Method, device, equipment and medium for determining dispatch potential of electric vehicle cluster

Abstract

The present application relates to a method, apparatus, device, and medium for determining the dispatching potential of an electric vehicle cluster. The method comprises: obtaining target dispatching demand information for an electric vehicle cluster in a region to which the power system belongs in the current time period; the target dispatching demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile in the region to which the power system belongs; obtaining a regulation potential prediction model for the electric vehicle cluster; the regulation potential prediction model is determined based on a regulation potential function and a dispatching constraint function of the electric vehicle cluster, the regulation potential function being used to characterize changes in the adjustable power of the electric vehicle cluster in a future time period, and the dispatching constraint function being used to constrain the charging and discharging of the electric vehicle cluster; based on the regulation potential prediction model and the target dispatching demand information, determining the dispatchable range of the electric vehicle cluster in the future time period. This method can quickly and accurately determine the dispatching potential of an electric vehicle cluster.

Description

Technical Field

[0001] The present application relates to the field of power grid dispatching technology, and in particular to a method, device, equipment and medium for determining the dispatching potential of an electric vehicle cluster. Background Art

[0002] Electric vehicles are rapidly gaining adoption worldwide and are seen as a promising alternative to traditional gasoline vehicles. While diverse distributed demand-side resources, such as electric vehicle loads, are numerous and relatively small in capacity, their penetration is rapidly increasing, significantly increasing the flexibility of distribution networks. To further enhance forward-looking understanding of the potential for diverse demand-side resources, such as electric vehicles, to participate in power system regulation, an aggregated assessment of the regulatory capabilities of electric vehicle resources is necessary.

[0003] However, existing research has evaluated the dispatch potential of electric vehicle clusters by constructing objective functions and constraints that reflect the charging and discharging processes of electric vehicles and solving these objective functions. Existing mathematical optimization methods struggle to quickly map the system's initial state to complex dynamic responses. Changes to parameters such as vehicle demand require recalculation, leading to lengthy solution times. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, equipment and medium for determining the scheduling potential of an electric vehicle cluster in response to the above technical problems, which can quickly and accurately determine the scheduling potential of an electric vehicle cluster.

[0005] In a first aspect, the present application provides a method for determining the dispatch potential of an electric vehicle cluster, comprising:

[0006] Obtaining target dispatch demand information for the electric vehicle cluster within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region;

[0007] Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a scheduling constraint function of the electric vehicle cluster, the regulation potential function being used to characterize changes in the adjustable power of the electric vehicle cluster in a future time period, and the scheduling constraint function being used to constrain charging and discharging of the electric vehicle cluster;

[0008] Based on the regulation potential prediction model and according to the target scheduling demand information, the dispatchable range of the electric vehicle cluster in the future time period is determined.

[0009] In one embodiment, the regulation potential function is constructed based on a power upper limit variable representing an upper power limit value that can be adjusted by the electric vehicle cluster in a future period, and a power lower limit variable representing a lower power limit value that can be adjusted by the electric vehicle cluster in a future period.

[0010] In one embodiment, the regulatory potential function is constructed in the following manner:

[0011] using the difference between the power upper limit variable and the power lower limit variable as a first intermediate function;

[0012] multiplying the square of the first intermediate function by a preset weight coefficient as a second intermediate function;

[0013] The regulation potential function is constructed according to the difference between the first intermediate function and the second intermediate function.

[0014] In one embodiment, the scheduling constraint function includes the charging demand constraint of the electric vehicle cluster, the physical constraints of electric vehicle charging and discharging, and the physical constraints of charging and discharging of charging piles; the scheduling constraint function is constructed in the following manner:

[0015] Constructing the charging demand constraint according to the state of charge parameters and charging time parameters of each electric vehicle;

[0016] Constructing physical constraints on charging and discharging of the electric vehicles based on the charging and discharging operating parameters and state of charge parameters of each electric vehicle and the charging and discharging parameters of each charging pile;

[0017] The charging and discharging physical constraints of the charging pile are constructed according to the power upper limit variable, the power lower limit variable and the charging time parameters of each electric vehicle.

[0018] In one embodiment, the electric vehicle cluster regulation potential prediction model is constructed in the following manner:

[0019] Constructing an initial regulation potential prediction model according to the regulation potential function and the scheduling constraint function;

[0020] Acquire sample data; wherein the sample data includes historical dispatch demand information of the electric vehicle cluster in a reference period and a dispatchable range in a comparison period; wherein the comparison period is a period after the reference period;

[0021] The sample data is used to train the initial regulation potential prediction model to obtain the regulation potential prediction model of the electric vehicle cluster.

[0022] In one embodiment, obtaining sample data includes:

[0023] Obtaining historical demand information of the electric vehicle cluster within a reference period;

[0024] According to the historical demand information, the control potential function and the scheduling constraint function are updated respectively to obtain an updated control potential function and an updated scheduling constraint function;

[0025] Taking the maximum function value of the updated regulation potential function as the goal and the updated dispatch constraint function as the constraint condition, the updated regulation potential function is solved to obtain the dispatchable range of the electric vehicle in the comparison period.

[0026] In one embodiment, the charging demand information of each electric vehicle includes the remaining state of charge of the electric vehicle before charging, the target state of charge after charging, and the expected charging period; the battery status information of each electric vehicle includes the maximum chargeable state of charge and the minimum chargeable state of charge of the power battery of the electric vehicle; and the charging and discharging parameters of each charging pile include the maximum charging power and the maximum discharging power of the charging pile.

[0027] In a second aspect, the present application further provides a device for determining the dispatching potential of an electric vehicle cluster, comprising:

[0028] An information acquisition module is used to obtain target dispatch demand information of electric vehicle clusters in the area to which the power system belongs in the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile in the area to which the power system belongs;

[0029] A model acquisition module, configured to acquire a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a scheduling constraint function of the electric vehicle cluster, wherein the regulation potential function is used to characterize changes in the adjustable power of the electric vehicle cluster in a future period, and the scheduling constraint function is used to constrain the charging and discharging of the electric vehicle cluster;

[0030] A potential determination module is used to determine the dispatchable range of the electric vehicle cluster in the future period based on the regulation potential prediction model and the target scheduling demand information.

[0031] 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:

[0032] Obtaining target dispatch demand information for the electric vehicle cluster within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region;

[0033] Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a scheduling constraint function of the electric vehicle cluster, the regulation potential function being used to characterize changes in the adjustable power of the electric vehicle cluster in a future time period, and the scheduling constraint function being used to constrain charging and discharging of the electric vehicle cluster;

[0034] Based on the regulation potential prediction model and according to the target scheduling demand information, the dispatchable range of the electric vehicle cluster in the future time period is determined.

[0035] 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:

[0036] Obtaining target dispatch demand information for the electric vehicle cluster within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region;

[0037] Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a scheduling constraint function of the electric vehicle cluster, the regulation potential function being used to characterize changes in the adjustable power of the electric vehicle cluster in a future time period, and the scheduling constraint function being used to constrain charging and discharging of the electric vehicle cluster;

[0038] Based on the regulation potential prediction model and according to the target scheduling demand information, the dispatchable range of the electric vehicle cluster in the future time period is determined.

[0039] 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:

[0040] Obtaining target dispatch demand information for the electric vehicle cluster within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region;

[0041] Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a scheduling constraint function of the electric vehicle cluster, the regulation potential function being used to characterize changes in the adjustable power of the electric vehicle cluster in a future time period, and the scheduling constraint function being used to constrain charging and discharging of the electric vehicle cluster;

[0042] Based on the regulation potential prediction model and according to the target scheduling demand information, the dispatchable range of the electric vehicle cluster in the future time period is determined.

[0043] The above-mentioned method, device, equipment, and medium for determining the dispatch potential of an electric vehicle cluster introduce a regulation potential prediction model for the electric vehicle cluster. Since the regulation potential prediction model is determined based on the regulation potential function and dispatch constraint function of the electric vehicle cluster, it is equivalent to comprehensively considering the changes in the adjustable power of each electric vehicle in the electric vehicle cluster, ensuring that the constructed regulation potential prediction model can accurately simulate the changes in the adjustable power of the electric vehicle cluster during the charging process. Furthermore, by combining the regulation potential prediction model with charging demand information and battery status information of each electric vehicle, as well as target dispatch demand information including charging and discharging parameters of each charging pile in the power system area, the accuracy of the determined dispatchable range of the electric vehicle cluster in the future time period is guaranteed. At the same time, by introducing the regulation potential prediction model, the efficiency of determining the dispatchable range of the electric vehicle cluster in the future time period is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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.

[0045] Figure 1 A schematic flow chart of a method for determining the dispatch potential of an electric vehicle cluster in one embodiment;

[0046] Figure 2 A schematic diagram of a process for constructing a regulation potential function in one embodiment;

[0047] Figure 3 A schematic diagram of a process for constructing a scheduling constraint function in one embodiment;

[0048] Figure 4 A schematic diagram of a process for constructing a regulatory potential prediction model in one embodiment;

[0049] Figure 5A schematic diagram of a process for obtaining sample data in one embodiment;

[0050] Figure 6 A schematic diagram of a rolling evaluation calculation result when the maximum adjustable potential is used as a target in one embodiment;

[0051] Figure 7 A schematic flow chart of a method for determining the dispatch potential of an electric vehicle cluster in another embodiment;

[0052] Figure 8 A structural block diagram of a device for determining the dispatch potential of an electric vehicle cluster in one embodiment;

[0053] Figure 9 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] 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.

[0055] The method for determining the dispatch potential of an electric vehicle cluster provided in the embodiments of the present application can be applied to the dispatch process of a power grid system, and specifically can be applied to an application environment where the dispatch potential of an electric vehicle cluster is evaluated before the power grid system is dispatched. The method for determining the dispatch potential of an electric vehicle cluster provided in the embodiments of the present application can be executed by a computer device, which can be a server or a terminal with powerful computing capabilities.

[0056] In an exemplary embodiment, Figure 1 As shown, a method for determining the dispatching potential of an electric vehicle cluster is provided. The method is described by taking the application of the method to a server as an example, and specifically includes the following steps:

[0057] S101, obtaining target dispatch demand information of electric vehicle clusters in the area to which the power system belongs during the current period.

[0058] Among them, the electric vehicle cluster within the area to which the power system belongs is a cluster composed of electric vehicles within the area to which the power system belongs; specifically, in an embodiment of the present application, the electric vehicle cluster within the area to which the power system belongs can be a cluster composed of electric vehicles connected to charging piles within the area to which the power system belongs.

[0059] The target scheduling demand information includes the charging demand information and battery status information of each electric vehicle, as well as the charge and discharge parameters of each charging pile within the power system area. In this embodiment of the present application, the charging demand information of each electric vehicle includes the remaining state of charge of the electric vehicle before charging, the target state of charge after charging, and the expected charging period; the battery status information of each electric vehicle includes the maximum chargeable state of charge and the minimum chargeable state of charge of the power battery of the electric vehicle; and the charge and discharge parameters of each charging pile include the maximum charging power and the maximum discharge power of the charging pile.

[0060] Optionally, after an electric vehicle is connected to a charging pile, the charging pile collects various demand information related to the assessment of the adjustable potential of the electric vehicle cluster, including the charging demand of each user, the battery status information of each electric vehicle, and fixed parameter information such as charging and discharging of the charging pile. The charging demand of each user includes the remaining battery state of charge (SOC) of the vehicle in the current period, the estimated departure time of the vehicle, and the target battery SOC of the vehicle; the battery status information of the electric vehicle includes the maximum energy of the power battery, the maximum and minimum chargeable SOC of the power battery; and the fixed parameter information of charging and discharging of the charging pile includes the maximum charging power and maximum discharge power of the charging pile.

[0061] S102, obtaining a regulation potential prediction model for an electric vehicle cluster.

[0062] The control potential prediction model is a model that predicts the scheduling potential of an electric vehicle cluster in a future time period. In an embodiment of the present application, the control potential prediction model can be determined based on the control potential function and scheduling constraint function of the electric vehicle cluster. The control potential function is used to characterize the changes in the adjustable power of the electric vehicle cluster in the future time period, and the scheduling constraint function is used to constrain the charging and discharging of the electric vehicle cluster. In an embodiment of the present application, the control potential function is constructed based on a power upper limit variable that characterizes the upper limit value of the adjustable power of the electric vehicle cluster in the future time period, and a power lower limit variable that characterizes the lower limit value of the adjustable power of the electric vehicle cluster in the future time period.

[0063] The scheduling constraint function includes the charging demand constraint of the electric vehicle cluster, the physical constraint of electric vehicle charging and discharging, and the physical constraint of charging and discharging of charging piles.

[0064] Optionally, the control potential prediction model can be pre-built based on preset rules. In an embodiment of the present application, the control potential prediction model can be based on a neural network model and constructed and trained according to the control potential function and scheduling constraint function of the electric vehicle cluster. Furthermore, the pre-built control potential prediction model can be directly retrieved from a memory.

[0065] S103, based on the regulation potential prediction model and according to the target scheduling demand information, determine the dispatchable range of the electric vehicle cluster in the future period.

[0066] The dispatchable range of the electric vehicle cluster in the future period can be represented by the upper limit value and the lower limit value of the adjustable power of the electric vehicle cluster at each moment in the future period.

[0067] Optionally, the target scheduling demand information can be input into the regulation potential prediction model so that the model parameters of the regulation potential prediction model can perform computational analysis on the target scheduling demand information, and the output results of the regulation potential prediction model can be used as the dispatchable range of the electric vehicle cluster in the future period.

[0068] The above-mentioned method for determining the dispatch potential of an electric vehicle cluster introduces a regulation potential prediction model for the electric vehicle cluster. Since the regulation potential prediction model is determined based on the regulation potential function and dispatch constraint function of the electric vehicle cluster, it comprehensively considers the changes in the adjustable power of each electric vehicle in the electric vehicle cluster, ensuring that the constructed regulation potential prediction model can accurately simulate the changes in the adjustable power of the electric vehicle cluster during the charging process. Furthermore, by combining the regulation potential prediction model with the charging demand information and battery status information of each electric vehicle, as well as the target dispatch demand information of the charging and discharging parameters of each charging pile in the power system area, the accuracy of the determined dispatchable range of the electric vehicle cluster in the future time period is guaranteed. At the same time, by introducing the regulation potential prediction model, the efficiency of determining the dispatchable range of the electric vehicle cluster in the future time period is improved.

[0069] Optionally, in one embodiment, Figure 2 As shown, a method for constructing a regulatory potential function is provided, which specifically includes the following steps:

[0070] S201 : Taking the difference between the upper power limit variable and the lower power limit variable as a first intermediate function.

[0071] Optionally, the power upper limit variable and the power lower limit variable may be subtracted, and the difference obtained by the subtraction may be used as a first intermediate function. Specifically, the first intermediate function may be expressed by the following formula (1):

[0072] Ω1=P + (t)-P - (t) (1)

[0073] Where, Ω1 represents the first intermediate function; P + (t) is the power upper limit variable of the electric vehicle cluster during period t; P - (t) is the power lower limit variable of the electric vehicle cluster during period t.

[0074] S202: Multiplying the square of the first intermediate function by a preset weight coefficient is used as a second intermediate function.

[0075] Optionally, the product of the square of the first intermediate function and the preset weight coefficient can be used as the second intermediate function. Specifically, the second intermediate function can be expressed by the following formula (2):

[0076] Ω2=π1(P + (t)-P - (t)) 2 (2)

[0077] Among them, Ω2 represents the second intermediate function; π1 is the preset weight coefficient, and the quadratic term (P + (t)-P - (t)) 2 The adjustable potential of the electric vehicle cluster is distributed more evenly in time, and the weight coefficient can adjust the intensity of the quadratic term on the objective function.

[0078] S203: Constructing a regulation potential function according to the difference between the first intermediate function and the second intermediate function.

[0079] Optionally, the process of constructing the control potential function based on the difference between the first intermediate function and the second intermediate function can be expressed by the following formula (3):

[0080]

[0081] β ′ =max (β1,…,β i ,…,β N ) (4)

[0082] F P ={(P + (t1),P - (t1)),…,(P + (β ′ ),P - (β ′ )) (5)

[0083] Where Ω represents the regulatory potential function; F P is the set of power upper limit variables and power lower limit variables of the electric vehicle cluster within the adjustable time range of the electric vehicle cluster; β ′ is the departure time of the last electric vehicle expected to leave in the current period. t1 is the initial time; N is the number of electric vehicles in the electric vehicle cluster; β i is the estimated departure time of the i-th electric car last night.

[0084] In an embodiment of the present application, by introducing a first intermediate function, a second intermediate function and a preset weight coefficient, a method for accurately and quickly constructing a control potential function is provided; at the same time, based on the power upper limit variable and the power lower limit variable, the constructed control potential function can accurately characterize the power changes of the electric vehicle cluster during the charging and discharging process.

[0085] Optionally, the scheduling constraint function includes the charging demand constraint of the electric vehicle cluster, the physical constraint of electric vehicle charging and discharging, and the physical constraint of charging and discharging of the charging pile; based on the above embodiment, in one embodiment, if Figure 3 As shown, a method for constructing a scheduling constraint function is provided, which specifically includes the following steps:

[0086] S301: Constructing charging demand constraints based on the state of charge parameters and charging time parameters of each electric vehicle.

[0087] The charging demand constraint is a constraint on the amount of electricity required by the electric vehicle cluster during charging. The state of charge parameter is a parameter that characterizes the change in the state of charge of the power battery during charging. The charging time parameter is a parameter that characterizes the charging time of the electric vehicle.

[0088] Optionally, the process of constructing charging demand constraints based on the state of charge parameters and charging time parameters of each electric vehicle can be expressed by the following formulas (6) to (10):

[0089] s i (t1) = s 1,i (6)

[0090]

[0091] Among them, s 1,i is the state of charge parameter, which represents the remaining battery state of charge of the i-th electric vehicle before charging; s 2,i is the state of charge parameter, which represents the target battery state of charge of the i-th electric vehicle after charging; is the state of charge parameter, which represents the maximum chargeable state of the power battery of the i-th electric vehicle; is the state of charge parameter, which represents the minimum chargeable state of the power battery of the i-th electric vehicle; β i is the charging time parameter.

[0092] S302 : constructing electric vehicle charging and discharging physical constraints based on the charging and discharging operating parameters and state of charge parameters of each electric vehicle and the charging and discharging parameters of each charging pile.

[0093] Optionally, based on the charging and discharging operating parameters and state of charge parameters of each electric vehicle, as well as the charging and discharging parameters of each charging pile, the process of constructing the physical constraints of electric vehicle charging and discharging can be expressed by the following formulas (11) to (17):

[0094]

[0095] in, and are the charging and discharging condition parameters, respectively representing the charging and discharging decision parameters of the i-th electric vehicle, and they are not 1 at the same time; η c and η d are the charging and discharging parameters, representing the charging and discharging efficiency of the electric vehicle; Δ is the duration of each period; e i is the state of charge parameter, which represents the maximum energy of the power battery of the i-th electric vehicle; and are the charging and discharging parameters of the charging pile, which respectively represent the maximum charging power and maximum discharging power of the charging pile connected to the i-th electric vehicle.

[0096] S303: Construct charging and discharging physical constraints of the charging pile according to the power upper limit variable, the power lower limit variable and the charging time parameters of each electric vehicle.

[0097] Optionally, based on the power upper limit variable, the power lower limit variable and the charging time parameters of each electric vehicle, the process of constructing the charging and discharging physical constraints of the charging pile can be expressed by the following formula (18):

[0098]

[0099] In this embodiment, through the charging demand constraints of the electric vehicle cluster, the physical constraints of electric vehicle charging and discharging, and the physical constraints of charging and discharging of charging piles, the constructed scheduling constraint function can comprehensively consider the charging demand and charging and discharging conditions of electric vehicles, as well as the charging and discharging conditions of charging piles, thereby ensuring the accuracy and comprehensiveness of the constructed scheduling constraint function.

[0100] Optionally, in one embodiment, Figure 4 As shown, a method for constructing a regulation potential prediction model for an electric vehicle cluster is provided, which specifically includes the following steps:

[0101] S401: Construct an initial regulation potential prediction model based on the regulation potential function and the scheduling constraint function.

[0102] Optionally, an initial regulation potential prediction model can be constructed based on a neural network framework according to the parameters in the regulation potential function and the scheduling constraint function.

[0103] Exemplarily, the input of the constructed initial regulation potential prediction model can be the historical scheduling demand information of the electric vehicle cluster during the reference period, such as the charging demand of each user, the battery status information of each electric vehicle, the charging and discharging of the charging pile and other fixed parameter information; the output can be the dispatchable range of the electric vehicle cluster during the comparison period; wherein the comparison period is the period after the reference period.

[0104] S402, obtaining sample data.

[0105] The sample data includes the historical dispatch demand information of the electric vehicle cluster in the reference period and the dispatchable range in the comparison period; the reference period can be any pre-set historical period; the comparison period is the period after the reference period.

[0106] Optionally, the historical dispatch demand information of the electric vehicle cluster during the reference period can be obtained from all charging piles in the area to which the power system belongs, and the dispatchable range of the electric vehicle cluster during the comparison period can be calculated based on the historical dispatch demand information; further, the historical dispatch demand information of the electric vehicle cluster during the reference period and the dispatchable range during the comparison period are used as sample data.

[0107] S403 , using sample data to train the initial regulation potential prediction model to obtain a regulation potential prediction model for the electric vehicle cluster.

[0108] Optionally, to ensure the integrity and usability of the sample data, the sample data can be preprocessed. Furthermore, the preprocessed sample data is divided into a training set and a test set. The training set is used to train the initial regulation potential prediction model, and the test set is used to train and test the initially trained regulation potential prediction model. When the calculated loss value meets the requirements, the training process is terminated, thereby obtaining the regulation potential prediction model for the electric vehicle cluster.

[0109] In an embodiment of the present application, an initial control potential prediction model is constructed based on the control potential function and the scheduling constraint function, and the initial control potential prediction model is further trained to ensure the accuracy of the constructed control potential prediction model of the electric vehicle cluster; in addition, the introduced control potential prediction model realizes the rapid fitting and solution of the parameter system between the control potential function and the scheduling constraint function.

[0110] Optionally, in one embodiment, Figure 5 As shown, a method for obtaining sample data is provided to refine the above S402, which specifically includes the following steps:

[0111] S501, obtaining historical demand information of an electric vehicle cluster within a reference period.

[0112] Optionally, historical dispatch demand information of the electric vehicle cluster during the reference period can be obtained from all charging piles in the area to which the power system belongs.

[0113] S502 : updating the control potential function and the scheduling constraint function respectively according to the historical demand information to obtain an updated control potential function and an updated scheduling constraint function.

[0114] Optionally, the parameters involved in the historical demand information are substituted into the control potential function and the scheduling constraint function respectively to update the control potential function and the scheduling constraint function, thereby obtaining the updated control potential function and the updated scheduling constraint function.

[0115] S503 , taking the maximum function value of the updated control potential function as the goal and the updated dispatch constraint function as the constraint condition, solves the updated control potential function to obtain the dispatchable range of the electric vehicle in the comparison period.

[0116] Optionally, a preset solution algorithm is used, with the goal of maximizing the function value of the updated control potential function and the updated scheduling constraint function as a constraint condition, to solve the updated control potential function, and the values ​​of the power upper limit variable and the power lower limit variable when the function value of the control potential function is maximum are used as the dispatchable range of the electric vehicle during the comparison period.

[0117] In an embodiment of the present application, by obtaining historical demand information and solving the control potential function based on the historical demand information, the accuracy of the dispatchable range of electric vehicles in the comparison period is ensured, thereby ensuring the accuracy of the control potential prediction model obtained by training using sample data.

[0118] Optionally, to clearly and intuitively describe the implementation process and effects of the method for determining the dispatch potential of an electric vehicle cluster provided in an embodiment of the present application, a specific example is provided in one embodiment. Specifically, the method was developed and implemented using the Pycharm development platform and the Python 3.8 programming language, and the testing and verification of this embodiment was completed using a PC equipped with an Intel Xeon-X5650 2.6GHz CPU and 24GB of memory.

[0119] In one embodiment, a technical verification was conducted around a residential electric vehicle charging station. An operational scenario was constructed based on electric vehicle charging demand data from a residential complex. The complex is equipped with 30 bidirectional charging and discharging stations. The evaluation and control interval is 15 minutes, and control is available at all times of the day. The rated charge and discharge power of each charging station is 30 kW. It is assumed that all connected electric vehicles have a power battery capacity of 120 kWh, a maximum state of charge (SOC) of 0.98, and a minimum state of charge (SOC) of 0.02. Because the verification scenario is a residential complex, the common charging pattern for electric vehicles is "late return, early departure." Vehicle arrival times are uniformly distributed between 7 p.m. and 9 p.m., and vehicle expected departure times are uniformly distributed between 7 a.m. and 10 a.m. The maximum charging and discharging powers of all connected charging stations, as well as the maximum and minimum chargeable state of charge (SOC) of the power batteries, are fixed values ​​and not used as inputs. Four variables—the current remaining battery state of charge of all electric vehicles, the expected departure time, the target battery capacity, and the maximum energy capacity of all electric vehicles' power batteries—are used as inputs to the control potential prediction model. The hyperparameter settings for the control potential prediction model are shown in Table 1.

[0120] Table 1 Model structure of regulatory potential prediction model

[0121]

[0122] Using the sample data acquisition method provided in the above example, 2,000 samples were generated. 80% of these samples were randomly selected as the training set, and 20% as the test set. A back-propagation neural network was used for the regulatory potential prediction model. After debugging, a back-propagation neural network with three hidden layers and 50 neurons per layer performed optimally when the number of electric vehicles was 30.

[0123] like Figure 6 The figure shows the rolling evaluation results for the maximum adjustable power potential. In this case, the power execution trajectory provided by the regulatory agency is assumed to schedule the EV cluster near the midpoint of the adjustable power upper and lower bounds. During the rolling optimization process, the adjustable power potential evaluation model did not encounter any unsolvable problems. The feasibility of the evaluation model means that EV user demand can be met as long as the cluster power falls within the upper and lower bounds in the future time period.

[0124] Table 2 shows a comparison of the inference speed of the control potential prediction model (proxy model) and directly solving the control potential function (mechanism model). This comparison compares the average single-shot inference time (excluding other program execution time) of the control potential prediction model and the mechanism model when evaluating the control flexibility of clusters with different numbers of electric vehicles. Table 2 clearly shows that the average inference time of the control potential prediction model ranges from 1ms to 3ms.

[0125] Table 2 Comparison of inference speed between proxy model and optimized model (unit: seconds)

[0126]

[0127] Figure 7 This is a flow chart of a method for determining the dispatching potential of an electric vehicle cluster in another embodiment. Based on the above embodiment, this embodiment provides an optional example of a method for determining the dispatching potential of an electric vehicle cluster. Figure 7 The specific implementation process is as follows:

[0128] S701: Use the difference between the upper power limit variable and the lower power limit variable as a first intermediate function.

[0129] S702: Multiply the square of the first intermediate function by a preset weight coefficient as a second intermediate function.

[0130] S703: Construct a regulation potential function according to the difference between the first intermediate function and the second intermediate function.

[0131] S704: Constructing a charging demand constraint in a scheduling constraint function based on the state of charge parameters and charging time parameters of each electric vehicle.

[0132] S705 , constructing electric vehicle charging and discharging physical constraints in the scheduling constraint function based on the charging and discharging operating condition parameters and charge state parameters of each electric vehicle and the charging and discharging parameters of each charging pile.

[0133] S706 , constructing charging and discharging physical constraints of the charging pile in the scheduling constraint function according to the power upper limit variable, the power lower limit variable and the charging time parameters of each electric vehicle.

[0134] S707: Construct an initial regulation potential prediction model based on the regulation potential function and the scheduling constraint function.

[0135] S708, obtaining sample data.

[0136] Among them, the sample data includes the historical scheduling demand information of the electric vehicle cluster in the reference period and the scheduling range in the comparison period; the comparison period is the period after the reference period.

[0137] Optionally, historical demand information of the electric vehicle cluster during a reference period is obtained; based on the historical demand information, the control potential function and the scheduling constraint function are updated respectively to obtain an updated control potential function and an updated scheduling constraint function; with the maximum function value of the updated control potential function as the goal and the updated scheduling constraint function as the constraint condition, the updated control potential function is solved to obtain the dispatchable range of the electric vehicle during the comparison period.

[0138] S709 , using sample data to train the initial regulation potential prediction model to obtain a regulation potential prediction model for the electric vehicle cluster.

[0139] S710: Obtain target dispatch demand information of electric vehicle clusters in the area to which the power system belongs during the current period.

[0140] The target scheduling demand information includes the charging demand information and battery status information of each electric vehicle, as well as the charging and discharging parameters of each charging pile in the area to which the power system belongs.

[0141] S711, based on the regulation potential prediction model and according to the target scheduling demand information, determine the dispatchable range of the electric vehicle cluster in the future period.

[0142] The specific process of S701-S711 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.

[0143] 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.

[0144] Based on the same inventive concept, an embodiment of the present application further provides a device for determining the dispatch potential of an electric vehicle cluster, which is used to implement the aforementioned method for determining the dispatch potential of an electric vehicle cluster. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in the embodiments of the device for determining the dispatch potential of one or more electric vehicle clusters provided below can be found in the aforementioned method for determining the dispatch potential of an electric vehicle cluster, and will not be repeated here.

[0145] In an exemplary embodiment, Figure 8 As shown, a device 800 for determining the dispatch potential of an electric vehicle cluster is provided, comprising: an information acquisition module 810, a model acquisition module 820 and a potential determination module 830, wherein:

[0146] The information acquisition module 810 is used to obtain the target scheduling demand information of the electric vehicle cluster in the area to which the power system belongs in the current period; wherein the target scheduling demand information includes the charging demand information and battery status information of each electric vehicle, as well as the charging and discharging parameters of each charging pile in the area to which the power system belongs.

[0147] The model acquisition module 820 is used to obtain a control potential prediction model for an electric vehicle cluster. The control potential prediction model is determined based on the control potential function and the scheduling constraint function of the electric vehicle cluster. The control potential function is used to characterize the change in the adjustable power of the electric vehicle cluster in the future period. The scheduling constraint function is used to constrain the charging and discharging of the electric vehicle cluster.

[0148] The potential determination module 830 is used to determine the dispatchable range of the electric vehicle cluster in the future period based on the regulation potential prediction model and the target dispatch demand information.

[0149] The above-mentioned device for determining the dispatch potential of an electric vehicle cluster introduces a regulation potential prediction model for the electric vehicle cluster. Since the regulation potential prediction model is determined based on the regulation potential function and dispatch constraint function of the electric vehicle cluster, it comprehensively considers the changes in the adjustable power of each electric vehicle in the electric vehicle cluster, ensuring that the constructed regulation potential prediction model can accurately simulate the changes in the adjustable power of the electric vehicle cluster during the charging process. Furthermore, by combining the regulation potential prediction model with charging demand information and battery status information of each electric vehicle, as well as target dispatch demand information including charging and discharging parameters of each charging pile in the power system area, the accuracy of the determined dispatchable range of the electric vehicle cluster in the future time period is guaranteed. At the same time, by introducing the regulation potential prediction model, the efficiency of determining the dispatchable range of the electric vehicle cluster in the future time period is improved.

[0150] In one embodiment, the regulation potential function is constructed based on a power upper limit variable representing an upper power limit value that can be adjusted by the electric vehicle cluster in a future period, and a power lower limit variable representing a lower power limit value that can be adjusted by the electric vehicle cluster in a future period.

[0151] In one embodiment, the electric vehicle cluster dispatch potential determination device 800 further includes:

[0152] The first function unit is configured to use the difference between the upper power limit variable and the lower power limit variable as a first intermediate function.

[0153] The second function unit is configured to take the product of the square of the first intermediate function and a preset weight coefficient as the second intermediate function.

[0154] The first construction unit is used to construct a control potential function according to the difference between the first intermediate function and the second intermediate function.

[0155] In one embodiment, the scheduling potential determination device 800 further includes:

[0156] The second constructing unit is used to construct a charging demand constraint according to the state of charge parameters and charging time parameters of each electric vehicle.

[0157] The third construction unit is used to construct the electric vehicle charging and discharging physical constraints according to the charging and discharging operating condition parameters and charge state parameters of each electric vehicle and the charging and discharging parameters of each charging pile.

[0158] The fourth construction unit is used to construct charging and discharging physical constraints of the charging pile according to the power upper limit variable, the power lower limit variable and the charging time parameters of each electric vehicle.

[0159] In one embodiment, the scheduling potential determination device 800 further includes:

[0160] The first construction module is used to construct an initial regulation potential prediction model based on the regulation potential function and the scheduling constraint function.

[0161] The data acquisition module is used to obtain sample data; wherein the sample data includes the historical scheduling demand information of the electric vehicle cluster in the reference period and the scheduling range in the comparison period; the comparison period is the period after the reference period.

[0162] The model training module is used to train the initial regulation potential prediction model using sample data to obtain the regulation potential prediction model of the electric vehicle cluster.

[0163] In one embodiment, the data acquisition module is specifically configured to:

[0164] Obtain historical demand information of the electric vehicle cluster during a reference period; based on the historical demand information, update the control potential function and the scheduling constraint function respectively to obtain an updated control potential function and an updated scheduling constraint function; with the maximum function value of the updated control potential function as the goal and the updated scheduling constraint function as the constraint condition, solve the updated control potential function to obtain the dispatchable range of electric vehicles during the comparison period.

[0165] In one embodiment, the charging demand information of each electric vehicle includes the remaining state of charge of the electric vehicle before charging, the target state of charge after charging, and the expected charging period; the battery status information of each electric vehicle includes the maximum chargeable state of charge and the minimum chargeable state of charge of the power battery of the electric vehicle; and the charging and discharging parameters of each charging pile include the maximum charging power and the maximum discharging power of the charging pile.

[0166] Each module in the above-mentioned apparatus for determining the dispatch potential of an electric vehicle cluster can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in the form of software in a memory in the computer device, so that the processor can call and execute the corresponding operations of each module.

[0167] 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, a method for determining the scheduling potential of an electric vehicle cluster is implemented.

[0168] 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.

[0169] 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:

[0170] Obtaining target dispatch demand information for electric vehicle clusters within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region;

[0171] Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a dispatch constraint function of the electric vehicle cluster, the regulation potential function is used to characterize changes in the adjustable power of the electric vehicle cluster in a future period, and the dispatch constraint function is used to constrain charging and discharging of the electric vehicle cluster;

[0172] Based on the regulation potential prediction model and the target scheduling demand information, the dispatchable range of the electric vehicle cluster in the future period is determined.

[0173] In one embodiment, the regulation potential function is constructed based on a power upper limit variable representing an upper power limit value that can be adjusted by the electric vehicle cluster in a future period, and a power lower limit variable representing a lower power limit value that can be adjusted by the electric vehicle cluster in a future period.

[0174] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0175] The difference between the power upper limit variable and the power lower limit variable is used as the first intermediate function; the product of the square of the first intermediate function and the preset weight coefficient is used as the second intermediate function; and a control potential function is constructed based on the difference between the first intermediate function and the second intermediate function.

[0176] In one embodiment, the scheduling constraint function includes a charging demand constraint of the electric vehicle cluster, a physical constraint on electric vehicle charging and discharging, and a physical constraint on charging and discharging of a charging pile; and when the processor executes the computer program, the processor further implements the following steps:

[0177] Based on the state of charge parameters and charging time parameters of each electric vehicle, the charging demand constraints are constructed; based on the charging and discharging operating parameters and state of charge parameters of each electric vehicle, as well as the charging and discharging parameters of each charging pile, the charging and discharging physical constraints of the electric vehicle are constructed; based on the power upper limit variable, power lower limit variable and the charging time parameters of each electric vehicle, the charging and discharging physical constraints of the charging pile are constructed.

[0178] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0179] An initial regulation potential prediction model is constructed based on the regulation potential function and the scheduling constraint function; sample data is obtained; wherein the sample data includes the historical scheduling demand information of the electric vehicle cluster in a reference period and the scheduling range in a comparison period; the comparison period is the period after the reference period; the sample data is used to train the initial regulation potential prediction model to obtain a regulation potential prediction model for the electric vehicle cluster.

[0180] In one embodiment, when the processor executes the computer program to obtain sample data, the processor further implements the following steps:

[0181] Obtain historical demand information of the electric vehicle cluster during a reference period; based on the historical demand information, update the control potential function and the scheduling constraint function respectively to obtain an updated control potential function and an updated scheduling constraint function; with the maximum function value of the updated control potential function as the goal and the updated scheduling constraint function as the constraint condition, solve the updated control potential function to obtain the dispatchable range of electric vehicles during the comparison period.

[0182] In one embodiment, the charging demand information of each electric vehicle includes the remaining state of charge of the electric vehicle before charging, the target state of charge after charging, and the expected charging period; the battery status information of each electric vehicle includes the maximum chargeable state of charge and the minimum chargeable state of charge of the power battery of the electric vehicle; and the charging and discharging parameters of each charging pile include the maximum charging power and the maximum discharging power of the charging pile.

[0183] 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:

[0184] Obtaining target dispatch demand information for electric vehicle clusters within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region;

[0185] Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a dispatch constraint function of the electric vehicle cluster, the regulation potential function is used to characterize changes in the adjustable power of the electric vehicle cluster in a future period, and the dispatch constraint function is used to constrain charging and discharging of the electric vehicle cluster;

[0186] Based on the regulation potential prediction model and the target scheduling demand information, the dispatchable range of the electric vehicle cluster in the future period is determined.

[0187] In one embodiment, the regulation potential function is constructed based on a power upper limit variable representing an upper power limit value that can be adjusted by the electric vehicle cluster in a future period, and a power lower limit variable representing a lower power limit value that can be adjusted by the electric vehicle cluster in a future period.

[0188] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0189] The difference between the power upper limit variable and the power lower limit variable is used as the first intermediate function; the product of the square of the first intermediate function and the preset weight coefficient is used as the second intermediate function; and a control potential function is constructed based on the difference between the first intermediate function and the second intermediate function.

[0190] In one embodiment, the scheduling constraint function includes a charging demand constraint of the electric vehicle cluster, a physical constraint on electric vehicle charging and discharging, and a physical constraint on charging and discharging of a charging pile; and when the processor executes the computer program, the processor further implements the following steps:

[0191] Based on the state of charge parameters and charging time parameters of each electric vehicle, the charging demand constraints are constructed; based on the charging and discharging operating parameters and state of charge parameters of each electric vehicle, as well as the charging and discharging parameters of each charging pile, the charging and discharging physical constraints of the electric vehicle are constructed; based on the power upper limit variable, power lower limit variable and the charging time parameters of each electric vehicle, the charging and discharging physical constraints of the charging pile are constructed.

[0192] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0193] An initial regulation potential prediction model is constructed based on the regulation potential function and the scheduling constraint function; sample data is obtained; wherein the sample data includes the historical scheduling demand information of the electric vehicle cluster in a reference period and the scheduling range in a comparison period; the comparison period is the period after the reference period; the sample data is used to train the initial regulation potential prediction model to obtain a regulation potential prediction model for the electric vehicle cluster.

[0194] In one embodiment, when the processor executes the computer program to obtain sample data, the processor further implements the following steps:

[0195] Obtain historical demand information of the electric vehicle cluster during a reference period; based on the historical demand information, update the control potential function and the scheduling constraint function respectively to obtain an updated control potential function and an updated scheduling constraint function; with the maximum function value of the updated control potential function as the goal and the updated scheduling constraint function as the constraint condition, solve the updated control potential function to obtain the dispatchable range of electric vehicles during the comparison period.

[0196] In one embodiment, the charging demand information of each electric vehicle includes the remaining state of charge of the electric vehicle before charging, the target state of charge after charging, and the expected charging period; the battery status information of each electric vehicle includes the maximum chargeable state of charge and the minimum chargeable state of charge of the power battery of the electric vehicle; and the charging and discharging parameters of each charging pile include the maximum charging power and the maximum discharging power of the charging pile.

[0197] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0198] Obtaining target dispatch demand information for electric vehicle clusters within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region;

[0199] Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a dispatch constraint function of the electric vehicle cluster, the regulation potential function is used to characterize changes in the adjustable power of the electric vehicle cluster in a future period, and the dispatch constraint function is used to constrain charging and discharging of the electric vehicle cluster;

[0200] Based on the regulation potential prediction model and the target scheduling demand information, the dispatchable range of the electric vehicle cluster in the future period is determined.

[0201] In one embodiment, the regulation potential function is constructed based on a power upper limit variable representing an upper power limit value that can be adjusted by the electric vehicle cluster in a future period, and a power lower limit variable representing a lower power limit value that can be adjusted by the electric vehicle cluster in a future period.

[0202] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0203] The difference between the power upper limit variable and the power lower limit variable is used as the first intermediate function; the product of the square of the first intermediate function and the preset weight coefficient is used as the second intermediate function; and a control potential function is constructed based on the difference between the first intermediate function and the second intermediate function.

[0204] In one embodiment, the scheduling constraint function includes a charging demand constraint of the electric vehicle cluster, a physical constraint on electric vehicle charging and discharging, and a physical constraint on charging and discharging of a charging pile; and when the processor executes the computer program, the processor further implements the following steps:

[0205] Based on the state of charge parameters and charging time parameters of each electric vehicle, the charging demand constraints are constructed; based on the charging and discharging operating parameters and state of charge parameters of each electric vehicle, as well as the charging and discharging parameters of each charging pile, the charging and discharging physical constraints of the electric vehicle are constructed; based on the power upper limit variable, power lower limit variable and the charging time parameters of each electric vehicle, the charging and discharging physical constraints of the charging pile are constructed.

[0206] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0207] An initial regulation potential prediction model is constructed based on the regulation potential function and the scheduling constraint function; sample data is obtained; wherein the sample data includes the historical scheduling demand information of the electric vehicle cluster in a reference period and the scheduling range in a comparison period; the comparison period is the period after the reference period; the sample data is used to train the initial regulation potential prediction model to obtain a regulation potential prediction model for the electric vehicle cluster.

[0208] In one embodiment, when the processor executes the computer program to obtain sample data, the processor further implements the following steps:

[0209] Obtain historical demand information of the electric vehicle cluster during a reference period; based on the historical demand information, update the control potential function and the scheduling constraint function respectively to obtain an updated control potential function and an updated scheduling constraint function; with the maximum function value of the updated control potential function as the goal and the updated scheduling constraint function as the constraint condition, solve the updated control potential function to obtain the dispatchable range of electric vehicles during the comparison period.

[0210] In one embodiment, the charging demand information of each electric vehicle includes the remaining state of charge of the electric vehicle before charging, the target state of charge after charging, and the expected charging period; the battery status information of each electric vehicle includes the maximum chargeable state of charge and the minimum chargeable state of charge of the power battery of the electric vehicle; and the charging and discharging parameters of each charging pile include the maximum charging power and the maximum discharging power of the charging pile.

[0211] It should be noted that the user information (including but not limited to target scheduling demand 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.

[0212] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and 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 embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may 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 may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database 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 processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0213] 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.

[0214] 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 determining the dispatching potential of an electric vehicle cluster, characterized in that: The method comprises: Obtaining target dispatch demand information for the electric vehicle cluster within the power system region during the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile within the power system region; Obtaining a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a scheduling constraint function of the electric vehicle cluster, the regulation potential function is used to characterize changes in the adjustable power of the electric vehicle cluster in a future time period, the scheduling constraint function is used to constrain the charging and discharging of the electric vehicle cluster, and the regulation potential function is constructed based on a power upper limit variable that characterizes an upper limit value of the adjustable power of the electric vehicle cluster in a future time period, and a power lower limit variable that characterizes a lower limit value of the adjustable power of the electric vehicle cluster in a future time period; Based on the regulation potential prediction model and according to the target scheduling demand information, determining the dispatchable range of the electric vehicle cluster in the future period; Wherein, the regulatory potential function is constructed in the following manner: using the difference between the power upper limit variable and the power lower limit variable as a first intermediate function; multiplying the square of the first intermediate function by a preset weight coefficient as a second intermediate function; constructing the regulation potential function according to the difference between the first intermediate function and the second intermediate function; The electric vehicle cluster regulation potential prediction model is constructed in the following way: Constructing an initial regulation potential prediction model according to the regulation potential function and the scheduling constraint function; Acquire sample data; wherein the sample data includes historical dispatch demand information of the electric vehicle cluster in a reference period and a dispatchable range in a comparison period; the comparison period is a period after the reference period; The sample data is used to train the initial regulation potential prediction model to obtain the regulation potential prediction model of the electric vehicle cluster.

2. The method according to claim 1, characterized in that The scheduling constraint function includes the charging demand constraint of the electric vehicle cluster, the physical constraints of electric vehicle charging and discharging, and the physical constraints of charging and discharging of charging piles; the scheduling constraint function is constructed in the following way: Constructing the charging demand constraint according to the state of charge parameters and charging time parameters of each electric vehicle; Constructing physical constraints on charging and discharging of the electric vehicles based on the charging and discharging operating parameters and state of charge parameters of each electric vehicle and the charging and discharging parameters of each charging pile; The charging and discharging physical constraints of the charging pile are constructed according to the power upper limit variable, the power lower limit variable and the charging time parameters of each electric vehicle.

3. The method according to claim 1, characterized in that The obtaining of sample data includes: Obtaining historical demand information of the electric vehicle cluster within a reference period; According to the historical demand information, the control potential function and the scheduling constraint function are updated respectively to obtain an updated control potential function and an updated scheduling constraint function; Taking the maximum function value of the updated regulation potential function as the goal and the updated dispatch constraint function as the constraint condition, the updated regulation potential function is solved to obtain the dispatchable range of the electric vehicle in the comparison period.

4. The method according to any one of claims 1 to 3, characterized in that The charging demand information of each electric vehicle includes the remaining state of charge of the electric vehicle before charging, the target state of charge after charging, and the expected charging period; the battery status information of each electric vehicle includes the maximum chargeable state of charge and the minimum chargeable state of charge of the power battery of the electric vehicle; the charging and discharging parameters of each charging pile include the maximum charging power and maximum discharging power of the charging pile.

5. A device for determining the dispatching potential of an electric vehicle cluster, characterized in that: The device comprises: An information acquisition module is used to obtain target dispatch demand information of electric vehicle clusters in the area to which the power system belongs in the current period; wherein the target dispatch demand information includes charging demand information and battery status information of each electric vehicle, as well as charging and discharging parameters of each charging pile in the area to which the power system belongs; a model acquisition module, configured to acquire a regulation potential prediction model for the electric vehicle cluster; wherein the regulation potential prediction model is determined based on a regulation potential function and a scheduling constraint function of the electric vehicle cluster, the regulation potential function being used to characterize changes in the adjustable power of the electric vehicle cluster in a future time period, the scheduling constraint function being used to constrain the charging and discharging of the electric vehicle cluster, and the regulation potential function being constructed based on a power upper limit variable characterizing an upper limit value of the adjustable power of the electric vehicle cluster in a future time period, and a power lower limit variable characterizing a lower limit value of the adjustable power of the electric vehicle cluster in a future time period; a potential determination module, configured to determine a dispatchable range of the electric vehicle cluster in the future period based on the regulation potential prediction model and the target dispatch demand information; Wherein, the device further comprises: a first function unit, configured to use a difference between the upper power limit variable and the lower power limit variable as a first intermediate function; A second function unit, configured to multiply the square of the first intermediate function by a preset weight coefficient as a second intermediate function; a first constructing unit, configured to construct the regulation potential function according to a difference between the first intermediate function and the second intermediate function; The device further comprises: A first construction module is used to construct an initial regulation potential prediction model based on the regulation potential function and the scheduling constraint function; A data acquisition module, configured to acquire sample data; wherein the sample data includes historical dispatch demand information of the electric vehicle cluster within a reference period and a dispatchable range within a comparison period; the comparison period is a period after the reference period; A model training module is used to train the initial regulation potential prediction model using the sample data to obtain the regulation potential prediction model of the electric vehicle cluster.

6. 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 4 are implemented.

7. 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 4 are implemented.

Images