Charging pile operation management method, system and platform based on cloud platform

Abstract

The invention discloses a charging pile operation management method, system and platform based on a cloud platform, and relates to the field of charging pile management, and the method comprises the steps: generating a user portrait of each charging station; according to the electric energy redundancy of the target area and the user portraits of the charging stations, electric energy consumption of the charging stations at future time nodes is predicted, and whether the charging stations are connected to a power grid energy storage device or not is judged; for one charging station, if the charging station is connected to the power grid energy storage device, determining an allocation strategy between a target charging pile in the charging station and the power grid energy storage device according to the equipment information; generating a power demand prediction result of the target charging pile at the future time node according to the user portrait of each charging station, the electric energy redundancy of the target region and the distribution strategy; and obtaining a regulation and control strategy of the target charging pile in the charging station at the future time node according to the power demand prediction result. The charging experience feeling of a user can be effectively improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of charging pile management, and in particular to a charging pile operation management method, system and platform based on a cloud platform. Background Art

[0002] In recent years, with the rapid development of the new energy industry, the construction of new energy charging piles has also increased day by day. Although the number of charging piles is growing, from the current situation, the user charging experience has not improved accordingly. The utilization rate of existing charging piles is very low, and there is a huge waste of resources. For example, some charging piles have too much demand for use, and the construction of charging piles is insufficient, resulting in the phenomenon of charging queues. In some places, charging piles are not used for a long time, which not only affects the user's charging experience, but also causes a waste of resources.

[0003] Therefore, there is an urgent need for a charging pile operation management method, system and platform based on a cloud platform to predict the power consumption of charging piles and ensure the user's charging experience. Summary of the invention

[0004] The embodiments of the present application provide a charging pile operation management method, system and platform based on a cloud platform, which are used to enhance the user's charging experience.

[0005] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions: In a first aspect, a charging pile operation management method based on a cloud platform is characterized by comprising: Acquiring a power redundancy amount of a target area, wherein the target area includes at least one sub-area, and each sub-area includes at least one charging station; Obtaining historical charging information and station location of each charging station in the target area within a preset time period; Combining the historical charging information and the station location, generating a user profile for each charging station; According to the power redundancy of the target area and the user profile of the charging station, the power consumption of the charging station at a future time node is predicted, and according to the power consumption, whether the charging station is connected to the grid energy storage device is determined; For one of the charging sites, if the charging site is connected to a grid energy storage device, determine a target charging pile in the charging site, obtain device information of the target charging pile, and determine an allocation strategy between the target charging pile in the charging site and the grid energy storage device according to the device information; Generate a power demand forecast result of the target charging pile at a future time node according to the user profile of each charging station, the power redundancy of the target area and the allocation strategy; According to the power demand forecast result, a control strategy for the target charging pile in the charging station at a future time node is obtained.

[0006] In a possible implementation of the first aspect, combining the historical charging information and the station location to generate a user portrait of each charging station includes: Constructing a homogeneous graph of the charging stations according to the historical charging information and the station locations, wherein the homogeneous graph includes nodes and edges; Inputting the homogeneous graph into a pre-trained graph neural network model, and outputting a node vector of each charging station; A user portrait of each charging site is generated through the node vector, wherein the node vector corresponds to the user portrait one-to-one, and the user portrait of each charging site includes the charging type and charging habits of the vehicles in each charging site.

[0007] In a possible implementation manner of the first aspect, a node of the homogeneous graph is the historical charging information of each of the charging sites, and an edge of the homogeneous graph is a distance between two of the charging sites.

[0008] In a possible implementation of the first aspect, predicting the power consumption of the charging site at a future time node according to the power redundancy of the target area and the user profile of the charging site, and determining whether the charging site is connected to a grid energy storage device according to the power consumption, includes: Predicting the power consumption of each charging station at a future time node through the user portrait of each charging station, and obtaining the power data peak of each charging station according to the power consumption; Acquire the dynamic data of power usage in the target area, and determine the power regulation data of each charging station according to the peak value of the power data of each charging station and the dynamic data of power usage in the target area; If the power regulation data of each of the charging sites is greater than the power redundancy of the target area, it is determined that the charging site is connected to the power grid energy storage device.

[0009] In a possible implementation of the first aspect, determining the power regulation data of each charging site according to the power data peak of each charging site and the power change dynamic data of the target area includes: Determine the dynamic data of electric energy change in the target area within a preset time interval where the peak value of electric energy data of each charging station is located as the first dynamic data; The area where the first dynamic data is smaller than the average of the dynamic data of electric energy change in the target area is regarded as a low-energy consumption area; Respectively obtaining the electric energy redundancy of the low-energy consumption area in the electric energy data peak time period of each charging station; The redundant power in the low-power consumption area is respectively regulated to each of the charging sites, and the power regulation data of each of the charging sites is determined.

[0010] In a possible implementation of the first aspect, predicting the power consumption of each charging station at a future time node by using the user profile of each charging station includes: Obtaining the power consumption of each charging station through the user portrait of each charging station; The power consumption of each charging station is input into the pre-trained model to predict the power consumption of each charging station at a future time node.

[0011] In a possible implementation manner of the first aspect, determining, according to the device information, an allocation strategy between a target charging pile in the charging site and the grid energy storage device includes: In response to a user's selection instruction for a target charging pile in the charging station, obtaining a location of the target charging pile, and identifying a grid energy storage device that is closest to the location of the target charging pile as a first energy storage device; Acquiring information of the first energy storage device; The information of the first energy storage device is compared with the information of the target charging pile to determine an allocation strategy between the target charging pile in the charging station and the grid energy storage device.

[0012] In a possible implementation of the first aspect, the information of the first energy storage device and the information of the charging pile include power regulation data, location information of the power grid energy storage device and the charging pile, and fault information of the power grid energy storage device, and the comparing the information of the first energy storage device with the information of the target charging pile to determine an allocation strategy between the target charging pile in the charging station and the power grid energy storage device includes: Acquire dynamic power change data of the target charging pile, and determine first control data of the target charging pile according to the dynamic power change data of the target charging pile; Comparing the first control data of the target charging pile with the electric energy redundancy of the first energy storage device, and if the electric energy redundancy is greater than the first control data, determining a first matching degree between the target charging pile and the first energy storage device; Comparing the geographical location information of the target charging pile with the geographical location information of the first energy storage device, and determining a second matching degree between the target charging pile and the first energy storage device if the geographical location of the target charging pile and the geographical location of the first energy storage device are less than a preset distance; Determining whether the grid energy storage device connected to the target charging pile is faulty; If the grid energy storage device connected to the target charging pile is not faulty, obtaining the power output state of the grid energy storage device, and if the power output state of the grid energy storage device is a stable output state, determining a third matching degree between the target charging pile and the first energy storage device; If the first matching degree, the second matching degree and the third matching degree all meet the corresponding preset standards, an allocation strategy between the target charging pile in the charging site and the grid energy storage device is determined.

[0013] In a second aspect, the present application provides a charging pile operation management platform, including: An electric energy redundancy acquisition module is used to acquire electric energy redundancy in a target area, wherein the target area includes at least one sub-area, and each sub-area includes at least one charging station; A historical charging information and station location acquisition module, which acquires the historical charging information and station location of each charging station in the target area within a preset time period; A user portrait generation module, combining the historical charging information and the station location to generate a user portrait for each charging station; A grid energy storage device access module predicts the energy consumption of the charging station at a future time node based on the energy redundancy of the target area and the user profile of the charging station, and determines whether the charging station is connected to the grid energy storage device based on the energy consumption; an allocation strategy determination module, for one of the charging sites, if the charging site is connected to a power grid energy storage device, determining a target charging pile in the charging site, obtaining device information of the target charging pile, and determining an allocation strategy between the target charging pile in the charging site and the power grid energy storage device according to the device information; A power demand forecast result generating module, which generates a power demand forecast result of the target charging pile at a future time node according to the user profile of each charging station, the power redundancy of the target area and the allocation strategy; The power control strategy module obtains the control strategy of the target charging pile in the charging station at a future time node according to the power demand prediction result.

[0014] In a third aspect, the present application provides a charging pile operation management system based on a cloud platform, including: a memory configured to store instructions; and The processor is configured to call the instructions from the memory and implement the above-mentioned cloud platform-based charging pile operation management method when executing the instructions.

[0015] Through the above technical solution, by constructing a user profile for each charging station in the target area, the information of each charging station in the target area can be accurately grasped, which is helpful to provide more accurate services for users who use the charging stations. By judging whether the target area is connected to the power grid energy storage device, electric energy can be provided to the charging piles in the target area to ensure stable power supply for charging piles in areas with relatively large charging demand. In addition, through the user profile of each charging station, the power redundancy and allocation strategy of the target area, the power demand forecast results of the target charging piles at future time nodes are generated, the use of charging piles in the target area is mastered in advance, and electric energy regulation can be carried out according to the current power usage, which can effectively ensure stable power supply in the target area.

[0016] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a charging pile operation management method based on a cloud platform provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a charging pile operation and management platform provided in an embodiment of the present application; Figure 3 A schematic diagram of a structure for constructing a homogeneous graph neural network provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0020] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0021] Figure 1 The following schematically shows a flow chart of a charging pile operation management method based on a cloud platform according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a charging pile operation and management method based on a cloud platform, which may include the following steps.

[0022] S110, obtaining electric energy redundancy in a target area, where the target area includes at least one sub-area, and each sub-area includes at least one charging station; S120, obtaining historical charging information and station location of each charging station in the target area within a preset time period; S130, generating a user profile for each charging station by combining historical charging information and station locations; S140, predicting the power consumption of the charging station at a future time node based on the power redundancy of the target area and the user profile of the charging station, and determining whether the charging station is connected to the grid energy storage device based on the power consumption; S150: For one of the charging stations, if the charging station is connected to a grid energy storage device, determine a target charging pile in the charging station, obtain device information of the target charging pile, and determine an allocation strategy between the target charging pile in the charging station and the grid energy storage device according to the device information; S160, generating a power demand forecast result of a target charging pile at a future time node based on the user profile of each charging station, the power redundancy and allocation strategy of the target area; S170: Obtain a control strategy for a target charging pile in the charging station at a future time node based on the power demand forecast result.

[0023] First, the power redundancy of the target area is obtained. In this embodiment, the target area can be the city where the user who uses the charging pile is located. For example, the city where the user is located is Shanghai, and the target area is determined to be Shanghai. The power redundancy is the remaining power reserve in the power grid system of the target area on the basis of meeting the normal power load operation. The target area includes at least one sub-area, and each sub-area includes at least one charging station.

[0024] Secondly, the historical charging information and station location of each charging station in the target area within a preset time period are obtained. In this embodiment, the preset time period can be determined according to actual conditions. The historical charging information of each charging station includes the historical power consumption of the charging station, as well as the number of vehicles entering the charging station and the basic vehicle information.

[0025] By combining historical charging information and station locations, a user profile of each charging station is generated. Specifically, first, the historical information of each charging station is obtained. In this embodiment, the historical information of the charging station includes the historical power consumption of the charging station, the number of vehicles entering the charging station and the basic information of the vehicles. The vehicle charging data of each charging station is obtained through the corresponding basic information of the vehicles and the historical information of each charging station. In other words, the number of vehicles entering the charging station and the basic information of the vehicles are obtained. In this embodiment, the basic information of the vehicles includes the power consumed by the vehicle when it is fully charged and the energy consumption of the vehicle charging. For example, the battery capacity of the vehicle is 82 kWh, and a full charge requires 98 kWh of electricity. The efficiency of the charging equipment, the aging of the battery, and the ambient temperature and other factors will affect the energy consumption of the vehicle charging. The power consumed by the vehicle when it is fully charged and the energy consumption of the vehicle charging are determined by the power consumed by the vehicle when it enters the charging station to when it leaves the charging station, and the vehicle charging data of each charging station is determined within the preset time period. The vehicle charging data of each charging station is input into the pre-trained neural network model to generate the charging preference label of each charging station. The pre-trained neural network model refers to the neural network model that is pre-trained on a large-scale data set and is often used for trend prediction and other aspects. The charging preference label of each charging station and the location of each station constitute the user profile of each charging station. The user profile refers to the user information file constructed for a specific user group through data analysis, market research and user behavior. The user profile of the station is generated by the preference and location of the charging station.

[0026] After generating the user portrait, the power consumption of the charging station at the future time node is predicted based on the power redundancy of the target area and the user portrait of the charging station. Specifically, first, the power consumption of each charging station at the future time node is predicted through the user portrait of each charging station. For example, the consumption of each station in the historical time node can be obtained through the user portrait of the station. The power consumption at the future time node is predicted based on the consumption of each station in the historical time node. The power consumption at the future time node can be obtained through the prediction model, where the prediction model can be a neural network model. Secondly, by obtaining the dynamic data of power usage in the target area, the peak value of power data of each charging station is determined based on the peak value of power data of each charging station and the dynamic data of power usage in the target area. The power regulation data of all charging sites are compared with the power redundancy of the target area. If the power regulation data of all charging sites is greater than the power redundancy of the target area, it is determined that the charging site is connected to the grid energy storage device. For example, after determining the power regulation data of each charging site, the power regulation data are added to obtain the power regulation data of all charging sites. For example, the power regulation data of all charging sites is 5000WH, and the power redundancy of the target area is 4000WH. At this time, the power regulation data of all charging sites is greater than the power redundancy of the target area, and the power redundancy of the target area is insufficient, and the grid energy storage device needs to be connected.

[0027] When it is determined that the charging station needs to be connected to the grid energy storage device, the target charging pile in the charging station is determined, and the equipment information of the target charging pile is obtained. In this embodiment, the target charging station refers to the charging station that needs to be connected to the grid energy storage device, and the target charging pile refers to the charging pile in the charging station. The allocation strategy between the target charging pile and the grid energy storage device in the charging station is determined based on the equipment information, that is, by obtaining the equipment information of the target charging pile, in this embodiment, the equipment information of the target charging pile is the location information of the target charging pile and the amount of electric energy required by the charging pile. Through the equipment location information of the target charging pile in the charging station, the nearest grid energy storage device to the target charging pile is determined. By judging the energy reserve and equipment status of the target charging pile and the nearest grid energy storage device, the most suitable grid energy storage device for the target charging pile is determined, thereby determining the allocation strategy between the target charging pile and the grid energy storage device.

[0028] Through the user portrait of each site, the power redundancy and allocation strategy of the target area, the power demand forecast results of the target charging pile at the future time node are generated. That is to say, the power consumption of each site can be obtained through the user portrait of each site, and the power consumption of each site at the future time node can be predicted through the power consumption of each site and the power redundancy and allocation strategy of the target area. According to the predicted power consumption of each site at the future time node, the power demand forecast results of the target charging pile at the future time node can be generated.

[0029] Through the power demand forecast results, the control strategy of the target charging pile in the charging station at the future time node is obtained. For example, the power demand forecast results show that the power required by the charging station is 900kWh, and the power grid in the target area controls the power of the target charging pile to 600kWh, and there is a power shortage of 300kWh. Therefore, a power control strategy of 300kWh for the target charging pile in the charging station at the future time node will be generated.

[0030] Through the above technical solution, by constructing a user profile for each charging station in the target area, the information of each charging station in the target area can be accurately grasped, which is helpful to provide more accurate services for users who use the charging stations. By judging whether the target area is connected to the power grid energy storage device, electric energy can be provided to the charging piles in the target area to ensure stable power supply for charging piles in areas with relatively large charging demand. In addition, through the user profile of each charging station, the power redundancy and allocation strategy of the target area, the power demand forecast results of the target charging piles at future time nodes are generated, the use of charging piles in the target area is mastered in advance, and electric energy regulation can be carried out according to the current power usage, which can effectively ensure stable power supply in the target area.

[0031] In one implementation of this embodiment, historical charging information and station locations are combined to generate a user profile for each charging station, including: S210, constructing a homogeneous graph of charging stations according to historical charging information and station locations, where the homogeneous graph includes nodes and edges; S220, inputting the homogeneous graph into a pre-trained graph neural network model, and outputting a node vector of each charging station; S230. Generate a user profile for each charging station through the node vector, wherein the node vector corresponds to the user profile one-to-one, and the user profile for each charging station includes the charging type and charging habits of the vehicles at each charging station.

[0032] Combined with historical charging information and station locations, a user profile of each charging station is generated. Specifically, first, a homogeneous graph neural network of the charging station is constructed based on the historical charging information and station locations. A homogeneous graph means that all nodes and edges in the graph are of the same type, with relatively uniform structures and attributes, which is suitable for a simple and unified graph neural network model. Each charging station is used as a homogeneous graph neural network node. The homogeneous graph neural network includes nodes of the homogeneous graph corresponding to each charging station. The nodes of the homogeneous graph of each charging station are mainly obtained through the historical charging information of each charging station. The historical charging information of each charging station includes the historical power consumption of the charging station, as well as the number of vehicles entering the charging station and the basic information of the vehicles. The homogeneous graph neural network of the station is constructed through the location information of each charging station and the historical charging information of each charging station.

[0033] The homogeneous graph is input into the pre-trained graph neural network model, and the node vector of each charging station is output. Specifically, the homogeneous graph neural network of the charging station is constructed according to the historical charging information and the station location, and is input into the pre-trained graph neural network model, and the node vector of each charging station is output. The graph neural network is a deep learning model specifically used to process graph structure data. It can capture the neighborhood structure information of nodes and is widely used in various fields, such as social network analysis, bioinformatics, recommendation systems, etc. The homogeneous graph neural network is input into the graph neural network model to obtain the node vector of each charging station. In this embodiment, the node vector of each charging station includes vehicle charging type, vehicle charging habits, vehicle charging time characteristics and vehicle charging geographical characteristics.

[0034] After obtaining the node vector of each charging station through the graph neural network model, the user portrait of each charging station is obtained according to the characteristics of the node vector of each charging station. The user portrait refers to a user information file constructed for a specific user group through data analysis, market research, user behavior and other means. In this embodiment, the user portrait of each charging station includes the proportion of different vehicle types at each charging station, the vehicle charging habits of each charging station such as the average charging time and charging frequency, the time characteristics of each charging station such as the peak charging time period, the geographical characteristics of each charging station such as the different locations of different charging stations resulting in different main sources of users, and the consumption characteristics of users at each charging station such as the average charging fee payment method.

[0035] Through the node vector, a user profile of each charging station is generated, wherein the node vector corresponds to the user profile one by one, and the user profile of each charging station includes the charging type and charging habits of the vehicles in each charging station. For example, through the node vector of each station, such as any node feature in the homogeneous graph neural network, the vehicle charging habits, vehicle charging time features and vehicle charging geographical features in the node features are obtained, and the user profile of this node can be obtained, thereby determining the user profile of this charging station.

[0036] By constructing a homogeneous graph neural network and inputting it into a pre-trained graph neural network model, outputting the node vector of the charging station, and obtaining the user portrait of the charging station, the basic information of the charging station can be determined more accurately, so that the service of the charging station can be closer to the needs of users, the allocation of electric energy resources can be more efficient, and the market competitiveness of the charging station can be improved.

[0037] In one implementation of this embodiment, the nodes of the homogeneous graph are the historical charging information of each charging station, and the edges of the homogeneous graph are the distances between two charging stations.

[0038] A homogeneous graph neural network of charging stations is constructed based on historical charging information and station locations. A homogeneous graph means that all nodes and edges in the graph are of the same type, with relatively uniform structures and attributes, and is suitable for a simple and unified graph neural network model. A homogeneous graph neural network includes nodes of a homogeneous graph and edges of a homogeneous graph. A homogeneous graph means that all nodes and edges in the graph are of the same type, with relatively uniform structures and attributes, and is suitable for a simple and unified graph neural network model. That is to say, in this embodiment, the nodes of the homogeneous graph of the corresponding charging stations in the homogeneous graph neural network (historical charging information) include vehicle charging type, vehicle charging habits, vehicle charging time characteristics, and vehicle charging geographical characteristics, wherein the vehicle charging type is the charging form of different types of vehicles, such as fast charging or slow charging, the vehicle charging habits are the average charging time and frequency of the vehicle, the time characteristics of each charging station, such as the peak charging time period, the geographical characteristics of each charging station, such as the different locations of different charging stations, which makes the main sources of users different, and the consumption characteristics of users at each charging station, such as the average charging fee payment method.

[0039] In the process of constructing the homogeneous graph neural network, each charging station is used as a node of the homogeneous graph of the homogeneous graph neural network, such as Figure 3 As shown, Figure 3A schematic diagram of a structure for constructing a homogeneous graph neural network provided in an embodiment of the present application, wherein each charging station is regarded as node 1, node 2, node 3, etc. In this embodiment, the number of nodes is determined according to the time situation, and the distance between each charging station is regarded as the edge of the homogeneous graph of the homogeneous graph neural network. The distance between the two charging stations can be obtained by the station positions of the two charging stations. For example, in actual situations, the distance between the target charging pile and the nearest charging pile is regarded as the length of the edge in the homogeneous graph neural network, and the homogeneous graph neural network is constructed according to this length.

[0040] By treating each charging station as a node of the homogeneous graph of the homogeneous graph neural network and the distance between each charging station as an edge of the homogeneous graph of the homogeneous graph neural network, the relationship between each charging station can be more clearly displayed, providing more accurate information for the operation and management of charging piles.

[0041] In one implementation of this embodiment, based on the power redundancy of the target area and the user profile of the charging station, the power consumption of the charging station at a future time node is predicted, and based on the power consumption, whether the charging station is connected to the grid energy storage device is determined, including: S410, predicting the power consumption of each charging station at a future time node through the user portrait of each charging station, and obtaining the power data peak of each charging station according to the power consumption; S420, obtaining dynamic data on power usage in the target area, and determining power regulation data for each charging station according to the peak value of power data of each charging station and the dynamic data on power usage in the target area; S430: If the power regulation data of each charging station is greater than the power redundancy of the target area, it is determined that the charging station is connected to the grid energy storage device.

[0042] According to the power redundancy of the target area and the user portrait of the charging station, the power consumption of the charging station at the future time node is predicted, and whether the charging station is connected to the grid energy storage device is determined according to the power consumption. Specifically, first, the power consumption of each charging station at the future time node is predicted through the user portrait of each charging station. Specifically, first, the power consumption of each charging station is obtained through the user portrait of each charging station. The user portrait refers to a user information file constructed by means of data analysis, market research and user behavior for a specific user group. The information of the target group can be accurately obtained by using the user portrait. The power consumption of each charging station is input into the pre-trained model. In this embodiment, the pre-trained model can be a neural network model. The neural network model is a mathematical model that simulates the structure and function of the human brain neural network and is used to process and analyze data. The power consumption of each charging station is input into the neural network model, and the power consumption of each charging station at the future time node is output. In this embodiment, the future time node can be determined according to the actual situation.

[0043] Secondly, the dynamic data of power usage in the target area is obtained, and the power regulation data of each charging station is determined according to the peak power data of each charging station and the dynamic data of power usage in the target area. Specifically, the peak power data of each charging station is determined according to the peak power data of each charging station and the dynamic data of power usage in the target area by obtaining the dynamic data of power usage in the target area. The power regulation data of all charging stations are compared with the power redundancy of the target area. If the power regulation data of all charging stations is greater than the power redundancy of the target area, it is determined that the charging station is connected to the grid energy storage device. For example, after determining the power regulation data of each charging station, the power regulation data are added to obtain the power regulation data of all charging stations. For example, the power regulation data of all charging stations is 5000WH, and the power redundancy of the target area is 4000WH. At this time, the power regulation data of all charging stations is greater than the power redundancy of the target area. The power redundancy of the target area is insufficient and needs to be connected to the grid energy storage device.

[0044] By determining whether a charging station is connected to a grid energy storage device based on the amount of electricity consumed at a future time node, the power system operation efficiency can be effectively improved from a system level, and the reliability and stability of the power supply of the grid energy storage device can be improved, thereby effectively balancing the grid load and avoiding the shortage and waste of electricity resources.

[0045] In one implementation of this embodiment, the power regulation data of each charging site is determined according to the power data peak of each charging site and the power change dynamic data of the target area, including: S510, determining the dynamic data of electric energy change in the target area within the preset time interval where the peak value of electric energy data of each charging station is located as the first dynamic data; S520, treating the area where the first dynamic data is smaller than the average of the dynamic data of electric energy change in the target area as a low-energy consumption area; S530, respectively obtaining the power redundancy in the low-energy consumption area during the power data peak time period of each charging station; S540: Regulate the power redundancy in the low-energy consumption area to each charging station, and determine the power regulation data of each charging station.

[0046] Determine the dynamic data of electric energy change in the target area within the preset time interval where the peak value of the electric energy data of each charging station is located as the first dynamic data. In this embodiment, the first dynamic data is the peak phase of the electric energy data of each charging station. Determine the dynamic data of electric energy changes in the target area within the preset time interval where the peak value of the electric energy data of each charging station is located as the first dynamic data. In this embodiment, the first dynamic data is the dynamic data of electric energy changes in the target area during the peak stage of the electric energy data of each charging station. The dynamic data of electric energy changes in the target area during the peak time period of the electric energy data of each charging station is determined.

[0047] Areas where the first dynamic data is less than the average of the dynamic data of electric energy changes in the target area are taken as low-energy consumption areas. That is to say, at each charging station, during the peak time period of electric energy data, the power consumption of the target area is judged, and areas where the first dynamic data is less than the average of the dynamic data of electric energy changes in the target area are taken as low-energy consumption areas. In this embodiment, low-energy consumption areas are areas where the first dynamic data is less than the average of the dynamic data of electric energy changes in the target area. By determining the location of the low-energy consumption area, the electric energy at the location of the low-energy consumption area is regulated during the peak stage of electric energy consumption of the target charging pile, and is regulated to the target charging pile that needs to be supplemented with electric energy during the peak stage of electric energy consumption of the target charging pile.

[0048] After obtaining the location of the low-energy consumption area, obtain the power redundancy of the low-energy consumption area in the peak time period of the power data of each charging station, and regulate the power redundancy of the low-energy consumption area to each charging station, and determine the power regulation data of each charging station. Specifically, after determining the low-energy consumption area, confirm the power redundancy of the low-energy consumption area, and regulate the power redundancy of the low-energy consumption area to each charging station that needs power supplement, thereby determining the power regulation data of each charging station.

[0049] By determining the power regulation data of each charging station through the peak power data of each charging station and the dynamic data of power changes in the target area, the power amount required by each charging station can be determined, which helps to accurately replenish power for each charging station and effectively avoid waste of power resources.

[0050] In one implementation of this embodiment, predicting the power consumption of each charging station at a future time node based on the user portrait of each charging station includes: S610, obtaining the power consumption of each charging station through the user portrait of each charging station; S620: Input the power consumption of each charging station into the pre-trained model to predict the power consumption of each charging station at a future time node.

[0051] Through the user portrait of each charging station, the power consumption of each charging station at future time nodes is predicted. Specifically, first, the power consumption of each charging station is obtained through the user portrait of each charging station. User portrait refers to a user information file constructed for a specific user group through data analysis, market research, user behavior and other means. User portrait can be used to accurately obtain information about the target group.

[0052] The acquired electric energy consumption of each charging station is input into a pre-trained model. In this embodiment, the pre-trained model may be a neural network model. The neural network model is a mathematical model that simulates the structure and function of the human brain neural network and is used to process and analyze data. The electric energy consumption of each charging station is input into the neural network model, and the electric energy consumption of each charging station at a future time node is output. In this embodiment, the future time node may be determined based on actual conditions.

[0053] In this embodiment, the user portrait of each charging station includes the charging type and charging habits of the vehicles in each charging station. Specifically, the charging type includes the charging power required for different types of vehicles (such as pure electric vehicles and plug-in hybrid vehicles), and the charging habits include the charging frequency and charging time of each type of vehicle.

[0054] According to the charging power and charging frequency, the power consumption of each charging station is obtained, including: Cluster the charging types and charging durations of vehicles at all charging stations to obtain the power demand set and charging duration set for each charging type; Calculating a first average value of the power demand set and a second average value of the charging duration set; The electric energy consumption calculation formula is adopted to calculate the electric energy consumption of different charging types in each charging station according to the first average value, the second average value and the charging frequency.

[0055] The formula for calculating electric energy consumption includes: ; Where E is the energy consumption (unit: kWh), P is the average power requirement of each charging type (unit: kW), which is obtained by clustering and averaging the power of all charging types, and F is the charging frequency, which means the number of times the battery is charged in a specific time period.

[0056] The first average value represents the average charging power (unit: kW) of each charging type, and the second average value represents the average charging time (unit: hour) of each charging type.

[0057] By clustering the charging type and charging time of vehicles, users' charging habits can be understood more accurately, thus providing data support for the operation and management of charging stations. At the same time, calculating the average value of power demand and charging time can reduce the impact of individual outliers on the calculation of power consumption, thereby improving the accuracy of the calculation. The clustering method can identify the characteristics of different charging types, making the average value of each type more representative. By understanding the power consumption of different charging types, charging stations can allocate resources more efficiently. The number of charging piles or power settings can be adjusted according to high-demand periods to meet user needs.

[0058] By using the pre-trained neural network model to obtain the power consumption of each charging station at future time nodes, the efficiency of power regulation can be improved for each charging station, the accuracy of power regulation can be ensured, and potential risks can be better identified, thereby optimizing the power regulation management process and improving overall efficiency.

[0059] In one implementation of this embodiment, determining an allocation strategy between a target charging pile and a grid energy storage device in a charging site according to device information includes: S710, in response to a user's selection instruction for a target charging pile in a charging station, obtaining a location of the target charging pile, and identifying a grid energy storage device that is closest to the location of the target charging pile as a first energy storage device; S720, obtaining information of the first energy storage device; S730: Compare the information of the first energy storage device with the information of the target charging pile, and determine an allocation strategy between the target charging pile and the grid energy storage device in the charging station.

[0060] In response to a user's selection instruction for a target charging pile in a charging station, the location of the target charging pile is obtained, and the grid energy storage device that is closest to the location of the target charging pile is identified as a first energy storage device. In this embodiment, the first energy storage device is a device for storing electrical energy, such as a clean energy microgrid device. The charging station is a charging station that needs to be connected to a grid energy storage device. The target charging pile is any charging pile in the charging station. That is to say, when the user selects a charging pile to charge in the target charging station, the location of the target charging pile selected by the user is obtained, and the grid energy storage device that is closest to the location of the target charging pile is identified as the first energy storage device.

[0061] After identifying the grid energy storage device that is closest to the target charging pile, obtain the information of the first energy storage device. In this embodiment, the information of the first energy storage device is the energy storage capacity and device status of the first energy storage device. Compare the information of the first energy storage device with the information of the target charging pile to determine the allocation strategy between the target charging pile and the grid energy storage device in the charging station. Specifically, compare the required power of the target charging pile with the stored power of the first energy storage device to determine whether the stored power of the first energy storage device is greater than the required power of the target charging pile. When the stored power of the first energy storage device is greater than the required power of the target charging pile, determine the first matching degree between the target charging pile and the first energy storage device. Secondly, compare the geographical location information of the target charging pile with the geographical location information of the first energy storage device. If the geographical location of the target charging pile is less than the preset distance from the geographical location of the first energy storage device, determine the second matching degree between the target charging pile and the first energy storage device. Finally, by judging whether the grid energy storage device connected to the target charging pile is faulty, when the grid energy storage device connected to the target charging pile is in a normal state, the third matching degree between the target charging pile and the first energy storage device is determined. When the first matching degree, the second matching degree and the third matching degree all meet the corresponding preset standards, the allocation strategy between the target charging pile and the grid energy storage device in the charging station is determined.

[0062] By determining the allocation strategy between the target charging piles in the charging station and the grid energy storage device, the target charging piles in the charging station can be powered in a timely manner to ensure the smooth operation of the power supply of the target charging station.

[0063] In one implementation of this embodiment, the information of the first energy storage device and the information of the charging pile include power control data, location information of the grid energy storage device and the charging pile, and fault information of the grid energy storage device. The information of the first energy storage device is compared with the information of the target charging pile to determine the allocation strategy between the target charging pile and the grid energy storage device in the charging station, including: S810, obtaining dynamic power change data of the target charging pile, and determining first control data of the target charging pile according to the dynamic power change data of the target charging pile; S820, comparing the first control data of the target charging pile with the electric energy redundancy of the first energy storage device, and if the electric energy redundancy is greater than the first control data, determining a first matching degree between the target charging pile and the first energy storage device; S830, comparing the geographical location information of the target charging pile with the geographical location information of the first energy storage device, and if the geographical location of the target charging pile and the geographical location of the first energy storage device are less than a preset distance, determining a second matching degree between the target charging pile and the first energy storage device; S840, determining whether a grid energy storage device connected to the target charging pile is faulty; S850: If the grid energy storage device connected to the target charging pile is not faulty, obtaining the power output state of the grid energy storage device; if the power output state of the grid energy storage device is a stable output state, determining a third matching degree between the target charging pile and the first energy storage device; S860: If the first matching degree, the second matching degree, and the third matching degree all meet corresponding preset standards, determine an allocation strategy between the target charging piles in the charging station and the grid energy storage device.

[0064] The dynamic power change data of the target charging pile is obtained, and the first control data of the target charging pile is determined through the dynamic power change data of the target charging pile. Specifically, the peak stage of power consumption and the trough stage of power consumption of the target charging pile during the power change process can be determined through the dynamic power change data of the target charging pile. When the power consumption is at the peak stage, the power consumption of the target charging pile is greater than the regulated power of the target charging pile in the target area and the target site. At this time, the power required by the target charging pile is determined, and the power required by the target charging pile is used as the first control data of the target charging pile.

[0065] The first control data of the target charging pile is compared with the electric energy redundancy of the first energy storage device. If the electric energy redundancy is greater than the first control data, the first matching degree of the target charging pile and the first energy storage device is determined. In this embodiment, the first control data refers to the electric energy required by the target charging pile when the electric energy consumption of the target charging pile is greater than the electric energy regulated by the target charging pile in the target area for the target site. For example, the electric energy regulated by the target area for the target site is 400kWh. When the regulated electric energy is less than the electric energy consumed by the target site, the electric energy of the target site is insufficient at this time, and the electric energy required by the target charging pile. When the target charging pile determines the first energy storage device that is closest to it, the electric energy required by the target charging pile is compared with the electric energy redundancy of the first energy storage device. If the electric energy redundancy is greater than the first control data, it means that the electric energy of the first energy storage device at this time can supply power to the target charging pile, and the first control data of the target charging pile is determined.

[0066] The geographic location information of the target charging pile is compared with the geographic location information of the first energy storage device. If the geographic location of the target charging pile is less than the preset distance from the geographic location of the first energy storage device, the second matching degree of the target charging pile and the first energy storage device is determined. Specifically, first, the geographic location information of the target charging pile is obtained, and a search is performed at the location of the target charging pile to determine the first energy storage device that is closest to the target charging pile, and the second matching degree of the target charging pile and the first energy storage device is determined. For example, a search is performed at the location of the target charging pile to find five energy storage devices, and the distances between the five energy storage devices and the target charging pile are 400 meters, 600 meters, 200 meters, 500 meters, and 300 meters, respectively. The power grid energy storage device that is 200 meters away from the target charging pile is used as the first energy storage device.

[0067] After determining the second matching degree between the target charging pile and the first energy storage device, determine whether the power grid energy storage device connected to the target charging pile is faulty, and determine the fault information of the target charging pile. When the fault information of the first energy storage device connected to the target charging pile is obtained, it is determined that the first energy storage device is faulty and cannot provide stable power supply to the target charging pile. At this time, the third matching degree between the target charging pile and the first energy storage device cannot be determined. After identifying the first energy storage device and determining that there is no fault information, the first energy storage device can provide stable power supply to the target charging pile, and determine the third matching degree between the target charging pile and the first energy storage device. In this embodiment, the voltage fluctuation of the stable input of the power grid energy storage device is within the range of ±5% of the rated value, indicating that the power grid energy storage device can provide stable power supply to the target charging pile.

[0068] If the first matching degree, the second matching degree and the third matching degree all meet the corresponding preset standards, the allocation strategy between the target charging pile and the grid energy storage device in the charging station is determined. Specifically, when the distance range between the target charging pile and the first energy storage device is the closest range, the first matching degree between the target charging pile and the first energy storage device is determined. When the first control data of the target charging pile is less than the power redundancy of the first energy storage device, the second matching degree between the target charging pile and the first energy storage device is determined. For example, when the power redundancy of the first energy storage device closest to the target charging pile is 300kWh, but the first control data of the target charging pile is 400kWh, it means that the power redundancy of the first energy storage device is insufficient at this time and it is impossible to provide stable power supply to the target charging pile. At this time, it is necessary to determine the grid energy storage device with the second closest distance to the target charging pile, and judge the first control data of the target charging pile and the power redundancy of the grid energy storage device with the second closest distance. When the first control data of the target charging pile is less than the power redundancy of the grid energy storage device with the second closest distance, the second matching degree between the target charging pile and the grid energy storage device with the second closest distance is determined.

[0069] By comparing the first matching degree, the second matching degree and the third matching degree between the target charging pile and the first energy storage device, the position and information of the first energy storage device can be obtained more accurately, ensuring that the first energy storage device can supply power to the target charging pile, so that the power supply of the target charging pile is stable, and the user experience of using the target charging pile is improved.

[0070] Figure 2 A schematic diagram of the structure of a charging pile operation and management platform based on a cloud platform provided in an embodiment of the present application is shown, Figure 2 As shown, the embodiment of the present application also provides a charging pile operation management platform, including: The power redundancy acquisition module 10 acquires the power redundancy of a target area, where the target area includes at least one sub-area, and each sub-area includes at least one charging station; A historical charging information and station location acquisition module 20, which acquires historical charging information and station location of each charging station in a target area within a preset time period; The user portrait generation module 30 generates a user portrait for each charging station by combining the historical charging information and the station location; The grid energy storage device access module 40 predicts the energy consumption of the charging station at a future time node based on the energy redundancy of the target area and the user profile of the charging station, and determines whether the charging station is connected to the grid energy storage device based on the energy consumption; The allocation strategy determination module 50 determines, for one of the charging stations, a target charging pile in the charging station, obtains device information of the target charging pile, and determines an allocation strategy between the target charging pile in the charging station and the grid energy storage device according to the device information; The power demand forecast result generating module 60 generates the power demand forecast result of the target charging pile at a future time node according to the user profile of each charging station, the power redundancy and allocation strategy of the target area; The power control strategy module 70 obtains the control strategy of the target charging pile in the charging station at a future time node according to the power demand prediction result.

[0071] The present application also provides an electronic device, including: a memory configured to store instructions; and The processor is configured to call instructions from the memory and implement the above-mentioned cloud platform-based charging pile operation management method when executing the instructions.

[0072] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0073] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0077] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0078] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0079] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0080] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A charging pile operation management method based on a cloud platform, characterized in that: include: Acquiring a power redundancy amount of a target area, wherein the target area includes at least one sub-area, and each sub-area includes at least one charging station; Obtaining historical charging information and station location of each charging station in the target area within a preset time period; Combining the historical charging information and the station location, generating a user profile for each charging station; According to the power redundancy of the target area and the user profile of the charging station, the power consumption of the charging station at a future time node is predicted, and according to the power consumption, whether the charging station is connected to the grid energy storage device is determined; For one of the charging sites, if the charging site is connected to a grid energy storage device, determine a target charging pile in the charging site, obtain device information of the target charging pile, and determine an allocation strategy between the target charging pile in the charging site and the grid energy storage device according to the device information; Generate a power demand forecast result of the target charging pile at a future time node according to the user profile of each charging station, the power redundancy of the target area and the allocation strategy; According to the power demand forecast result, a control strategy for the target charging pile in the charging station at a future time node is obtained.

2. The method according to claim 1, characterized in that The generating a user profile of each charging station by combining the historical charging information and the station location includes: Constructing a homogeneous graph of the charging stations according to the historical charging information and the station locations, wherein the homogeneous graph includes nodes and edges; Inputting the homogeneous graph into a pre-trained graph neural network model, and outputting a node vector of each charging station; A user portrait of each charging site is generated through the node vector, wherein the node vector corresponds to the user portrait one-to-one, and the user portrait of each charging site includes the charging type and charging habits of the vehicles in each charging site.

3. The method according to claim 2, characterized in that The nodes of the homogeneous graph are the historical charging information of each charging station, and the edges of the homogeneous graph are the distance between two charging stations.

4. The method according to claim 2, characterized in that: The method predicts the power consumption of the charging station at a future time node based on the power redundancy of the target area and the user profile of the charging station, and determines whether the charging station is connected to a power grid energy storage device based on the power consumption, including: Predicting the power consumption of each charging station at a future time node through the user portrait of each charging station, and obtaining the power data peak of each charging station according to the power consumption; Acquire the dynamic data of power usage in the target area, and determine the power regulation data of each charging station according to the peak value of the power data of each charging station and the dynamic data of power usage in the target area; If the power regulation data of each of the charging sites is greater than the power redundancy of the target area, it is determined that the charging site is connected to the power grid energy storage device.

5. The method according to claim 4, characterized in that The step of determining the power regulation data of each charging site according to the power data peak value of each charging site and the power change dynamic data of the target area includes: Determining first dynamic data from the power change dynamic data of the target area, wherein the first dynamic data is the power change dynamic data within a preset time interval where the power data peak of each charging station is located; The area where the first dynamic data is smaller than the average of the dynamic data of electric energy change in the target area is regarded as a low-energy consumption area; Respectively obtaining the electric energy redundancy of the low-energy consumption area in the electric energy data peak time period of each charging station; The redundant power in the low-power consumption area is respectively regulated to each of the charging sites, and the power regulation data of each of the charging sites is determined.

6. The method according to claim 4, characterized in that The predicting of the power consumption of each charging station at a future time node based on the user profile of each charging station includes: Obtaining the power consumption of each charging station through the user portrait of each charging station; The power consumption of each charging station is input into the pre-trained model to predict the power consumption of each charging station at a future time node.

7. The method according to claim 1, characterized in that The determining, according to the device information, an allocation strategy between a target charging pile in the charging site and the grid energy storage device comprises: In response to a user's selection instruction for a target charging pile in the charging station, obtaining a location of the target charging pile, and identifying a grid energy storage device that is closest to the location of the target charging pile as a first energy storage device; Acquiring information of the first energy storage device; The information of the first energy storage device is compared with the information of the target charging pile to determine an allocation strategy between the target charging pile in the charging station and the grid energy storage device.

8. The method according to claim 7, characterized in that The information of the first energy storage device and the information of the charging pile include power regulation data, location information of the power grid energy storage device and the charging pile, and fault information of the power grid energy storage device. The information of the first energy storage device is compared with the information of the target charging pile to determine the allocation strategy between the target charging pile in the charging station and the power grid energy storage device, including: Acquire dynamic power change data of the target charging pile, and determine first control data of the target charging pile according to the dynamic power change data of the target charging pile; Comparing the first control data of the target charging pile with the electric energy redundancy of the first energy storage device, and if the electric energy redundancy is greater than the first control data, determining a first matching degree between the target charging pile and the first energy storage device; Comparing the geographical location information of the target charging pile with the geographical location information of the first energy storage device, and determining a second matching degree between the target charging pile and the first energy storage device if the geographical location of the target charging pile and the geographical location of the first energy storage device are less than a preset distance; Determining whether the grid energy storage device connected to the target charging pile is faulty; If the grid energy storage device connected to the target charging pile is not faulty, obtaining the power output state of the grid energy storage device, and if the power output state of the grid energy storage device is a stable output state, determining a third matching degree between the target charging pile and the first energy storage device; If the first matching degree, the second matching degree and the third matching degree all meet the corresponding preset standards, an allocation strategy between the target charging pile in the charging site and the grid energy storage device is determined.

9. A charging pile operation management platform, characterized in that: include: An electric energy redundancy acquisition module is used to acquire electric energy redundancy in a target area, wherein the target area includes at least one sub-area, and each sub-area includes at least one charging station; A historical charging information and station location acquisition module, which acquires the historical charging information and station location of each charging station in the target area within a preset time period; A user portrait generation module, combining the historical charging information and the station location to generate a user portrait for each charging station; A grid energy storage device access module predicts the energy consumption of the charging station at a future time node based on the energy redundancy of the target area and the user profile of the charging station, and determines whether the charging station is connected to the grid energy storage device based on the energy consumption; an allocation strategy determination module, for one of the charging sites, if the charging site is connected to a power grid energy storage device, determining a target charging pile in the charging site, obtaining device information of the target charging pile, and determining an allocation strategy between the target charging pile in the charging site and the power grid energy storage device according to the device information; A power demand forecast result generating module, which generates a power demand forecast result of the target charging pile at a future time node according to the user profile of each charging station, the power redundancy of the target area and the allocation strategy; The power control strategy module obtains the control strategy of the target charging pile in the charging station at a future time node according to the power demand prediction result.

10. A charging pile operation and management system based on a cloud platform, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instruction from the memory and to implement the charging pile operation management method based on a cloud platform according to any one of claims 1 to 8 when executing the instruction.

Images