the load change of the power system in the future time period, and a first constraint function that constrains the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster; The scheduling strategy of each electric vehicle in the future time period is determined according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle.

2. The method according to claim 1, characterized in that The method of determining the cluster charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model and the expected grid connection time, expected grid disconnection time, and current operation data of each electric vehicle, as well as the system operation data of the power system, includes: Determine the responsiveness of each electric vehicle based on its expected grid connection time, expected grid disconnection time, and current operating data; The electric vehicle with a response degree greater than a response degree threshold among all electric vehicles is regarded as the first vehicle to participate in the dispatch; Determining a unified network entry time and a unified network exit time for the first vehicle according to the expected network entry time and the expected network exit time of the first vehicle; Based on the first scheduling prediction model, the future charging and discharging power of the electric vehicle cluster in a future time period is determined according to the unified grid-connection time, unified grid-off time and current operation data of the first vehicle, and the system operation data of the power system.

3. The method according to claim 2, characterized in that The current operating data of each electric vehicle dispatching includes at least battery capacity, expected state of charge, current state of charge and maximum power; The step of determining the responsiveness of each electric vehicle based on the expected grid connection time, the expected grid disconnection time, and the current operating data of each electric vehicle includes: For each electric vehicle, determining a minimum charging time for the electric vehicle based on the battery capacity, desired state of charge, current state of charge, and maximum power of the electric vehicle; The difference between the expected off-grid time and the expected on-grid time of the electric vehicle is used as the expected on-grid time; The ratio between the expected on-grid time and the shortest charging time is used as the responsiveness of the electric vehicle.

4. The method according to claim 2, characterized in that The method of determining the future charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model and the unified grid connection time, unified grid disconnection time, and current operation data of the first vehicle, as well as the system operation data of the power system, includes: Using the unified grid-connection time, unified grid-off time, and current operating data of the first vehicle, as well as the system operating data of the power system, respectively updating the first objective function and the first constraint function to obtain an updated first objective function and an updated first constraint function; Taking the minimum function value of the updated first objective function as the goal and the updated first constraint function as the constraint, the updated first objective function is solved to obtain the cluster charging and discharging power of the electric vehicle cluster in the future period.

5. The method according to claim 2, characterized in that Before or simultaneously determining the future charge and discharge power of the electric vehicle cluster in a future time period based on the first scheduling prediction model and the unified grid connection time, unified grid disconnection time, and current operating data of the first vehicle, as well as the system operating data of the power system, the method further includes: The electric vehicles whose responsiveness is less than the responsiveness threshold among the electric vehicles are regarded as the second vehicles that do not participate in the scheduling; The charging of the second vehicle is controlled according to the current operating data, the expected grid-entry time, and the expected grid-off time of the second vehicle, so that the charging power of the second vehicle remains consistent during a period between the corresponding expected grid-entry time and the expected grid-off time.

6. The method according to claim 1, characterized in that The step of determining the scheduling strategy for each electric vehicle in the future time period based on the cluster charging and discharging power of the electric vehicle cluster and the current operating data of each electric vehicle includes: Obtaining a second scheduling prediction model; wherein the second scheduling prediction model includes a second objective function describing the operating cost of each electric vehicle and a second constraint function constraining the charge and discharge balance of each electric vehicle; Using the cluster charge and discharge power of the electric vehicle cluster and the current operating data of each electric vehicle, respectively updating the second objective function and the second constraint function to obtain an updated second objective function and an updated second constraint function; Taking the minimum function value of the updated second objective function as the goal and the updated second constraint function as the constraint, the updated second objective function is solved to obtain the scheduling strategy of each electric vehicle in the future period.

7. An electric vehicle dispatching device, characterized in that: The device comprises: A time determination module is used to determine the expected grid entry time and expected grid exit time of each electric vehicle based on the historical travel data of each electric vehicle in the electric vehicle cluster in the area to which the power system belongs; a first prediction module, configured to determine, based on a first scheduling prediction model and according to the expected grid connection time, expected grid disconnection time, and current operating data of each electric vehicle, as well as the system operating data of the power system, the cluster charge and discharge power of the electric vehicle cluster in a future time period; wherein the first scheduling prediction model includes a first objective function describing the load variation of the power system in the future time period, and a first constraint function constraining the system operation balance of the power system and the charge and discharge balance of the electric vehicle cluster; The second prediction module is used to determine the scheduling strategy of each electric vehicle in the future time period according to the cluster charging and discharging power of the electric vehicle cluster and the current operation data of each electric vehicle.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images