Power grid charging strategy determination method and device and electronic equipment

Abstract

The invention discloses a power grid charging strategy determination method and device and electronic equipment. The method comprises the steps that a dynamic space charging model of a predetermined charging station is established, and the dynamic space charging model comprises a plurality of data items; according to the dynamic space charging model, an objective function and constraint conditions used for determining an electric vehicle charging strategy are constructed, the objective function aims at minimizing the charging cost of an electric vehicle user and maximizing the charging amount of the electric vehicle, and the constraint conditions comprise the battery capacity constraint and the battery remaining capacity constraint; the demand constraint of a user on the SOC of the battery and the charging electricity price constraint during parking are carried out; and solving the objective function under the constraint condition to obtain a power grid charging strategy. The technical problem that the determined power grid charging strategy is not accurate when the power grid charging strategy for balancing the charging cost and the charging electric quantity is determined in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of charging strategy determination, and in particular to a method, device and electronic equipment for determining a power grid charging strategy. Background Art

[0002] As the world becomes increasingly concerned about climate change and environmental issues, countries are taking active actions to promote the development of renewable energy and clean transportation. In this context, electric vehicles, as a representative of clean energy transportation, have attracted extensive research and attention. However, the large-scale popularization of electric vehicles has also brought about a series of new problems, one of which is how to use electricity more efficiently and effectively manage the load of the power system.

[0003] In the current context, the research on charging and discharging scheduling of electric vehicle clusters has become the focus of current attention. As a reliable backup auxiliary service resource in the power grid, electric vehicles are considered to be a high-quality asset due to their excellent flexibility and energy storage characteristics. By adopting a reasonable scheduling strategy, electric vehicles are expected to alleviate the challenges of grid load, achieve load balancing of the power system, and even act as distributed power sources when needed. Therefore, establishing a comprehensive optimization scheduling strategy is crucial to effectively balance the supply and demand relationship in the new energy power generation market. However, when determining the grid charging strategy that balances the charging cost and the charging power in the related technology, there is a technical problem that the determined grid charging strategy is inaccurate.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and electronic device for determining a power grid charging strategy, so as to at least solve the technical problem that when determining a power grid charging strategy for balancing charging cost and charging power in the related art, the determined power grid charging strategy is inaccurate.

[0006] According to one aspect of an embodiment of the present invention, a method for determining a power grid charging strategy is provided, comprising: establishing a dynamic spatial charging model of a predetermined charging station, wherein the dynamic spatial charging model comprises a plurality of data items, and the plurality of data items comprise: an electric vehicle serial number, an electric vehicle access grid status, an electric vehicle charging mode, and an electric vehicle battery state of charge; based on the dynamic spatial charging model, constructing an objective function and constraints for determining an electric vehicle charging strategy, wherein the objective function aims to minimize the charging cost of electric vehicle users and maximize the charging amount of the electric vehicle, and the constraints comprise battery capacity constraints, battery remaining power constraints, user demand constraints for battery SOC, and charging electricity price constraints during parking; solving the objective function under the constraints to obtain a power grid charging strategy.

[0007] Optionally, after solving the objective function under the constraints and obtaining the power grid charging strategy, it also includes: when the power grid charging strategy includes charging powers corresponding to multiple electric vehicles respectively, determining the newly added vehicles in the predetermined charging station within a predetermined time period; when the number of the newly added vehicles is less than a predetermined threshold, obtaining the newly added vehicle data corresponding to the newly added vehicles, wherein the newly added vehicle data at least includes: newly added vehicle parameter data, preferred charging data corresponding to the owner of the newly added vehicle, and newly added historical charging data; based on the newly added vehicle data and associated features, determining the charging power allocated to the newly added vehicle, wherein the associated features are associated features representing the relationship between the charging power and the vehicle data.

[0008] Optionally, before determining the charging power allocated to the newly added vehicle based on the newly added vehicle data and associated features, the method further includes: obtaining sample vehicle data corresponding to a plurality of sample electric vehicles that have been charged at the predetermined charging station, wherein the sample vehicle data includes at least: sample vehicle parameter data, preferred charging data corresponding to the sample vehicle owner, and sample historical charging data; inputting the sample charging powers and sample vehicle data corresponding to the plurality of sample electric vehicles into a neural network model for feature extraction to obtain the associated features representing the relationship between the charging power and the vehicle data.

[0009] Optionally, in the case of the charging powers corresponding to the multiple electric vehicles included in the grid charging strategy, after determining the newly added vehicles in the predetermined charging station within the predetermined time period, it also includes: when the number of the newly added vehicles is greater than a predetermined threshold, updating the dynamic spatial charging model of the predetermined charging station to obtain an updated spatial charging model; based on the updated spatial charging model, determining the update objective function and update constraints: solving the update objective function under the update constraints to obtain an updated grid charging strategy, wherein the updated grid charging strategy includes the charging strategy corresponding to the newly added vehicles.

[0010] Optionally, establishing a dynamic spatial charging model for a predetermined charging station includes: obtaining full vehicle data of vehicles in the predetermined charging station and charging station parameters of the predetermined charging station; and establishing a dynamic spatial charging model for the predetermined charging station based on the full vehicle data and the charging station parameters.

[0011] Optionally, determining the charging mode of the electric vehicle includes: determining the time required to reach the expected power and the expected price based on the expected power when the vehicle leaves the predetermined charging station, the connected power when the vehicle connects to the predetermined charging station, the rated capacity of the vehicle battery, and the charging power corresponding to multiple candidate charging modes, wherein the multiple candidate charging modes include: a fast charging mode, a slow charging mode that does not obey the grid dispatch, and a slow charging mode that obeys the grid dispatch; determining the charging mode of the electric vehicle from multiple candidate charging modes based on the time required to reach the expected power and the expected price.

[0012] Optionally, a first sub-function is constructed based on the time period electricity price, the charging powers corresponding to multiple candidate charging modes, and the charging electricity prices corresponding to multiple candidate charging modes, and a second sub-function is determined based on the average power consumption of the electric vehicle in driving state and the charging power of the electric vehicle; the objective function is determined based on the first sub-function and the second sub-function.

[0013] According to one aspect of an embodiment of the present invention, a device for determining a power grid charging strategy is provided, comprising: an establishment module for establishing a dynamic spatial charging model of a predetermined charging station, wherein the dynamic spatial charging model comprises a plurality of data items, and the plurality of data items comprise: an electric vehicle serial number, an electric vehicle access grid status, an electric vehicle charging mode, and an electric vehicle battery state of charge; a construction module for constructing an objective function and constraints for determining an electric vehicle charging strategy based on the dynamic spatial charging model, wherein the objective function aims to minimize the charging cost of electric vehicle users and maximize the charging amount of the electric vehicle, and the constraints comprise battery capacity constraints, battery remaining power constraints, user demand constraints for battery SOC, and charging price constraints during parking; a determination module for solving the objective function under the constraints to obtain a power grid charging strategy.

[0014] According to one aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement any of the above-mentioned methods for determining a power grid charging strategy.

[0015] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any of the above-mentioned methods for determining a power grid charging strategy.

[0016] In an embodiment of the present invention, a dynamic spatial charging model of a predetermined charging station is established, wherein the dynamic spatial charging model includes multiple data items, and the multiple data items include: an electric vehicle serial number, an electric vehicle access grid state, an electric vehicle charging mode, and an electric vehicle battery state of charge. According to the dynamic spatial charging model, an objective function and constraints for determining an electric vehicle charging strategy are constructed, wherein the objective function is to minimize the charging cost of electric vehicle users and maximize the charging amount of electric vehicles, and the constraints include battery capacity constraints, battery remaining power constraints, user demand constraints for battery SOC, and charging electricity price constraints during parking. Solve the objective function under the constraints to obtain a grid charging strategy. Among them, an objective function is formulated to minimize the charging cost of electric vehicle users and maximize the charging amount of electric vehicles, so that the charging cost and the charging amount can be balanced. Because it is specifically constructed according to the dynamic spatial charging model of the predetermined charging station, the accuracy of the constructed objective function and constraints can be guaranteed, thereby solving the technical problem that when determining a grid charging strategy that balances the charging cost and the charging amount in the related art, the determined grid charging strategy is inaccurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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:

[0018] Figure 1 is a flow chart of a method for determining a power grid charging strategy according to an embodiment of the present invention;

[0019] Figure 2 4 is a structural block diagram of a device for determining a power grid charging strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the specification 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 data 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] Example 1

[0023] According to an embodiment of the present invention, an embodiment of a method for determining a power grid charging strategy 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.

[0024] Figure 1 is a flow chart of a method for determining a power grid charging strategy according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0025] Step S102, establishing a dynamic spatial charging model of a predetermined charging station, wherein the dynamic spatial charging model includes multiple data items, and the multiple data items include: an electric vehicle serial number, a state of the electric vehicle connected to a power grid, a charging mode of the electric vehicle, and a battery state of charge of the electric vehicle;

[0026] In step S102 provided in the present application, the establishment of a dynamic space charging model is explained. The dynamic space charging model is a model used to comprehensively determine the charging status or situation of vehicles inside a predetermined charging station, and to monitor and analyze data items such as the serial number, grid access status, charging mode, and battery charge status of the electric vehicle to achieve dynamic management and optimized scheduling of electric vehicles in the charging station. Among them, the electric vehicle serial number is used to uniquely identify each electric vehicle, the grid access status indicates whether the electric vehicle has been connected to the grid of the charging station, that is, whether it is already charging, the charging mode includes different charging methods such as fast charging and slow charging, and the battery charge status reflects the remaining power of the electric vehicle battery.

[0027] Through the dynamic spatial charging model, the charging station can monitor the charging needs of each electric vehicle in real time, and flexibly adjust the charging mode and charging power according to the access status of the electric vehicle and the battery charge state, so as to maximize the charging efficiency and resource utilization. In addition, the dynamic spatial charging model can also predict future charging needs through data analysis of electric vehicles in the charging station, and make allocation and planning of charging station resources in advance, thereby improving the operating efficiency and user experience of the charging station.

[0028] Step S104, based on the dynamic space charging model, construct an objective function and constraints for determining the electric vehicle charging strategy, wherein the objective function aims to minimize the charging cost of the electric vehicle user and maximize the charging amount of the electric vehicle, and the constraints include battery capacity constraints, battery remaining power constraints, user demand constraints on battery power SOC and charging electricity price constraints during parking:

[0029] In step S104 provided in the present application, an objective function and constraint conditions for determining an electric vehicle charging strategy are constructed based on a dynamic spatial charging model. The determined electric vehicle charging strategy refers to selecting when and how to charge in different time periods to maximize the user's charging benefits and reduce charging costs, and is a strategy for how to charge in different time periods.

[0030] Among them, the objective function is to minimize the charging cost and maximize the charging amount, which can improve the user's charging satisfaction and save charging costs. Among them, the constraints are to limit the battery capacity, remaining power, user's demand for battery SOC and charging electricity price during parking of electric vehicles, to ensure that the battery life will not be damaged during the charging process, meet the user's charging needs, and consider the charging cost and charging efficiency. By setting the battery capacity constraint, it can be ensured that the electric vehicle will not exceed the maximum capacity of the battery during the charging process to avoid damage to the battery life. By setting the battery remaining power constraint, the battery remaining power needs to be considered before charging to determine the most suitable charging strategy to avoid overcharging or undercharging. By setting the user's demand constraint for battery SOC, the corresponding charging plan can be formulated according to the user's demand for battery SOC to meet the user's charging needs. Through the charging electricity price constraint during parking, the charging electricity price during parking can be considered, and charging can be selected during the period with lower electricity prices to reduce the charging cost. These constraints can help optimize the charging strategy of electric vehicles, improve charging efficiency and user satisfaction, while reducing charging costs and promoting the promotion and application of electric vehicles. By minimizing the charging cost and maximizing the charging amount as well as the constraints, a more reasonable and efficient electric vehicle charging strategy can be achieved, providing users with a better charging experience and economic benefits.

[0031] Step S106, solving the objective function under the constraint conditions to obtain the grid charging strategy.

[0032] In step S106 provided in the present application, the objective function under the constraint condition is solved to obtain the grid charging strategy. By solving the objective function under the constraint condition, a more efficient and sustainable grid charging strategy can be obtained, thereby improving the utilization rate of the grid, reducing energy waste, optimizing charging efficiency, and reducing energy costs. The purpose of dynamically managing and optimizing the charging status of vehicles in the predetermined charging station is achieved.

[0033] Through the above steps S102-S106, a dynamic spatial charging model of a predetermined charging station is established, wherein the dynamic spatial charging model includes multiple data items, and the multiple data items include: the serial number of the electric vehicle, the state of access to the electric grid, the charging mode of the electric vehicle, and the battery state of charge of the electric vehicle. According to the dynamic spatial charging model, an objective function and constraints for determining the charging strategy of the electric vehicle are constructed, wherein the objective function is to minimize the charging cost of the electric vehicle user and maximize the charging amount of the electric vehicle, and the constraints include battery capacity constraints, battery remaining power constraints, user demand constraints for battery SOC, and charging electricity price constraints during parking. Solve the objective function under the constraints to obtain the grid charging strategy. Among them, an objective function is formulated to minimize the charging cost of the electric vehicle user and maximize the charging amount of the electric vehicle, so that the charging cost and the charging amount can be balanced. Because it is specifically constructed according to the dynamic spatial charging model of the predetermined charging station, the accuracy of the constructed objective function and constraints can be guaranteed, thereby solving the technical problem that the determined grid charging strategy is inaccurate when determining the grid charging strategy that balances the charging cost and the charging amount in the related technology.

[0034] As an optional embodiment, after solving the objective function under the constraints and obtaining the power grid charging strategy, it also includes: when the power grid charging strategy includes charging powers corresponding to multiple electric vehicles, determining new vehicles in a predetermined charging station within a predetermined time period; when the number of new vehicles is less than a predetermined threshold, obtaining new vehicle data corresponding to the new vehicles, wherein the new vehicle data at least includes: new vehicle parameter data, preferred charging data corresponding to the owner of the new vehicle, and new historical charging data; based on the new vehicle data and associated features, determining the charging power allocated to the new vehicle, wherein the associated features are associated features that represent the relationship between the charging power and the vehicle data.

[0035] In this embodiment, after solving the objective function under the constraint conditions and obtaining the grid charging strategy, the charging behavior of newly entered vehicles in the predetermined charging station is also considered. When the grid charging strategy includes the charging powers corresponding to multiple electric vehicles, the newly added vehicles in the predetermined charging station within the predetermined time period can be determined, and the method of allocating charging power to the newly added vehicles can be determined based on the number of newly added vehicles. In particular, when the number of newly added vehicles is less than the predetermined threshold, a separate allocation can be made, and when the number of newly added vehicles is greater than or equal to the predetermined threshold, a global judgment and allocation is made. In this embodiment, the operation steps when the number of newly added vehicles is less than the predetermined threshold are described.

[0036] When the number of newly added vehicles is less than a predetermined threshold, the newly added vehicle data corresponding to the newly added vehicles can be obtained, wherein the newly added vehicle data at least includes: newly added vehicle parameter data, preferred charging data corresponding to the newly added vehicle owner, and newly added historical charging data. The newly added vehicle parameter data refers to the basic information of the vehicle, including vehicle model, license plate number, etc., in order to record the vehicle and determine the charging power within a reasonable range for it. The preferred charging data corresponding to the owner of the newly added vehicle refers to the owner's preference settings for charging method, time, etc., so that the system can better meet the owner's needs when the vehicle needs to be charged. In addition, the newly added historical charging data refers to the charging records of the newly added vehicle in the past, including charging time, charging amount, charging method and other information, which can help the system better understand the charging habits and needs of the vehicle.

[0037] By adding new vehicle data, the system can better manage and optimize the vehicle's charging needs, improve charging efficiency and user experience. For example, the system can arrange charging plans for vehicles in advance based on the owner's preferred charging data to avoid the shortage of charging points during peak hours. At the same time, the system can also analyze the vehicle's charging habits based on historical charging data and provide personalized charging suggestions for car owners. This can not only improve user satisfaction, but also increase the utilization rate of charging facilities and maximize the use of resources.

[0038] According to the newly added vehicle data and the associated features, the charging power allocated to the newly added vehicle is determined, wherein the associated features are involved, and the associated features are associated features that represent the relationship between the charging power and the vehicle data. Because the charging power is usually affected by multiple factors such as the vehicle model, battery capacity, and charging pile type, these factors can be used as associated features. By analyzing the association between the charging power and the vehicle data, it can help to better optimize the design and use of the charging equipment, improve the charging efficiency, extend the battery life, and reduce the charging time. Factors such as the user's charging habits included in the vehicle data can better construct a more comprehensive associated feature, so as to better understand the relationship between the charging power and the vehicle data. In this way, the charging strategy for the newly added vehicle can be determined without coordinating the global management strategy, and the charging strategy can also save the user's charging cost and maximize the charging power of the electric vehicle to a certain extent.

[0039] As an optional embodiment, before determining the charging power allocated to the newly added vehicle based on the newly added vehicle data and associated features, it also includes: obtaining sample vehicle data corresponding to multiple sample electric vehicles that have been charged at a predetermined charging station, wherein the sample vehicle data at least includes: sample vehicle parameter data, preferred charging data corresponding to the sample vehicle owner, and sample historical charging data; inputting the sample charging powers and sample vehicle data corresponding to the multiple sample electric vehicles into a neural network model for feature extraction to obtain associated features representing the relationship between the charging power and the vehicle data.

[0040] In this embodiment, the part of determining the associated features is explained, that is, how to determine the associated features, and obtain the sample vehicle data corresponding to multiple sample electric vehicles that have been charged at a predetermined charging station, wherein the sample vehicle data at least includes: sample vehicle parameter data, preferred charging data corresponding to the owner of the sample vehicle, and sample historical charging data. The sample charging power and sample vehicle data corresponding to the multiple sample electric vehicles are input into the neural network model for feature extraction to obtain the associated features representing the relationship between the charging power and the vehicle data. That is, the data of multiple electric vehicles when charging at a predetermined charging station can be collected in advance, including vehicle parameters, owner preferred charging data and historical charging data, and then these data are input into the neural network model for feature extraction to find the associated features between the charging power and the vehicle data. In this way, the charging characteristics of different vehicles can be revealed, and a reference basis can be provided for optimizing the management and service of charging stations. Among them, the neural network model can be a model determined based on different neural network structures, such as a convolutional neural network (CNN) or a recurrent neural network (RNN), and how to learn the complex relationship between charging power and vehicle data by training the neural network. The benefit of this method is that the charging service can be personalized and optimized according to the vehicle characteristics and charging behavior, and the charging efficiency and user satisfaction can be improved. Through deep learning technology, we can better understand the vehicle's charging needs, provide more accurate prediction and decision support for the intelligent charging management system, and thus improve the overall charging experience.

[0041] As an optional embodiment, in the case where the charging powers corresponding to multiple electric vehicles are included in the power grid charging strategy, after determining the newly added vehicles in the scheduled charging station within the predetermined time period, it also includes: when the number of newly added vehicles is greater than a predetermined threshold, updating the dynamic spatial charging model of the scheduled charging station to obtain an updated spatial charging model; based on the updated spatial charging model, determining the update objective function and update constraints: solving the update objective function under the update constraints to obtain an updated power grid charging strategy, wherein the updated power grid charging strategy includes the charging strategy corresponding to the newly added vehicles.

[0042] In this embodiment, it is explained that after solving the objective function under the constraint conditions and obtaining the grid charging strategy, the charging behavior of the newly entered vehicles in the predetermined charging station is also considered. When the grid charging strategy includes the charging powers corresponding to multiple electric vehicles, the newly added vehicles in the predetermined charging station within the predetermined time period can be determined, and the way to allocate charging power to the newly added vehicles can be determined according to the number of newly added vehicles. Among them, when the number of newly added vehicles is less than the predetermined threshold, a separate allocation can be made, and when the number of newly added vehicles is greater than or equal to the predetermined threshold, a global judgment and allocation is made. In this embodiment, the operation steps when the number of newly added vehicles is greater than or equal to the predetermined threshold are explained.

[0043] When the number of newly added vehicles is greater than or equal to the predetermined threshold, the dynamic spatial charging model of the scheduled charging station is directly updated to obtain an updated spatial charging model, that is, the parameters in the original dynamic spatial model are updated to obtain an updated spatial charging model. Then, based on the updated spatial charging model, the updated objective function and the updated constraint conditions are determined, that is, some parameters in the original function are updated to make it applicable to the current scheduled charging station. By solving the updated objective function under the updated constraint conditions, an updated power grid charging strategy including the charging strategy corresponding to the newly added vehicles is obtained. Among them, since the updated function is still a function that aims to minimize the charging cost of electric vehicle users and maximize the charging amount of electric vehicles, the charging cost and the charging amount can be balanced. Because it is specifically constructed according to the dynamic spatial charging model of the scheduled charging station, the accuracy of the constructed objective function and constraint conditions can be guaranteed, thereby solving the technical problem that the determined power grid charging strategy is inaccurate when determining the power grid charging strategy that balances the charging cost and the charging amount in the related technology. Moreover, when there are many new vehicles at the scheduled charging station, an overall regulation is carried out, so that the determined power grid charging strategy can be better adapted to each vehicle and improve the user's charging experience.

[0044] As an optional embodiment, a dynamic spatial charging model of a predetermined charging station is established, including: obtaining full vehicle data of vehicles in the predetermined charging station and charging station parameters of the predetermined charging station; and establishing a dynamic spatial charging model of the predetermined charging station based on the full vehicle data and the charging station parameters.

[0045] In this embodiment, the process of establishing a dynamic spatial charging model for a scheduled charging station is described. The dynamic spatial charging model refers to a dynamic scheduling and optimization of charging services at a charging station by comprehensively analyzing and modeling factors such as vehicle charging demand, charging equipment conditions, and charging station capacity based on the full vehicle data of the vehicles in the scheduled charging station. Through this model, the charging resources of the charging station can be effectively managed and utilized, the charging efficiency and service quality of the charging station can be improved, and the power consumption pressure of the charging station can be effectively alleviated, and the utilization rate of the charging equipment can be improved. When establishing a dynamic spatial charging model for a scheduled charging station, it is first necessary to obtain the full vehicle data of the vehicles in the scheduled charging station, including information such as vehicle type, charging demand period, and charging frequency. At the same time, it is also necessary to understand the charging station parameters of the scheduled charging station, including the number of charging piles, charging power, and charging station capacity. Based on the full vehicle data and charging station parameters, a dynamic spatial charging model for a scheduled charging station can be established, and the reasonable allocation and scheduling of charging resources at the charging station can be achieved by predicting and optimizing the charging demand of the vehicle. By simulating the charging demand and charging equipment utilization in different scenarios, reasonable charging strategies can be formulated for charging stations to improve the overall efficiency and service level of charging stations.

[0046] As an optional embodiment, determining a charging mode for an electric vehicle includes: determining the time required to reach the expected power and the expected price based on the expected power when the vehicle leaves a predetermined charging station, the connected power when the vehicle connects to the predetermined charging station, the rated capacity of the vehicle battery, and the charging power corresponding to a plurality of candidate charging modes, wherein the plurality of candidate charging modes include: a fast charging mode, a slow charging mode that does not comply with grid scheduling, and a slow charging mode that complies with grid scheduling; determining the charging mode for the electric vehicle from a plurality of candidate charging modes based on the time required to reach the expected power and the expected price.

[0047] In this embodiment, the process of determining the charging mode is described. The charging mode of an electric vehicle is very important to the user because different charging modes affect the charging time and cost. When determining the charging mode, the expected power when the vehicle leaves the predetermined charging station and the rated capacity of the on-board battery, as well as the access power when accessing the charging station, can be considered. At the same time, the charging power of different charging modes can also be considered, including fast charging mode, slow charging mode that does not obey the grid dispatch, and slow charging mode that obeys the grid dispatch. By comparing the time required for different charging modes to reach the expected power and the expected price, users can choose the charging mode that best suits their needs. For example, if the user needs to charge quickly and is willing to pay a higher fee, then the fast charging mode may be the best choice. If the user can accept a longer charging time and wants to save money, then the slow charging mode may be more suitable. Determining the most suitable charging mode helps to optimize charging efficiency and save costs, while also reducing the load impact on the power grid. Moreover, this embodiment also provides a mode that obeys the grid dispatch and a mode that does not obey the grid dispatch, which can better balance the overall situation of the reserved charging station and the user's wishes to achieve the effect of weighing efficiency and preference. In addition, by in-depth understanding of the characteristics and advantages and disadvantages of different charging modes, the charging behavior of electric vehicles can be better managed, the user experience can be improved and costs can be saved.

[0048] As an optional embodiment, a first sub-function is constructed based on the time period electricity price, the charging powers corresponding to multiple candidate charging modes, and the charging electricity prices corresponding to multiple candidate charging modes, and a second sub-function is determined based on the average power consumption of the electric vehicle in driving state and the charging power of the electric vehicle; and an objective function is determined based on the first sub-function and the second sub-function.

[0049] In this embodiment, the process of determining the objective function is described, wherein the first sub-function is used to determine the charging power and charging electricity price under each charging mode according to the time period electricity price and different charging modes, so as to select the most economical and most suitable charging mode in different time periods. The second sub-function is used to determine the charging time according to the average power consumption and charging power of the electric vehicle in the driving state, so as to ensure that the maximum load bearing capacity of the electric vehicle will not be exceeded during the charging process, and the charging efficiency can be maximized. The objective function is a function obtained by comprehensively considering the minimization of the user's charging cost and the maximization of the charging amount of the electric vehicle on the basis of the first sub-function and the second sub-function, so as to achieve the economical and efficient management of the charging process of the electric vehicle. This optimization model based on the time period electricity price and charging power can help electric vehicle users choose the most economical charging mode in different time periods, while maximizing the charging efficiency of the electric vehicle and reducing the charging cost. By reasonably arranging the charging time and power, it can not only save the user's charging cost, but also effectively balance the grid load and promote the popularization and sustainable development of electric vehicles.

[0050] Based on the above embodiments and optional embodiments, an optional implementation is provided, which is described in detail below.

[0051] A method for determining a power grid charging strategy is provided in an optional embodiment of the present invention, which involves a data-physical joint-driven electric vehicle cluster aggregation modeling method, which can solve the technical problem of inaccurate power grid charging strategy determined in the related technology when determining the power grid charging strategy for balancing charging cost and charging power, and can also solve the problems of large volatility and strong randomness of electric vehicle load.

[0052] The general method provided by the optional embodiment of the present invention includes:

[0053] Implement a dynamic spatial charging model for electric vehicle loads;

[0054] Establish an electric vehicle load optimization model that meets user needs;

[0055] The K-Shape aggregation algorithm combined with long short-term memory neural network is used to effectively aggregate the electric vehicle load obtained by the data-physics fusion driving model.

[0056] The optional implementation mode of the present invention is implemented by adopting the following technical solutions:

[0057] A. By modeling the single-machine mechanism of electric vehicles, the deterministic and linear parts are expressed using physical drive methods.

[0058] B. Use data-driven methods to supplement the non-deterministic and nonlinear parts. By effectively combining knowledge-driven and data-driven modeling, the single-machine model is further aggregated.

[0059] C. Combine the shape aggregation of the K-shape method and the feature extraction capability of the long short-term memory network LSTM to optimize the aggregation process of electric vehicle loads and improve the aggregation accuracy of electric vehicle loads in various typical scenarios.

[0060] D. Based on the aggregated multiple stand-alone electric vehicle models, similar models can be summarized and organized to establish a dynamic spatial charging model for electric vehicle loads (the same as the dynamic spatial charging model for the above-mentioned predetermined charging station).

[0061] E. Based on the dynamic space charging model, construct an objective function and constraints for determining the electric vehicle charging strategy, wherein the objective function aims to minimize the charging cost of electric vehicle users and maximize the charging amount of electric vehicles, and the constraints include battery capacity constraints, battery remaining power constraints, user demand constraints on battery SOC, and charging electricity price constraints during parking:

[0062] F. Solve the objective function under the constraints to obtain a grid charging strategy.

[0063] The step A specifically comprises the following steps:

[0064] A1. Construct a spatial charging model for electric vehicle loads and determine the charging status of electric vehicle batteries.

[0065] A2. Considering the data set samples of electric vehicle serial number, start driving time, end driving time, vehicle driving distance, electric vehicle access to the grid, vehicle charging status and battery charge status, the difference between electric vehicle access to the grid and charging status is analyzed.

[0066] The step C specifically comprises the following steps:

[0067] C1. Data preprocessing: Standardize the charging load of electric vehicles.

[0068] C2. Feature extraction. A long short-term memory neural network model is established, and the long short-term memory neural network is used to extract features and generate a feature vector of the electric vehicle load.

[0069] C3. Use K-shape algorithm to aggregate the electric vehicle charging load feature vector.

[0070] The step E specifically comprises the following steps:

[0071] E1. Establish an electric vehicle load optimization model that meets user needs. The objective function is to minimize the charging cost of electric vehicle users and maximize the charging capacity of electric vehicles.

[0072] E2. Constraints include the battery capacity, the remaining battery power, vehicle status constraints, user demand for battery SOC, and charging electricity price during parking.

[0073] Specifically, the method provided by the present invention comprises the following steps:

[0074] Step 1: In a specific embodiment of the present invention, a single-machine mechanism model is performed on the electric vehicle, and the data items include: the electric vehicle serial number, the start driving time, the end driving time, the vehicle driving distance, the state of the electric vehicle connected to the power grid, the vehicle charging state and the battery charge state;

[0075] Step 11: The electric vehicle battery charging state is represented by:

[0076] SOC e (t) = SOC e (t-1)+ηP e Δt

[0077] Among them, SOC e (t) and SOC e (t-1) is the charge state of the electric vehicle battery at time t and t-1 respectively; η is the charging efficiency of the electric vehicle; P e is the charging power of the electric vehicle.

[0078] Step 12: In a specific implementation case of the present invention, there is a difference between the electric vehicle's access to the grid and its charging state, that is, the electric vehicle is not necessarily being charged when it is connected to the grid. Its decision variable is expressed as follows: when the electric vehicle's access to the grid state is 1, its charging state can be 0 or 1.

[0079] The user's choice of charging mode can be determined by the length of time the electric vehicle stays, so the function of the charging selection range can be expressed as follows:

[0080]

[0081] Among them, t c is the charging time of vehicle c, is the time it takes for vehicle c to reach the desired SOC by fast charging, is the time it takes for vehicle c to reach SOC by slow charging, a, b, c represent the user’s selection range under each condition, F, S, OS represent the fast charging mode, the slow charging mode that does not obey the grid dispatch, and the slow charging mode that obeys the grid dispatch, respectively.

[0082] The formula details the relationship between the charging time of electric vehicle c in various scenarios and the user's charging selection range. When the charging time of electric vehicle c does not exceed the time required for fast charging to reach the desired SOC, the user will only choose to use the fast charging mode; if the charging time of electric vehicle c is between the time required for fast charging to reach the desired SOC and the time required for slow charging to reach the desired SOC, the user can choose between the two modes of fast charging and slow charging that does not comply with the grid dispatch; and when the charging time of electric vehicle c exceeds the time required for slow charging to reach the desired SOC, the user can choose between the three modes of fast charging, slow charging that does not comply with the grid dispatch, and slow charging that complies with the grid dispatch.

[0083] The time required for an electric vehicle c to choose fast charging or slow charging to reach the desired battery state of charge (SOC) is affected by the remaining battery power of the vehicle and the charging power. The specific expression is as follows:

[0084]

[0085] in, Indicates the preset SOC when vehicle c is disconnected from charging, SOC c is the SOC of vehicle c when it is connected to the grid, is the rated capacity of the vehicle battery, P f and P s Respectively represent the charging power in fast charging mode and slow charging mode.

[0086] Within the above range of electric vehicle charging options, electric vehicle users will choose the charging mode based on their economic preferences.

[0087] Step 2: Based on the single-machine modeling, a dynamic spatial charging model of the electric vehicle load is established, wherein the dynamic spatial charging model includes multiple data items, including: electric vehicle serial number, start driving time, end driving time, vehicle driving distance, electric vehicle access to the grid, vehicle charging status and battery charge status;

[0088] It should be noted that the above formulas may be different for different types of electric vehicles when modeling stand-alone models. There may be slight differences. After modeling based on the stand-alone model, the same type can be aggregated into one category for dynamic space charging modeling, thereby saving the computational effort of building a dynamic space charging model.

[0089] Step 3: Construct an objective function and constraints that satisfy the interests of users. The objective function is to minimize the charging cost of electric vehicle users and maximize the charging capacity of electric vehicles. The constraints include the capacity of the battery, the remaining power of the battery, the vehicle state constraint, the user's demand for battery SOC, and the charging price during parking:

[0090] Step 31: The objective function is expressed as:

[0091]

[0092] Among them, Q c (t) is the charging cost of vehicle c in time period t, is the additional mileage (km) obtained by vehicle c after completing the g-th trip through charging.

[0093] This example only covers the case where the power grid charges electric vehicles, so the electricity cost of electric vehicle users is related to the charging power in time period t and the unit price of electricity purchased in time period t. It is worth noting that under the constraints of combining orderly charging with electricity prices, this example assumes that the electricity price that follows the grid dispatch is not equal to the electricity price that does not follow the grid dispatch.

[0094]

[0095] q ch (t) = v1q F (t)+v2q S (t)+v3q OS (t)

[0096] Among them, q ch (t) represents the charging electricity price during period t, represents the charging power of vehicle c, q F (t) represents the fast charging mode electricity price during period t, q S (t) represents the slow charging mode electricity price that does not comply with the grid dispatch during period t, q OS (t) represents the slow charging mode electricity price in period t that complies with the grid dispatch, and v1, v2 and v3 represent binary decision variables respectively.

[0097] The amount of electricity that can be charged after the g-th segment of the trip is related to the charging time and charging power. The additional mileage obtained by charging after the trip is related to the charging power and the average power consumption of the vehicle. The specific calculation formula is as follows:

[0098]

[0099] in, represents the average power consumption of vehicle c in normal driving mode, represents the time period when vehicle c completes the g-th trip. Indicates the time period in which vehicle c is located when the g+1th trip starts.

[0100]

[0101] Among them, x c(t) represents the decision variable (0 or 1), when x c (t) = 1 means that vehicle c is in charging state at time t. c (t)=0 means that vehicle c is not charged at time t.

[0102] Step 32: Constraints include:

[0103] Combined with the objective function, the proposed orderly charging strategy for electric vehicles also takes into account the constraints of battery capacity, whether the vehicle is connected to the power grid, and the user's demand for battery SOC at the end of charging.

[0104] (1) Due to the limitation of the maximum capacity of the on-board battery, the sum of the charging power obtained by the electric vehicle during charging and the remaining power of the battery at the beginning of charging shall not exceed the upper capacity limit of the battery.

[0105]

[0106] Among them, L c represents the rated cruising range of vehicle c, L c ' ,g Indicates the mileage supported by the remaining power of vehicle c at the end of the g-th segment.

[0107] L c ' ,g The value is the battery support mileage of vehicle c at the start minus the mileage of the vehicle's journey g. There is a correlation between the remaining mileage of vehicle c at the start of the journey and the remaining mileage of the vehicle at the end of journey k and the amount of electricity that can be charged during parking. This relationship can be expressed by the following mathematical formula:

[0108]

[0109] Among them, K c,g is the distance traveled by vehicle c in the g-th segment.

[0110] In the formula, it is assumed that each electric vehicle is fully charged at the beginning of the first trip.

[0111] (2) The focus of this patent is on pure electric vehicles, which are powered by batteries. When the battery is exhausted, the vehicle will not be able to travel additional distances, so the remaining battery power cannot be negative.

[0112]

[0113] (3) Assume that at the end of each trip, the electric vehicle user directly connects the vehicle to the grid and disconnects the vehicle from the grid at the beginning of the next trip. The vehicle can only be charged when connected to the grid. Therefore, the vehicle state constraint can be expressed as:

[0114]

[0115] Wherein, the formula indicates that vehicle c cannot be charged during the g-th segment. and The parameters are determined by the distance the electric vehicle travels on the road.

[0116] (4) Before leaving the charging station, the user needs to ensure that the battery charge at the end of charging reaches the battery SOC requirement. This condition can be expressed as:

[0117]

[0118] (5) When charging during parking, the user can only select one charging mode, so the corresponding electricity price is also limited to one of the selected charging modes.

[0119] v1+v2+v3=1

[0120] Step 4: Solve the objective function under the constraints to obtain the grid charging strategy.

[0121] It should be noted that in the above steps, an aggregate analysis of the electric vehicle charging load can be performed.

[0122] Based on the above model, the electric vehicle charging load can be aggregated using the K-Shape aggregation + long short-term memory neural network method. The detailed steps are as follows:

[0123] Step S1: Data preprocessing. Set the electric vehicle charging load x = {x1, x2, ..., x T} is standardized, and the expression is as follows:

[0124]

[0125] Where μ is the mean value of EV charging load and σ is the standard deviation.

[0126] Step S2: Feature extraction: A long short-term memory neural network model is established, and the long short-term memory neural network is used to extract features and generate a feature vector of the electric vehicle load.

[0127] ① The expression of long short-term memory neural network is as follows:

[0128] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0129] i t=σ(W i ·[h t-1 ,x t ]+b i )

[0130]

[0131] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0132]

[0133] Among them, * represents the element-by-element multiplication operation; [h t-1 ,x t ] represents the vector h t-1 and x t ; σ is the Sigmoid activation function, which maps the value to the interval [0,1]; tanh is the hyperbolic tangent activation function, which maps the value to the interval [-1,1]; W f ,W i ,W C ,W o is the weight matrix; b f ,b i ,b C ,b o is the bias vector.

[0134] ②Construct a long short-term memory neural network model.

[0135] ③ The LSTM neural network model is trained using the electric vehicle charging load calculated by the data-physics joint model. The model parameters are updated by using the gradient descent method until the model converges.

[0136] ④The output of the long short-term memory neural network model is used as the feature vector of the electric vehicle charging load for subsequent aggregation analysis.

[0137] Step S3: Use K-shape algorithm to aggregate the electric vehicle charging load feature vector. Assume that there are N electric vehicle load sequence feature vectors F = [f1, f2, ..., f N ], the goal of K-shape is to minimize the aggregate variance within the shape basis distance (SBD).

[0138] Initialization. Randomly select K electric vehicle load sequences as the initial centroids.

[0139] ②For each electric vehicle charging load sequence, the shape basis distance is used to calculate its similarity with all centroids and assign it to the most similar centroid. The expression of the shape basis distance is as follows:

[0140]

[0141] ③ Update parameters. For each electric vehicle charging load aggregation cluster, the K-Shape algorithm finds the aggregation center C = [c1, c2, ..., c K ] and aggregate allocation A, minimizing the objective function:

[0142]

[0143] ④ Use internal and external evaluation indicators to evaluate the aggregation results. The internal indicators use the silhouette coefficient and Davies-Bouldin index, and the external evaluation indicator uses purity.

[0144] Silhouette Coefficient:

[0145]

[0146] Where a(i) is the average distance from data point i to other points in its cluster, and b(i) is the average distance from data point i to other points in its nearest cluster. The value range of the silhouette coefficient is between [-1, 1], and a value close to 1 indicates a good cluster.

[0147] Aggregate sum of squares:

[0148]

[0149] Among them, μ i is the center of cluster j, x j is the data point, and C is the set of all aggregation centers. The smaller the intra-class sum of squares, the more compact the aggregation.

[0150] purity:

[0151]

[0152] Where N is the total number of data points, c i is the set of points in cluster i, t j is the set of points under label j. The higher the purity, the better the aggregation effect.

[0153] ⑤If the internal and external evaluation indicators of the centroid meet the conditions, the algorithm terminates. If not, repeat ① to ④.

[0154] Through the aggregation analysis of electric vehicle charging load, the relationship between electric vehicle charging load or charging power and vehicle data can be analyzed, so as to guide the allocation of charging strategies for subsequent new vehicles. And through aggregation processing, it can also provide guidance when the single machine modeling is aggregated into a global dynamic spatial charging model.

[0155] Through the above optional implementation, at least the following beneficial effects can be achieved:

[0156] (1) For electric vehicle cluster loads, a single-machine model was used, and then a dynamic spatial charging model driven by data physics fusion was obtained through data fusion correction. This process not only reduces the amount of calculation, but also improves the accuracy of the model;

[0157] (2) By extracting the characteristics of electric vehicle loads and adopting the classification and aggregation method, the electric vehicle load aggregation modeling is completed to meet the needs of different scenarios;

[0158] (3) It solves the technical problem of inaccurate grid charging strategy when determining the grid charging strategy that balances charging cost and charging power in related technologies, and can also solve the problems of large fluctuation and strong randomness of electric vehicle load.

[0159] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0160] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0161] Example 2

[0162] According to an embodiment of the present invention, a device for implementing the above-mentioned method for determining a power grid charging strategy is also provided. Figure 2is a structural block diagram of a device for determining a power grid charging strategy according to an embodiment of the present invention. Figure 2 As shown, the device includes: an establishing module 202, a constructing module 204 and a determining module 206. The device is described in detail below.

[0163] Establishing module 202, for establishing a dynamic spatial charging model of a predetermined charging station, wherein the dynamic spatial charging model includes a plurality of data items, the plurality of data items including: an electric vehicle serial number, a state of the electric vehicle connected to a power grid, a charging mode of the electric vehicle, and a battery state of charge of the electric vehicle;

[0164] The construction module 204 is connected to the establishment module 202 and is used to construct an objective function and constraint conditions for determining the electric vehicle charging strategy based on the dynamic space charging model, wherein the objective function aims to minimize the charging cost of the electric vehicle user and maximize the charging amount of the electric vehicle, and the constraint conditions include battery capacity constraint, battery remaining power constraint, user demand constraint for battery SOC and charging electricity price constraint during parking:

[0165] The determination module 206 is connected to the construction module 204 and is used to solve the objective function under the constraint conditions to obtain the grid charging strategy.

[0166] It should be noted here that the above-mentioned establishment module 202, construction module 204 and determination module 206 correspond to steps S102 to S106 in the method for implementing the grid charging strategy determination method, and the instances and application scenarios implemented by the multiple modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0167] Example 3

[0168] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor is configured to execute instructions to implement any of the above-mentioned methods for determining a grid charging strategy.

[0169] Example 4

[0170] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining a power grid charging strategy.

[0171] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0172] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0173] 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 schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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.

[0174] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0175] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0176] 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 computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned 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 codes.

[0177] 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 principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for determining a power grid charging strategy, characterized in that: include: Establishing a dynamic spatial charging model for a predetermined charging station, wherein the dynamic spatial charging model includes a plurality of data items, the plurality of data items including: an electric vehicle serial number, a state of access to a power grid of the electric vehicle, a charging mode of the electric vehicle, and a battery state of charge of the electric vehicle; According to the dynamic space charging model, an objective function and constraint conditions for determining the electric vehicle charging strategy are constructed, wherein the objective function aims to minimize the charging cost of the electric vehicle user and maximize the charging amount of the electric vehicle, and the constraint conditions include battery capacity constraint, battery remaining power constraint, user demand constraint for battery SOC and charging electricity price constraint during parking; The objective function under the constraint conditions is solved to obtain a grid charging strategy.

2. The method according to claim 1, characterized in that After solving the objective function under the constraint conditions and obtaining the grid charging strategy, the method further includes: In the case where the grid charging strategy includes charging powers corresponding to a plurality of electric vehicles, determining a new vehicle added to the predetermined charging station within a predetermined time period; When the number of the newly added vehicles is less than a predetermined threshold, acquiring newly added vehicle data corresponding to the newly added vehicles, wherein the newly added vehicle data at least includes: newly added vehicle parameter data, preferred charging data corresponding to the newly added vehicle owner, and newly added historical charging data; The charging power allocated to the newly added vehicle is determined based on the newly added vehicle data and the associated feature, wherein the associated feature is an associated feature representing a relationship between the charging power and the vehicle data.

3. The method according to claim 2, characterized in that Before determining the charging power allocated to the newly added vehicle according to the newly added vehicle data and the associated features, the method further includes: Acquire sample vehicle data corresponding to a plurality of sample electric vehicles that have been charged at the predetermined charging station, wherein the sample vehicle data at least includes: sample vehicle parameter data, preferred charging data corresponding to the owner of the sample vehicle, and sample historical charging data; The sample charging powers and sample vehicle data respectively corresponding to the multiple sample electric vehicles are input into the neural network model for feature extraction to obtain the correlation features representing the relationship between the charging power and the vehicle data.

4. The method according to claim 2, characterized in that: In the case where the charging powers respectively corresponding to the plurality of electric vehicles included in the grid charging strategy are determined, after a new vehicle is added to the predetermined charging station within a predetermined time period, the method further includes: When the number of the newly added vehicles is greater than a predetermined threshold, updating the dynamic spatial charging model of the predetermined charging station to obtain an updated spatial charging model; According to the updated spatial charging model, the updated objective function and updated constraints are determined: The update objective function under the update constraint condition is solved to obtain an updated power grid charging strategy, wherein the updated power grid charging strategy includes a charging strategy corresponding to the newly added vehicle.

5. The method according to claim 1, characterized in that Build a dynamic spatial charging model for scheduled charging stations, including: Acquiring full vehicle data of vehicles in the predetermined charging station and charging station parameters of the predetermined charging station; A dynamic spatial charging model of the predetermined charging station is established based on the full vehicle data and the charging station parameters.

6. The method according to claim 1, characterized in that Determine the charging mode of the electric vehicle, including: Determine the time required to reach the expected power and the expected price based on the expected power when the vehicle leaves the predetermined charging station, the access power when the vehicle accesses the predetermined charging station, the rated capacity of the vehicle battery, and the charging power corresponding to multiple candidate charging modes, wherein the multiple candidate charging modes include: a fast charging mode, a slow charging mode that does not comply with grid scheduling, and a slow charging mode that complies with grid scheduling; A charging mode for the electric vehicle is determined from a plurality of candidate charging modes according to the time required for the expected amount of electricity and the expected price.

7. The method according to any one of claims 1 to 6, characterized in that: include: According to the time period electricity price, the charging powers corresponding to the multiple candidate charging modes, and the charging electricity prices corresponding to the multiple candidate charging modes, a first sub-function is constructed, and according to the average power consumption of the electric vehicle in the driving state and the charging power of the electric vehicle, a second sub-function is determined; The objective function is determined according to the first sub-function and the second sub-function.

8. A method for determining a power grid charging strategy, characterized in that: include: An establishment module is used to establish a dynamic spatial charging model of a predetermined charging station, wherein the dynamic spatial charging model includes a plurality of data items, the plurality of data items including: an electric vehicle serial number, a state of access to a power grid of the electric vehicle, a charging mode of the electric vehicle, and a battery state of charge of the electric vehicle; A construction module, for constructing an objective function and constraint conditions for determining an electric vehicle charging strategy based on the dynamic space charging model, wherein the objective function aims to minimize the charging cost of electric vehicle users and maximize the charging amount of electric vehicles, and the constraint conditions include battery capacity constraint, battery remaining power constraint, user demand constraint for battery SOC and charging electricity price constraint during parking; The determination module is used to solve the objective function under the constraint conditions to obtain a power grid charging strategy.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining a grid charging strategy according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining a grid charging strategy according to any one of claims 1 to 7.

Images