Processing method and device of electric vehicle charging data and electronic equipment

Abstract

The application discloses a kind of electric vehicle charging data processing method, device and electronic equipment.The method comprises: obtaining preset charging set, wherein, preset charging set includes: the preset charging node of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data;Using charging demand probability distribution model to analyze multiple preset charging nodes, determine the predicted charging data of each preset charging node, charging demand probability distribution model is used to determine the influence of preset resource data on preset charging data based on charging time data and charging space data;Predicted charging data is analyzed using particle swarm algorithm, target resource data is determined in multiple preset resource data of each preset charging node, and target charging capacity data corresponding to target resource data.The present application solves the technical problem of low utilization of charging resources in virtual power station aggregation.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to a method, device and electronic equipment for processing electric vehicle charging data. Background Art

[0002] As a new mode of transportation and a distributed power load with energy storage capabilities, electric vehicles (EVs) not only meet energy conservation and emission reduction policy requirements but also reduce reliance on traditional fossil fuels, making them a crucial component of the Energy Internet. EV charging stations are key equipment for vehicle-grid interaction. Pricing research for EV charging stations can effectively improve the operational efficiency of EV charging stations and enhance the economic efficiency of energy systems.

[0003] However, the existing pricing research process for electric vehicle charging stations does not adequately consider factors that affect electricity prices, resulting in low charging resource utilization in virtual power station aggregation.

[0004] With respect to the above-mentioned problem of low charging resource utilization in virtual power station aggregation, no effective solution has been proposed so far. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, and electronic device for processing electric vehicle charging data, so as to at least solve the technical problem of low charging resource utilization in virtual power station aggregation.

[0006] According to one aspect of an embodiment of the present invention, a method for processing electric vehicle charging data is provided, comprising: obtaining a preset charging set, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each of the preset charging nodes including: charging time data, charging space data, and multiple preset resource data, wherein the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to a unit of charging amount; analyzing the multiple preset charging nodes using a charging demand probability distribution model to determine predicted charging data for each preset charging node, wherein the charging demand probability distribution model is used to determine the impact of the preset resource data on preset charging amount data based on the charging time data and the charging space data, the predicted charging data represents the preset charging amount data corresponding to the multiple preset resource data in each preset charging node, and the distribution probability of each preset charging amount data, and the preset charging amount data represents the maximum charging amount expected to be consumed by the preset charging node; and analyzing the predicted charging data using a particle swarm algorithm to determine target resource data and target charging amount data corresponding to the target resource data from the multiple preset resource data of each preset charging node.

[0007] Optionally, obtaining the preset charging set includes: obtaining geographic location data of multiple preset charging stations; clustering the multiple preset charging stations based on the geographic location data to obtain multiple clusters; allocating a corresponding virtual charging station to each cluster; and establishing the preset charging node corresponding to each virtual charging station.

[0008] Optionally, establishing the preset charging node corresponding to each of the virtual charging stations includes: obtaining multiple preset charging time periods of the virtual charging station, wherein the preset charging time periods include: peak power consumption period, low power consumption period and stable power consumption period; setting the corresponding preset charging node for each of the preset charging time periods; and determining the charging time data of the preset charging node based on the preset charging time periods.

[0009] Optionally, establishing the preset charging node corresponding to each virtual charging station includes: determining the cluster corresponding to the virtual charging station, wherein the cluster includes at least one preset charging station; determining the virtual location data of the virtual charging station based on the geographic location data of at least one preset charging station in the cluster; and determining the charging space data of the preset charging node based on the virtual location data.

[0010] Optionally, establishing the preset charging node corresponding to each of the virtual charging stations includes: obtaining resource constraints for obtaining the virtual charging station, wherein the resource constraints include at least one of the following: upper and lower bound constraints on the preset resource data in each of the preset charging nodes, average value constraints on the preset resource data in multiple preset charging nodes, change constraint on the preset resource data in the same preset charging node, and difference constraint on the preset resource data between the preset charging nodes with the same charging time data and different charging space data; and determining multiple preset resource data of the preset charging node based on the resource constraints.

[0011] Optionally, before using the charging demand probability distribution model to analyze multiple preset charging nodes and determine the predicted charging data of each preset charging node, the method also includes: obtaining a first dependency model for representing the dependency relationship between the preset charging amount data and the preset resource data; obtaining a second dependency model for representing the dependency relationship between the preset charging amount data and the charging space data; obtaining a third dependency model for representing the dependency relationship between the preset charging amount data and the charging time data; determining the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, wherein the initial model includes: the first dependency model, the second dependency model and the third dependency model, and the initial weight parameters of the first dependency model, the second dependency model and the third dependency model.

[0012] Optionally, after determining the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model, and the third dependency model, the method further includes: analyzing the initial model using maximum likelihood estimation to determine an initial weight parameter of the first dependency model as a first weight parameter, determining an initial weight parameter of the second dependency model as a second weight parameter, and determining an initial weight parameter of the third dependency model as a third weight parameter;

[0013] The charging demand probability distribution model is determined based on the first dependency model and the first weight parameter, the second dependency model and the second weight parameter, and the third dependency model and the third weight parameter.

[0014] According to another aspect of an embodiment of the present invention, a device for processing electric vehicle charging data is provided, comprising: an acquisition module for acquiring a preset charging set, wherein the preset charging set comprises: preset charging nodes of a plurality of virtual charging stations, each of the preset charging nodes comprises: charging time data, charging space data and a plurality of preset resource data, the charging time data representing the charging period of the virtual charging station, the charging space data representing the geographical location of the virtual charging station, and the preset resource data representing the resource consumption corresponding to the unit charging amount; a first determination module for analyzing the plurality of preset charging nodes using a charging demand probability distribution model to determine a predicted value for each preset charging node; Charging data, wherein the charging demand probability distribution model is used to determine the influence of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, the predicted charging data represents the preset charging amount data corresponding to a plurality of the preset resource data in each of the preset charging nodes, and the distribution probability of each of the preset charging amount data, and the preset charging amount data represents the maximum charging amount expected to be consumed by the preset charging node; a second determination module is used to analyze the predicted charging data using a particle swarm algorithm, and determine the target resource data and the target charging amount data corresponding to the target resource data among the plurality of the preset resource data of each of the preset charging nodes.

[0015] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is further provided, characterized in that the non-volatile storage medium is used to store a program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the above-mentioned method for processing electric vehicle charging data.

[0016] According to another aspect of an embodiment of the present invention, an electronic device is provided, characterized in that it includes: a memory and a processor, the processor is used to run a program stored in the processor, wherein the program executes the above-mentioned method for processing electric vehicle charging data when running.

[0017] In an embodiment of the present invention, a preset charging set is obtained, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; a charging demand probability distribution model is used to analyze the multiple preset charging nodes to determine the predicted charging data of each preset charging node, wherein the charging demand probability distribution model is used to determine the influence of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, and to predict The measured charging data represents the preset charging capacity data corresponding to multiple preset resource data in each preset charging node, and the distribution probability of each preset charging capacity data, and the preset charging capacity data represents the maximum charging capacity expected to be consumed by the preset charging node; the predicted charging data is analyzed by using the particle swarm algorithm, and the target resource data and the target charging capacity data corresponding to the target resource data are determined from the multiple preset resource data of each preset charging node, thereby achieving the effect of determining the resource on the charging capacity based on time and space factors, thereby achieving the technical effect of improving the charging resource utilization rate based on time and space factors in virtual power station aggregation, and then solving the technical problem of low charging resource utilization rate in virtual power station aggregation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 is a flow chart of a method for processing electric vehicle charging data according to an embodiment of the present invention;

[0020] Figure 2 is a schematic diagram of a conditional random field model that only considers the spatial dependency of demands according to an embodiment of the present invention;

[0021] Figure 3 is a schematic diagram of a unified framework for spatiotemporal elasticity according to an embodiment of the present invention;

[0022] Figure 4 is a schematic diagram of price changes before and after electricity price optimization according to an embodiment of the present invention;

[0023] Figure 5 is a schematic diagram of a change in charging demand after electricity price optimization according to an embodiment of the present invention;

[0024] Figure 6 is a schematic diagram of price adjustment in various regions according to an embodiment of the present invention;

[0025] Figure 7 is a schematic diagram of charging capacity changes in various regions after price adjustment according to an embodiment of the present invention;

[0026] Figure 8 is a schematic diagram of a device for processing electric vehicle charging data according to an embodiment of the present invention;

[0027] Figure 9 It is a structural block diagram of a computer terminal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] According to an embodiment of the present invention, an embodiment of a method for processing electric vehicle charging data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 1 FIG. 1 is a flow chart of a method for processing electric vehicle charging data according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0032] Step S102: Obtaining a preset charging set, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data, and multiple preset resource data, the charging time data indicating the charging period of the virtual charging station, the charging space data indicating the geographical location of the virtual charging station, and the preset resource data indicating the resource consumption corresponding to a unit charge amount;

[0033] Step S104: Analyze multiple preset charging nodes using a charging demand probability distribution model to determine predicted charging data for each preset charging node, wherein the charging demand probability distribution model is used to determine the impact of preset resource data on preset charge capacity data based on the charging time data and the charging space data, the predicted charging data representing preset charge capacity data corresponding to multiple preset resource data in each preset charging node and the distribution probability of each preset charge capacity data, and the preset charge capacity data representing the maximum charge capacity expected to be consumed by the preset charging node;

[0034] Step S106 , using a particle swarm algorithm to analyze the predicted charging data, and determining target resource data and target charging capacity data corresponding to the target resource data from a plurality of preset resource data of each preset charging node.

[0035] In an embodiment of the present invention, a preset charging set is obtained, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; a charging demand probability distribution model is used to analyze the multiple preset charging nodes to determine the predicted charging data of each preset charging node, wherein the charging demand probability distribution model is used to determine the influence of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, and to predict The measured charging data represents the preset charging capacity data corresponding to multiple preset resource data in each preset charging node, and the distribution probability of each preset charging capacity data, and the preset charging capacity data represents the maximum charging capacity expected to be consumed by the preset charging node; the predicted charging data is analyzed by using the particle swarm algorithm, and the target resource data and the target charging capacity data corresponding to the target resource data are determined from the multiple preset resource data of each preset charging node, thereby achieving the effect of determining the resource on the charging capacity based on time and space factors, thereby achieving the technical effect of improving the charging resource utilization rate based on time and space factors in virtual power station aggregation, and then solving the technical problem of low charging resource utilization rate in virtual power station aggregation.

[0036] In the above step S102 , the preset resource data may represent electricity price.

[0037] In the above step S102 , the charging time data, charging space data, multiple preset resource data, and preset charging amount data in the preset charging node are charging data for charging the electric vehicle.

[0038] As an optional embodiment, obtaining a preset charging set includes: obtaining geographic location data of multiple preset charging stations; clustering the multiple preset charging stations based on the geographic location data to obtain multiple clusters; assigning a corresponding virtual charging station to each cluster; and establishing a preset charging node corresponding to each virtual charging station.

[0039] In the above-mentioned embodiment of the present invention, multiple preset charging stations can be clustered based on geographic location data, and corresponding virtual charging stations can be set for multiple preset charging stations with similar geographic location data. The analysis results of the virtual charging stations are used as the analysis results of the preset charging stations, and then preset charging nodes can be set for the virtual charging stations for analysis.

[0040] As an optional embodiment, establishing a preset charging node corresponding to each virtual charging station includes: obtaining multiple preset charging time periods of the virtual charging station, wherein the preset charging time periods include: peak power consumption period, low power consumption period and stable power consumption period; setting a corresponding preset charging node for each preset charging time period; and determining the charging time data of the preset charging node according to the preset charging time period.

[0041] Optionally, each virtual charging station may have a plurality of preset charging nodes, and the number of preset charging nodes of each virtual charging station may be the same as the number of preset charging periods.

[0042] In the above embodiment of the present invention, preset charging nodes are set for the virtual charging station according to the preset charging period, and charging time data is determined according to the preset charging period. It can be determined that each preset charging node has charging time data.

[0043] As an optional embodiment, establishing a preset charging node corresponding to each virtual charging station includes: determining a cluster corresponding to the virtual charging station, wherein the cluster includes at least one preset charging station; determining the virtual location data of the virtual charging station based on the geographic location data of at least one preset charging station in the cluster; and determining the charging space data of the preset charging node based on the virtual location data.

[0044] In the above embodiment of the present invention, since each virtual charging station represents multiple preset charging stations with similar geographical location data, the virtual location data of each virtual charging station can be determined based on the geographical location data of the preset charging stations in the cluster, and then the charging space data can be determined based on the virtual location data, and the charging time data of each preset charging node can be determined.

[0045] Optionally, in the case where the cluster includes a preset charging station, the geographical location data of the preset charging station is the virtual location data of the virtual charging station.

[0046] Optionally, when the cluster includes multiple preset charging stations, a cluster center and central position data of the cluster center can be determined based on the multiple preset charging stations, and the central position data is then determined as virtual position data of the virtual charging station.

[0047] Optionally, determining the central location data according to the plurality of preset charging stations includes: determining the central location data according to an average value of the geographical location data of the plurality of preset charging stations.

[0048] As an optional embodiment, establishing a preset charging node corresponding to each virtual charging station includes: obtaining resource constraints for the virtual charging station, wherein the resource constraints include at least one of the following: upper and lower bound constraints on the preset resource data in each preset charging node, average value constraints on the preset resource data in multiple preset charging nodes, change amount constraints on the preset resource data in the same preset charging node, and difference constraints on the preset resource data between preset charging nodes with the same charging time data and different charging space data; based on the resource constraints, determining multiple preset resource data of the preset charging node.

[0049] In the above-mentioned embodiment of the present invention, the multiple preset resource data of each preset charging node can be determined by at least one resource constraint condition, and then by analyzing the multiple preset resource data of the preset charging node, the optimal target resource data can be selected from the multiple preset resource data, thereby realizing the selection of the target resource data.

[0050] Optionally, in order to guide the pricing of charging service providers, it is necessary to maximize the profits of charging service providers. In addition to being constrained by the preset charging amount data, the preset resource data can also be constrained by setting resource constraints.

[0051] Optionally, the upper and lower bound constraints of the preset resource data in each preset charging node include: the upper and lower bound constraints of the price [ρ min ,ρ max ].

[0052] Optionally, the average value constraint of the preset resource data in the plurality of preset charging nodes includes: the average electricity cost of the user does not increase

[0053] Optionally, the change constraint of the preset resource data in the same preset charging node includes: the price change in a certain area and a certain period of time does not exceed λ times the original average price,

[0054] Optionally, the difference constraints of preset resource data between preset charging nodes with the same charging time data and different charging space data include: price difference at different locations in the same period

[0055] In the above step S104, since each preset charging node has multiple preset resource data, the predicted charging data of each preset charging node may include multiple preset charging amount data, and each preset charging amount data represents the prediction result obtained by the preset charging node with the corresponding preset resource data as the prediction condition.

[0056] In the above step S104, the charging demand probability distribution model may be a conditional random field model, which analyzes the impact of the charging time data and the charging space data on the preset charging amount data, as well as the impact of the preset resource data on the preset charging amount data.

[0057] Figure 2 is a schematic diagram of a conditional random field model that only considers the spatial dependency of requirements according to an embodiment of the present invention, such as Figure 2 As shown, the dotted line represents the correlation between local price (such as preset resource data) and demand (such as preset charging amount data), while the solid line represents the dependence between demand (such as preset charging amount data) and space (such as charging space data).

[0058] As an optional embodiment, before using the charging demand probability distribution model to analyze multiple preset charging nodes and determine the predicted charging data of each preset charging node, the method also includes: obtaining a first dependency model for representing the dependency relationship between preset charging amount data and preset resource data; obtaining a second dependency model for representing the dependency relationship between preset charging amount data and charging space data; obtaining a third dependency model for representing the dependency relationship between preset charging amount data and charging time data; and determining an initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, wherein the initial model includes: a first dependency model, a second dependency model and a third dependency model, and initial weight parameters of the first dependency model, the second dependency model and the third dependency model.

[0059] In the above-mentioned embodiment of the present invention, based on the first dependency model, the second dependency model and the third dependency model, a charging demand probability distribution model can be constructed to represent the influence of preset resource data on preset charging quantity data based on charging time data and charging space data. Then, based on the charging demand probability distribution model, the target charging quantity data corresponding to the optimal target resource data can be selected from the combination of multiple preset resource data and preset charging quantity data according to demand.

[0060] As an optional example, consider a “virtual charging station” aggregated from K regions, and use the framework of conditional random fields to represent the charging demand. Model the time and space transfer elasticity of Represents the total charging demand (such as preset charging capacity data) during peak hours (such as peak electricity consumption hours), normal hours (such as stable electricity consumption hours), and valley hours (such as low electricity consumption hours) in the i-th region, and records the set of time periods. Similarly Indicates the charging price during the peak, flat and valley periods in the i-th region (such as preset resource data). Under the conditions of time and space dependency, based on a given price (such as preset resource data) Estimated charging requirements (such as preset charging capacity data) The probability distribution of .

[0061] Optionally, a conditional random field framework is used to Model the time and space transfer elasticity. Introduce the conditional random field G = (V, E), the vertex set It represents the peak-valley-flat three-layer “virtual charging station” aggregated from K regions, and the edge sets are connected to the space E p , and the temporal connection E t , that is, E = E p +E t . The edge of space It shows the spatial correlation of charging demand (such as the second dependency model) and the temporal edge. Represents the temporal correlation between total demand in different periods in the same region (such as the third dependency model).

[0062] In the unified spatiotemporal elastic conditional random field model, the total demand for charging in each region is an implicit random variable, price is a random variable as an explicit variable. is the vector ρ, similarly, let For vector d, the conditional random field can calculate the conditional probability distribution of P(d|ρ). The conditional independence property in the conditional random field can be expressed as: when the price ρ is known, unconnected nodes are conditionally independent.

[0063] Figure 3 is a schematic diagram of a unified framework of spatiotemporal elasticity according to an embodiment of the present invention, such as Figure 3 As shown, the solid line represents the spatial correlation of demand, and the dotted line represents the temporal correlation of demand. There are three characteristic functions here, namely the local demand price relationship (such as the first dependency model) ψ i (d i,ρ i ), i∈V, the spatial dependency of demand (such as the second dependency model) Time dependencies of requirements (such as the second dependency model) Three parameters are introduced into the three dependency models: i , They represent the first dependency model and the first weight parameter, the second dependency model and the second weight parameter, and the third dependency model and the third weight parameter respectively, and are uniformly written into the parameter vector ω.

[0064] As an optional example, when the price (i.e., the preset resource data) is known, the charging demand probability distribution model is:

[0065]

[0066]

[0067] Among them, Z(ρ) is the partition function, which is used to normalize the probability.

[0068] As an optional embodiment, after determining the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, the method also includes: analyzing the initial model using maximum likelihood estimation, determining the initial weight parameter of the first dependency model as the first weight parameter, determining the initial weight parameter of the second dependency model as the second weight parameter, and determining the initial weight parameter of the third dependency model as the third weight parameter; determining the charging demand probability distribution model based on the first dependency model and the first weight parameter, the second dependency model and the second weight parameter, and the third dependency model and the third weight parameter.

[0069] In the above-mentioned embodiment of the present invention, the first weight parameter, the second dependency model and the second weight parameter in the initial model can be obtained by using the maximum likelihood estimation method, and then the charging demand probability distribution model is determined based on the determined first weight parameter, the second dependency model and the second weight parameter, in combination with the first dependency model, the second dependency model and the third dependency model, to achieve the determination of the charging demand probability distribution model.

[0070] In the above step S106, the particle swarm algorithm is used to solve the corresponding relationship between charging price (such as preset resource data) and demand (such as preset charging amount data) based on the charging demand probability distribution model.

[0071] It's important to note that the Particle Swarm Optimization (PSO) algorithm is a randomized search algorithm proposed by Kennedy and James in 2002. The algorithm mimics the foraging behavior of a flock of birds, characterizing both group and individual behavior. Each particle has an initial velocity and position. During iterations, the position is updated based on the velocity, which changes with the global and individual extreme points.

[0072] Alternatively, the particle swarm optimization algorithm can be expressed as:

[0073] v i =w·v i +c1·rand()·(pbest i -present i )+c2·rand()·(gbest-present i )

[0074] present i =present i +v i

[0075] Among them, v i represents the speed of the i-th particle, w represents the inertia coefficient, c1 and c2 are the learning rates of the individual and the group respectively, and pbest i is the best position for an individual, gbest is the best position for a group, present i is the current position of particle i.

[0076] Alternatively, based on the charging demand probability distribution model, the goal of maximizing the profit of the charging service provider can be achieved by using a particle swarm algorithm. The goal of maximizing the profit of the charging service provider can be expressed by the following formula:

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083] in, is the price of the ith region in period t, c t represents the electricity purchase cost during period t, The factor representing the normalized demand for the ith region in period t, represents the expected demand in the ith region during period t under the condition of parameter ω and price ρ. [ρ min ,ρ max ] indicates setting the upper and lower limits of the price. represents the average charging price in the dataset, ρ represents the average charging price in the ith region during the t period in the dataset. Max_diff It is the upper limit of the price difference between different locations during the same period.

[0084] Optionally, the goal of the solution It is the expectation of charging demand obtained by the established conditional random field model under the conditions of parameters ω and price ρ.

[0085] It should be noted that because the charging occupancy rate itself is low, the device rated power multiplied by the number of hours is not used as the normalization factor for normalization, but the maximum charging power is used as the normalization factor. The peak, flat and valley periods can be used express.

[0086] Figure 4 FIG. 1 is a schematic diagram of price changes before and after electricity price optimization according to an embodiment of the present invention. Figure 4 As shown, the changes in the prices (ie, preset resource data) of each virtual charging station before and after the electricity price optimization can be represented.

[0087] Figure 5 FIG. 1 is a schematic diagram of a change in charging demand after electricity price optimization according to an embodiment of the present invention. Figure 5 As shown, the changes in the charging demand (ie, the preset charging amount data) of each virtual charging station before and after the electricity price optimization can be represented.

[0088] Figure 6 FIG. 1 is a schematic diagram of price adjustment in various regions according to an embodiment of the present invention. Figure 6 As shown, it can represent the changes in prices (ie, preset resource data) in the areas where each virtual charging station is located before and after electricity price optimization.

[0089] Figure 7 FIG. 1 is a schematic diagram of charging capacity changes in various regions after price adjustment according to an embodiment of the present invention. Figure 7 As shown, the changes in charging demand (ie, preset charging amount data) in the area where each virtual charging station is located before and after electricity price optimization can be shown.

[0090] Optionally, the charging price change model obtained by the dynamic time-of-use pricing method based on spatiotemporal transfer elasticity is compared with the service provider's existing strategy to provide a reference for the service provider's operation strategy optimization.

[0091] The above-mentioned embodiment of the present application generates a conditional random field that takes into account the spatiotemporal elasticity through the spatiotemporal distribution of virtual power stations, and obtains a charging demand probability distribution model of the charging demand, thereby developing a dynamic time-sharing pricing method to achieve the goal of maximizing the service provider's profit, and providing an effective reference for the service provider's operating strategy.

[0092] This application effectively incorporates the relevant parameters of the virtual power plant into the dynamic time-of-use pricing method by adopting the time-space transfer elasticity algorithm, effectively improving the sophistication of the service provider's operating strategy.

[0093] This application uses a particle swarm algorithm to optimize dynamic time-of-use pricing, which can obtain the corresponding relationship between charging prices and demand changes, effectively improving the feasibility of the method.

[0094] According to an embodiment of the present invention, an embodiment of a device for processing electric vehicle charging data is also provided. It should be noted that the device for processing electric vehicle charging data can be used to execute the method for processing electric vehicle charging data in an embodiment of the present invention, and the method for processing electric vehicle charging data in an embodiment of the present invention can be executed in the device for processing electric vehicle charging data.

[0095] Figure 8 FIG. 1 is a schematic diagram of a device for processing electric vehicle charging data according to an embodiment of the present invention. Figure 8 As shown, the device may include: an acquisition module 82, configured to acquire a preset charging set, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data, and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; a first determination module 84, configured to analyze the multiple preset charging nodes using a charging demand probability distribution model to determine predicted charging data for each preset charging node, wherein the charging demand probability distribution model is configured to determine the influence of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, the predicted charging data represents the preset charging amount data corresponding to the multiple preset resource data in each preset charging node, and the distribution probability of each preset charging amount data, and the preset charging amount data represents the maximum charging amount expected to be consumed by the preset charging node; a second determination module 86, configured to analyze the predicted charging data using a particle swarm algorithm, and determine target resource data and target charging amount data corresponding to the target resource data from the multiple preset resource data of each preset charging node.

[0096] It should be noted that the acquisition module 82 in this embodiment can be used to execute step S102 in the embodiment of the present application, the first determination module 84 in this embodiment can be used to execute step S104 in the embodiment of the present application, and the second determination module 86 in this embodiment can be used to execute step S106 in the embodiment of the present application. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments.

[0097] In an embodiment of the present invention, a preset charging set is obtained, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; a charging demand probability distribution model is used to analyze the multiple preset charging nodes to determine the predicted charging data of each preset charging node, wherein the charging demand probability distribution model is used to determine the influence of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, and to predict The measured charging data represents the preset charging capacity data corresponding to multiple preset resource data in each preset charging node, and the distribution probability of each preset charging capacity data, and the preset charging capacity data represents the maximum charging capacity expected to be consumed by the preset charging node; the predicted charging data is analyzed by using the particle swarm algorithm, and the target resource data and the target charging capacity data corresponding to the target resource data are determined from the multiple preset resource data of each preset charging node, thereby achieving the effect of determining the resource on the charging capacity based on time and space factors, thereby achieving the technical effect of improving the charging resource utilization rate based on time and space factors in virtual power station aggregation, and then solving the technical problem of low charging resource utilization rate in virtual power station aggregation.

[0098] As an optional embodiment, the acquisition module includes: an acquisition unit, used to obtain the geographic location data of multiple preset charging stations; a clustering unit, used to cluster the multiple preset charging stations based on the geographic location data to obtain multiple cluster clusters; an allocation unit, used to allocate a corresponding virtual charging station to each cluster cluster; and an establishment unit, used to establish a preset charging node corresponding to each virtual charging station.

[0099] As an optional embodiment, the establishment unit includes: a first acquisition subunit, used to obtain multiple preset charging time periods of the virtual charging station, wherein the preset charging time periods include: peak power consumption period, low power consumption period and stable power consumption period; a setting subunit, used to set a corresponding preset charging node for each preset charging time period; a first determination subunit, used to determine the charging time data of the preset charging node according to the preset charging time period.

[0100] As an optional embodiment, the establishment unit includes: a second determination subunit, used to determine the cluster corresponding to the virtual charging station, wherein the cluster includes at least one preset charging station; a third determination subunit, used to determine the virtual location data of the virtual charging station based on the geographic location data of at least one preset charging station in the cluster; and a fourth determination subunit, used to determine the charging space data of the preset charging node based on the virtual location data.

[0101] As an optional embodiment, the establishment unit includes: a second determination subunit, used to obtain resource constraints for obtaining the virtual charging station, wherein the resource constraints include at least one of the following: upper and lower bound constraints on the preset resource data in each preset charging node, average value constraints on the preset resource data in multiple preset charging nodes, change constraints on the preset resource data in the same preset charging node, and difference constraints on the preset resource data between preset charging nodes with the same charging time data and different charging space data; a fifth determination subunit, used to determine multiple preset resource data of the preset charging node based on the resource constraints.

[0102] As an optional embodiment, the device also includes: a first acquisition submodule, which is used to analyze multiple preset charging nodes using the charging demand probability distribution model to obtain a first dependency model for representing the dependency relationship between the preset charging amount data and the preset resource data before determining the predicted charging data of each preset charging node; a second acquisition submodule, which is used to obtain a second dependency model for representing the dependency relationship between the preset charging amount data and the charging space data; a third acquisition submodule, which is used to obtain a third dependency model for representing the dependency relationship between the preset charging amount data and the charging time data; a first determination submodule, which is used to determine the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, wherein the initial model includes: the first dependency model, the second dependency model and the third dependency model, and the initial weight parameters of the first dependency model, the second dependency model and the third dependency model.

[0103] As an optional embodiment, the device also includes: a second determination submodule, which is used to analyze the initial model by maximum likelihood estimation after determining the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, and determine the initial weight parameter of the first dependency model as the first weight parameter, the initial weight parameter of the second dependency model as the second weight parameter, and the initial weight parameter of the third dependency model as the third weight parameter; a third determination submodule, which is used to determine the charging demand probability distribution model based on the first dependency model and the first weight parameter, the second dependency model and the second weight parameter, and the third dependency model and the third weight parameter.

[0104] The embodiment of the present invention can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal can also be replaced by a terminal device such as a mobile terminal.

[0105] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of a computer network.

[0106] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the method for processing electric vehicle charging data: obtaining a preset charging set, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; using the charging demand probability distribution model to analyze the multiple preset charging nodes, and determine the predicted charging data of each preset charging node, wherein the charging demand probability distribution model is used to determine the impact of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, the predicted charging data represents the preset charging amount data corresponding to the multiple preset resource data in each preset charging node, and the distribution probability of each preset charging amount data, and the preset charging amount data represents the maximum charging amount expected to be consumed by the preset charging node; using the particle swarm algorithm to analyze the predicted charging data, and determine the target resource data and the target charging amount data corresponding to the target resource data from the multiple preset resource data of each preset charging node. Optionally, the processor may also execute the program code of the following steps: obtaining geographic location data of a plurality of preset charging stations; clustering the plurality of preset charging stations according to the geographic location data to obtain a plurality of clusters; assigning a corresponding virtual charging station to each cluster; and establishing a preset charging node corresponding to each virtual charging station.

[0107] Optionally, Figure 9 1 is a block diagram of a computer terminal according to an embodiment of the present invention. Figure 9 As shown, the computer terminal 90 may include: one or more (only one is shown in the figure) processors 92 and a memory 94.

[0108] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for processing electric vehicle charging data in the embodiments of the present invention. The processor executes the software programs and modules stored in the memory to execute various functional applications and process electric vehicle charging data, thereby implementing the above-mentioned method for processing electric vehicle charging data. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the terminal 90 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtaining a preset charging set, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; using the charging demand probability distribution model to analyze the multiple preset charging nodes and determine the predicted charging data of each preset charging node, wherein the charging demand probability distribution model is used to determine the impact of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, the predicted charging data represents the preset charging amount data corresponding to the multiple preset resource data in each preset charging node, and the distribution probability of each preset charging amount data, and the preset charging amount data represents the maximum charging amount expected to be consumed by the preset charging node; using the particle swarm algorithm to analyze the predicted charging data, and determine the target resource data and the target charging amount data corresponding to the target resource data from the multiple preset resource data of each preset charging node. Optionally, the processor may also execute the program code of the following steps: obtaining geographic location data of a plurality of preset charging stations; clustering the plurality of preset charging stations according to the geographic location data to obtain a plurality of clusters; assigning a corresponding virtual charging station to each cluster; and establishing a preset charging node corresponding to each virtual charging station.

[0110] Optionally, the processor may also execute the program code of the following steps: obtaining multiple preset charging time periods of the virtual charging station, wherein the preset charging time periods include: peak power consumption period, valley power consumption period and stable power consumption period; setting a corresponding preset charging node for each preset charging time period; and determining the charging time data of the preset charging node according to the preset charging time period.

[0111] Optionally, the processor may also execute the program code of the following steps: determining a cluster corresponding to the virtual charging station, wherein the cluster includes at least one preset charging station; determining the virtual location data of the virtual charging station based on the geographic location data of at least one preset charging station in the cluster; and determining the charging space data of the preset charging node based on the virtual location data.

[0112] Optionally, the processor may also execute the program code of the following steps: obtaining resource constraints for obtaining a virtual charging station, wherein the resource constraints include at least one of the following: upper and lower bound constraints on the preset resource data in each preset charging node, average value constraints on the preset resource data in multiple preset charging nodes, change constraints on the preset resource data in the same preset charging node, and difference constraints on the preset resource data between preset charging nodes with the same charging time data and different charging space data; and determining multiple preset resource data of the preset charging node based on the resource constraints.

[0113] Optionally, the processor may also execute the program code of the following steps: before using the charging demand probability distribution model to analyze multiple preset charging nodes and determine the predicted charging data of each preset charging node, obtain a first dependency model for representing the dependency relationship between the preset charging amount data and the preset resource data; obtain a second dependency model for representing the dependency relationship between the preset charging amount data and the charging space data; obtain a third dependency model for representing the dependency relationship between the preset charging amount data and the charging time data; determine the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, wherein the initial model includes: the first dependency model, the second dependency model and the third dependency model, and the initial weight parameters of the first dependency model, the second dependency model and the third dependency model.

[0114] Optionally, the processor may also execute the program code of the following steps: after determining the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model, and the third dependency model, analyzing the initial model using maximum likelihood estimation to determine the initial weight parameter of the first dependency model as the first weight parameter, the initial weight parameter of the second dependency model as the second weight parameter, and the initial weight parameter of the third dependency model as the third weight parameter; determining the charging demand probability distribution model based on the first dependency model and the first weight parameter, the second dependency model and the second weight parameter, and the third dependency model and the third weight parameter.

[0115] According to an embodiment of the present invention, a solution for processing electric vehicle charging data is provided. By obtaining a preset charging set, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; using a charging demand probability distribution model to analyze the multiple preset charging nodes, determine the predicted charging data of each preset charging node, wherein the charging demand probability distribution model is used to determine the influence of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, and predict the charging demand. The data represents preset charging capacity data corresponding to multiple preset resource data in each preset charging node, and the distribution probability of each preset charging capacity data, and the preset charging capacity data represents the maximum charging capacity expected to be consumed by the preset charging node; the particle swarm algorithm is used to analyze the predicted charging data, and the target resource data and the target charging capacity data corresponding to the target resource data are determined from the multiple preset resource data of each preset charging node, thereby achieving the effect of determining the resource on the charging capacity based on time and space factors, thereby achieving the technical effect of improving the charging resource utilization rate based on time and space factors in virtual power station aggregation, and then solving the technical problem of low charging resource utilization rate in virtual power station aggregation.

[0116] It can be understood by those skilled in the art that Figure 9 The structure shown is for illustration only, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, a mobile Internet device (MID), a PAD, or other terminal devices. Figure 9 It does not limit the structure of the above electronic device. For example, the computer terminal 90 may also include Figure 8 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 9 Different configurations shown.

[0117] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a non-volatile medium. The non-volatile storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0118] The embodiment of the present invention further provides a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store the program code executed by the method for processing electric vehicle charging data provided in the above embodiment.

[0119] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0120] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: obtaining a preset charging set, wherein the preset charging set includes: preset charging nodes of multiple virtual charging stations, each preset charging node includes: charging time data, charging space data and multiple preset resource data, the charging time data represents the charging period of the virtual charging station, the charging space data represents the geographical location of the virtual charging station, and the preset resource data represents the resource consumption corresponding to the unit charging amount; using a charging demand probability distribution model to analyze the multiple preset charging nodes and determine the predicted charging data of each preset charging node, wherein the charging demand probability distribution model is used to determine the impact of the preset resource data on the preset charging amount data based on the charging time data and the charging space data, the predicted charging data represents the preset charging amount data corresponding to the multiple preset resource data in each preset charging node, and the distribution probability of each preset charging amount data, and the preset charging amount data represents the maximum charging amount expected to be consumed by the preset charging node; using a particle swarm algorithm to analyze the predicted charging data and determine the target resource data and the target charging amount data corresponding to the target resource data from the multiple preset resource data of each preset charging node.

[0121] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: obtaining geographic location data of multiple preset charging stations; clustering the multiple preset charging stations based on the geographic location data to obtain multiple clusters; assigning a corresponding virtual charging station to each cluster; and establishing a preset charging node corresponding to each virtual charging station.

[0122] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: obtaining multiple preset charging time periods of the virtual charging station, wherein the preset charging time periods include: peak power consumption period, low power consumption period and stable power consumption period; setting a corresponding preset charging node for each preset charging time period; and determining the charging time data of the preset charging node according to the preset charging time period.

[0123] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining a cluster corresponding to the virtual charging station, wherein the cluster includes at least one preset charging station; determining virtual location data of the virtual charging station based on geographic location data of at least one preset charging station in the cluster; and determining charging space data of the preset charging node based on the virtual location data.

[0124] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: obtaining resource constraints for the virtual charging station, wherein the resource constraints include at least one of the following: upper and lower bound constraints on the preset resource data in each preset charging node, average value constraints on the preset resource data in multiple preset charging nodes, change amount constraints on the preset resource data in the same preset charging node, and difference constraints on the preset resource data between preset charging nodes with the same charging time data and different charging space data; based on the resource constraints, determining multiple preset resource data of the preset charging node.

[0125] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: before using the charging demand probability distribution model to analyze multiple preset charging nodes and determine the predicted charging data of each preset charging node, obtain a first dependency model for representing the dependency relationship between the preset charging amount data and the preset resource data; obtain a second dependency model for representing the dependency relationship between the preset charging amount data and the charging space data; obtain a third dependency model for representing the dependency relationship between the preset charging amount data and the charging time data; determine the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, wherein the initial model includes: the first dependency model, the second dependency model and the third dependency model, and the initial weight parameters of the first dependency model, the second dependency model and the third dependency model.

[0126] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: after determining the initial model of the charging demand probability distribution model based on the first dependency model, the second dependency model and the third dependency model, analyzing the initial model using maximum likelihood estimation to determine the initial weight parameter of the first dependency model as the first weight parameter, determining the initial weight parameter of the second dependency model as the second weight parameter, and determining the initial weight parameter of the third dependency model as the third weight parameter; determining the charging demand probability distribution model based on the first dependency model and the first weight parameter, the second dependency model and the second weight parameter, and the third dependency model and the third weight parameter.

[0127] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0128] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0130] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0131] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0132] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a non-volatile storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program code.

[0133] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for processing electric vehicle charging data, characterized in that: include: Obtaining a preset charging set, wherein the preset charging set includes: preset charging nodes of a plurality of virtual charging stations, each of the preset charging nodes including: charging time data, charging space data, and a plurality of preset resource data, wherein the charging time data indicates a charging period of the virtual charging station, the charging space data indicates a geographical location of the virtual charging station, and the preset resource data indicates a resource consumption corresponding to a unit charge amount; Analyzing the plurality of preset charging nodes using a charging demand probability distribution model to determine predicted charging data for each of the preset charging nodes, wherein the charging demand probability distribution model is used to determine an impact of the preset resource data on preset charge capacity data based on the charging time data and the charging space data, the predicted charging data representing the preset charge capacity data corresponding to the plurality of preset resource data in each of the preset charging nodes and a distribution probability of each of the preset charge capacity data, the preset charge capacity data representing the maximum charge capacity expected to be consumed by the preset charging node; Analyzing the predicted charging data using a particle swarm algorithm, determining target resource data and target charging capacity data corresponding to the target resource data from the plurality of preset resource data of each preset charging node; The step of obtaining the preset charging set includes: Obtaining geographic location data of multiple preset charging stations; Clustering the plurality of preset charging stations according to the geographic location data to obtain a plurality of clusters; Allocating a corresponding virtual charging station to each of the clusters; Establishing the preset charging node corresponding to each virtual charging station; Wherein, establishing the preset charging node corresponding to each virtual charging station includes: Acquire multiple preset charging time periods of the virtual charging station, wherein the preset charging time periods include: a peak power consumption period, a low power consumption period, and a stable power consumption period; Setting the corresponding preset charging node for each preset charging period; According to the preset charging period, charging time data of the preset charging node is determined.

2. The method according to claim 1, characterized in that Establishing the preset charging node corresponding to each virtual charging station includes: Determining the cluster corresponding to the virtual charging station, wherein the cluster includes at least one of the preset charging stations; Determining virtual location data of the virtual charging station based on geographic location data of at least one of the preset charging stations in the cluster; The charging space data of the preset charging node is determined according to the virtual location data.

3. The method according to claim 1, characterized in that Establishing the preset charging node corresponding to each virtual charging station includes: Obtaining resource constraints for the virtual charging station, wherein the resource constraints include at least one of the following: upper and lower bound constraints on the preset resource data in each preset charging node, an average value constraint on the preset resource data in multiple preset charging nodes, a change constraint on the preset resource data in the same preset charging node, and a difference constraint on the preset resource data between preset charging nodes having the same charging time data but different charging space data; A plurality of preset resource data of the preset charging node is determined according to the resource constraint condition.

4. The method according to claim 1, wherein Before analyzing the plurality of preset charging nodes using the charging demand probability distribution model to determine predicted charging data for each of the preset charging nodes, the method further includes: Acquire a first dependency model for representing a dependency relationship between the preset charge capacity data and the preset resource data; obtaining a second dependency model for representing a dependency relationship between the preset charge amount data and the charging space data; acquiring a third dependency model for representing a dependency relationship between the preset charge amount data and the charging time data; An initial model of the charging demand probability distribution model is determined based on the first dependency model, the second dependency model, and the third dependency model, wherein the initial model includes: the first dependency model, the second dependency model, and the third dependency model, as well as initial weight parameters of the first dependency model, the second dependency model, and the third dependency model.

5. The method according to claim 4, characterized in that After determining an initial model of the charging demand probability distribution model according to the first dependency model, the second dependency model, and the third dependency model, the method further includes: Analyzing the initial model using maximum likelihood estimation, determining the initial weight parameter of the first dependent model as a first weight parameter, determining the initial weight parameter of the second dependent model as a second weight parameter, and determining the initial weight parameter of the third dependent model as a third weight parameter; The charging demand probability distribution model is determined based on the first dependency model and the first weight parameter, the second dependency model and the second weight parameter, and the third dependency model and the third weight parameter.

6. A device for processing electric vehicle charging data, characterized in that: include: an acquisition module, configured to acquire a preset charging set, wherein the preset charging set includes: preset charging nodes of a plurality of virtual charging stations, each of the preset charging nodes including: charging time data, charging space data, and a plurality of preset resource data, wherein the charging time data indicates a charging period of the virtual charging station, the charging space data indicates a geographical location of the virtual charging station, and the preset resource data indicates a resource consumption corresponding to a unit charge amount; a first determination module, configured to analyze the plurality of preset charging nodes using a charging demand probability distribution model to determine predicted charging data for each of the preset charging nodes, wherein the charging demand probability distribution model is configured to determine, based on the charging time data and the charging space data, an impact of the preset resource data on preset charge capacity data, the predicted charging data representing the preset charge capacity data corresponding to the plurality of preset resource data in each of the preset charging nodes, and a distribution probability of each of the preset charge capacity data, the preset charge capacity data representing a maximum charge capacity expected to be consumed by the preset charging node; a second determining module, configured to analyze the predicted charging data using a particle swarm algorithm, and determine target resource data and target charging capacity data corresponding to the target resource data from the plurality of preset resource data of each preset charging node; Wherein, the acquisition module includes: an acquisition unit, configured to acquire geographic location data of a plurality of preset charging stations; a clustering unit, configured to cluster the plurality of preset charging stations according to the geographic location data to obtain a plurality of clusters; an allocating unit, configured to allocate a corresponding virtual charging station to each of the clusters; An establishing unit, configured to establish the preset charging node corresponding to each of the virtual charging stations; Wherein, the establishing unit includes: A first acquisition subunit is configured to acquire a plurality of preset charging time periods of the virtual charging station, wherein the preset charging time periods include: a peak power consumption period, a valley power consumption period, and a stable power consumption period; A setting subunit, configured to set a corresponding preset charging node for each preset charging period; The first determining subunit is configured to determine the charging time data of the preset charging node according to the preset charging period.

7. A non-volatile storage medium, characterized in that: The non-volatile storage medium is used to store a program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the electric vehicle charging data processing method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the processor, wherein the program executes the method for processing electric vehicle charging data as described in any one of claims 1 to 5 when running.

Images