Charging performance evaluation system and method for electric vehicle charging station

Abstract

The invention discloses a charging performance evaluation system and method for an electric vehicle charging station. The system comprises a client and a server. The client is arranged on an electric vehicle, and a first data set is stored on the client; a second data set is stored on the server, the server is in communication connection with a plurality of charging devices of the charging station, and the charging devices are configured to be in communication connection with the client when the electric vehicle is charged; the server is configured to: verify that the first data set and the second data set are matched; acquiring real-time charging data of each electric vehicle in the charging station; processing to obtain charging data information; performing charging performance evaluation based on the charging data information through a charging performance evaluation model, and outputting a charging performance evaluation result; wherein the first data set and the second data set are historical charging data information of the electric vehicle. According to the invention, the charging process of the electric vehicle can be deeply monitored and evaluated, and in addition, through encryption transmission of data, the security and privacy of data transmission can be improved.

Description

Technical Field

[0001] This invention relates to the field of power technology, and in particular to a charging performance evaluation system and method for electric vehicle charging stations. Background Technology

[0002] With the rapid growth of the electric vehicle market, the demand for efficient and reliable charging solutions is increasing. The charging performance of electric vehicles not only affects the user's charging experience but also has a significant impact on the construction and operation of charging infrastructure.

[0003] Chinese invention patent CN117933777A discloses a method for evaluating the resource utilization rate of electric vehicle charging stations. This method includes steps such as establishing a resource utilization rate evaluation index system, sample selection and processing, feature index extraction, introduction of a nonlinear regression model, and calculation of the decision boundary for high-utilization-rate samples.

[0004] The aforementioned patents can only judge and evaluate the operation of charging stations based on surrounding user data, but lack the ability to deeply monitor and evaluate the charging process, and cannot provide real-time feedback on charging efficiency, charging mode adaptability, and battery health. Furthermore, security is also a significant challenge in the electric vehicle charging field, especially in the transmission and storage of data; ensuring the security and privacy of charging data is a pressing issue that needs to be addressed.

[0005] It should be noted that the above content falls within the inventor's cognitive technology scope and does not necessarily constitute prior art. Summary of the Invention

[0006] The purpose of this invention is to provide a charging performance evaluation system, method, electronic device, and computer-readable storage medium for electric vehicle charging stations, which can perform in-depth monitoring and evaluation of the charging process of electric vehicles. In addition, the encrypted transmission of data helps to improve the security and privacy of data transmission.

[0007] To achieve the above objectives, the present invention provides a charging performance evaluation system for electric vehicle charging stations, including a client and a server;

[0008] The client is installed on the electric vehicle and stores the first dataset.

[0009] The server stores a second dataset of the electric vehicle. The server is communicatively connected to several charging devices at at least one charging station. The charging devices are configured to communicate with the client when charging the electric vehicle.

[0010] The server is configured as follows:

[0011] Obtain the first dataset to verify that it matches the first dataset and the second dataset;

[0012] Obtain real-time charging data for each of the electric vehicles in the charging station;

[0013] The real-time charging data is preprocessed to obtain charging data information and stored in the server;

[0014] The charging performance is evaluated based on the charging data using a charging performance evaluation model, and the charging performance evaluation results are output.

[0015] The first dataset and the second dataset are historical charging data of the electric vehicle, and the charging performance evaluation model is an artificial intelligence model.

[0016] Furthermore, the charging performance evaluation model is a neural network model, which is trained based on the historical charging data of the electric vehicle.

[0017] Furthermore, the system also includes a blockchain for storing charging data information uploaded from the server.

[0018] Further, the verification matching of the first dataset and the second dataset includes:

[0019] Obtain the encryption key generated by the client;

[0020] The first charging data information is obtained from the second dataset based on the index of the encryption key;

[0021] The second charging data information is obtained from the first dataset based on the index of the first charging data information;

[0022] The first charging data information is hashed and encrypted to obtain a first hash value, and the second charging data information is hashed and encrypted to obtain a second hash value;

[0023] The first hash value and the second hash value are matched and verified.

[0024] Furthermore, the charging data information includes one or more of the following parameters: charging electrical parameters, charging mode information, charging time parameters, battery status information, environmental parameters, and charging station information.

[0025] Furthermore, charging performance is evaluated based on the charging data information using a charging performance evaluation model, including:

[0026] Calculate the charging performance score for multiple charging rounds within a statistical period and the weight value corresponding to the charging performance score for each round;

[0027] The rationality score of the power allocation strategy of the charging station is calculated based on the charging performance score and the weight value within the statistical period.

[0028] Furthermore, the relevant factors for calculating the weight value include charging demand, charging time window, charging rate, charging history reliability, and charging frequency.

[0029] To achieve the above objectives, the present invention also provides a method for evaluating the charging performance of an electric vehicle charging station, the method comprising:

[0030] Obtain the first dataset to verify that it matches the first dataset and the second dataset;

[0031] Obtain real-time charging data for each electric vehicle within the charging station;

[0032] The real-time charging data is preprocessed to obtain charging data information and stored in the server;

[0033] The charging performance is evaluated based on the charging data using a charging performance evaluation model, and the charging performance evaluation results are output.

[0034] The client is installed on the electric vehicle, the server is communicatively connected to several charging devices in the charging station, the first dataset and the second dataset are the charging data information of the electric vehicle, the first dataset is stored in the client of the electric vehicle, the second dataset is stored in the server, and the charging performance evaluation model is an artificial intelligence model.

[0035] To achieve the above objectives, the present invention also provides an electronic device, comprising:

[0036] processor;

[0037] A memory in which executable instructions of the processor are stored;

[0038] The processor is configured to perform the charging performance evaluation method as described above by executing the executable instructions.

[0039] To achieve the above objectives, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the charging performance evaluation method as described above.

[0040] In this invention, charging data information is generated by acquiring real-time charging data, and the charging data information is evaluated using an artificial intelligence model to obtain charging performance evaluation results. This allows for in-depth monitoring and evaluation of the electric vehicle charging process. Furthermore, the charging performance evaluation results can identify deficiencies in the current electric vehicle charging strategy. Based on the analysis of historical charging data and the charging performance evaluation model, more optimized charging modes and strategies can be proposed, which is beneficial for improving charging performance, increasing energy utilization efficiency, and reducing charging time. In addition, by verifying and matching the first dataset from the client and the second dataset from the server, the security and integrity of the charging data are ensured, which helps to ensure the accuracy and reliability of the evaluation results. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the architecture of the charging performance evaluation system in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of the neural network of the charging performance evaluation model in an embodiment of the present invention;

[0043] Figure 2 This is a flowchart of the charging performance evaluation method in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of the architecture of an electronic device in an embodiment of the present invention. Detailed Implementation

[0045] To illustrate the technical content, structural features, and effects of the present invention in detail, the following description is provided in conjunction with the embodiments and accompanying drawings.

[0046] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Example 1

[0048] Please see Figures 1 to 2 This invention discloses a charging performance evaluation system for an electric vehicle 30 charging station 40, comprising a client 10 and a server 20. The client 10 is installed on the electric vehicle 30 and stores a first dataset. The server 20 stores a second dataset of the electric vehicle 30 and is communicatively connected to at least one charging device 50 of the charging station 40. The charging devices 50 are configured to communicate with the client 10 when charging the electric vehicle 30.

[0049] Server 20 is configured to: acquire a first dataset to verify a match between the first and second datasets; acquire real-time charging data for each electric vehicle 30 within charging station 40; preprocess the real-time charging data to obtain charging data information and store it in server 20; perform charging performance evaluation based on the charging data information using a charging performance evaluation model and output the charging performance evaluation results.

[0050] Among them, the first dataset and the second dataset are historical charging data of electric vehicle 30, and the charging performance evaluation model is an artificial intelligence model.

[0051] It should be noted that the charging performance evaluation results may include real-time charging performance evaluation results for each electric vehicle 30 during a single charging cycle, single charging performance evaluation results for each charging cycle, and charging performance evaluation results for the power consumption strategy of charging station 40 within a preset period. The datasets used, i.e., the range of charging data information, will also differ for different evaluation results.

[0052] In some embodiments, the charging performance evaluation system includes multiple servers 20, which are connected by a distributed network.

[0053] Specifically, the charging data information includes one or more of the following parameters:

[0054] (1) Electrical parameters, including battery voltage, current, power and energy consumption during charging.

[0055] (2) Charging mode information, including different charging modes used by the electric vehicle 30 during the charging process and the electrical parameters of the charging device 50 in each mode.

[0056] (3) Time parameters, including the timestamps for the start and end of charging, and the duration of each charging mode during the charging process.

[0057] (4) Battery status information, including battery health status and charge status.

[0058] (5) Environmental parameters, including ambient temperature and humidity data during the charging process.

[0059] (6) Information on charging station 40, including the identification information of charging station 40, including geographical location and charging pile number.

[0060] It should be noted that each charging station 40 can be configured with several charging devices 50. The charging station 40 can be a public charging station or a charging system for a private residential parking lot. The charging station 40 provides functions such as connection and access to the public power supply network, power processing, and power distribution. By configuring the power consumption strategy of the charging station 40, it can control and monitor the power supply of the several charging devices 50 connected to it.

[0061] In a specific example, the charging device 50 may be equipped with a charging plug, which connects to the power supply line of the electric vehicle 30 and charges the electric vehicle 30.

[0062] It should be noted that the client 10 is configured on the electric vehicle 30 and can be integrated into the vehicle information system of the electric vehicle 30 to communicate with the vehicle's charging management system (BMS) and other vehicle control units (such as VCU - Vehicle Control Unit).

[0063] Client 10 connects to the main control unit of electric vehicle 30 via an internal vehicle communication network, such as CAN bus or Ethernet, and allows client 10 to receive charging parameter data (such as voltage, current, temperature, etc.) and other relevant vehicle status information from BMS in real time.

[0064] Client 10 includes a microprocessor, a storage module, a communication module, and necessary input and output interfaces. The microprocessor is responsible for executing data acquisition, preprocessing, and encryption algorithms. The storage module is used for temporary storage of acquired data and system operation logs. The communication module supports multiple communication standards (such as Wi-Fi, Bluetooth, 4G / 5G, etc.) for transmitting encrypted data to server 20. The input and output interfaces are used for connecting to other systems in the vehicle and for possible user interaction.

[0065] The software running on client 10 includes a data acquisition program, an encryption module, and a communication protocol stack. The data acquisition program collects charging and other operational data from the vehicle system in real time according to a preset sampling strategy. The encryption module is responsible for encrypting the collected data to ensure data security during transmission. The communication protocol stack supports efficient data exchange with the remote server 20.

[0066] Client 10 supports remote software updates, which helps ensure the continuous optimization and compatibility of the client 10 software environment.

[0067] To facilitate understanding of the present invention, the following illustrative description of the implementation of the connection and interaction between the client 10 and the charging device 50 should not be regarded as a limitation of the present invention.

[0068] After the electric vehicle 30 is connected to the charging device 50 and a physical connection is established, the client 10 begins to connect to the charging device 50 and prepares for data exchange. The process includes:

[0069] (1) Establish a communication connection. The control system of the charging device 50 and the client 10 in the electric vehicle 30 shake hands through the communication line of the charging interface to confirm each other's identity and compatibility.

[0070] (2) Client 10 sends charging request information to charging device 50 through standardized charging communication protocols (such as ISO 15118 or IEC 61851). This request information may include the identity authentication information of electric vehicle 30, charging parameter requirements (such as required power, voltage level, etc.), estimated charging time, etc. This information will become part of the charging data information and will then be uploaded to server 20.

[0071] (3) After receiving and processing the request from the client 10 of the electric vehicle 30, the charging device 50 sends a confirmation message back to the client 10 based on the current status of the charging device 50 and the load of the charging grid. The confirmation message includes the identity information of the charging device 50, the selected charging mode, the charging start command, and the estimated charging end time. After receiving this information, the client 10 confirms it and adjusts the charging control strategy according to the parameters provided by the charging device 50 to start the charging process.

[0072] (4) During the charging process, the client 10 continuously collects and monitors charging data (such as current, voltage, charging time, etc.) and feeds back this charging data and any abnormalities to the charging equipment 50 in real time to ensure the safety and efficiency of the charging process. At the same time, the charging equipment 50 and the charging station 40 also need to adjust the charging strategy according to changes in the power grid status or other external conditions, such as changing the charging rate or temporarily interrupting charging.

[0073] (5) After charging is complete, the client 10 will receive a charging end signal from the charging device 50 and send a confirmation message of charging end to the charging device 50 to complete the final data synchronization. At this time, the client 10 will save the charging data of this charging process to provide a basis for subsequent charging performance evaluation.

[0074] (6) At the same time, the charging data generated in step (5) will also be copied and sent by the charging device 50 to the charging station 40 and then forwarded to the server 20, or directly sent by the charging device 50 to the server 20.

[0075] In some embodiments, the charging performance evaluation model is a neural network model, which is trained based on the historical charging data of the electric vehicle 30.

[0076] Specifically, the charging performance evaluation model includes an input layer 401, multiple hidden layers 402, and an output layer 403; wherein the input layer 401, multiple hidden layers 402, and output layer 403 each include multiple nodes.

[0077] Understandably, when the performance evaluation module trains the evaluation model, or when the charging performance of the charging station 40 is evaluated using the charging performance evaluation model, some or all of the charging data information is input to the input layer 401. The charging data information is preprocessed by the server 20 through the collection of charging data, including data cleaning, normalization, and other steps, to convert it into a standardized data form that the input layer 401 can input.

[0078] The number of nodes n in the input layer 401 can be calculated based on the total charging time U at a set time interval Δt. The total charging time U can be the longest charging time under existing statistics, and the value of Δt can be 5 seconds, 10 seconds, 30 seconds, 60 seconds, etc. Based on the total charging time U, the charging process is divided into n time intervals according to the interval Δt, corresponding to the n nodes of the input layer 401, and n = U / Δt + 1. The value of Δt can be set according to the computing power of the server 20 and the expected accuracy of the evaluation model. This invention does not restrict the values ​​of U, Δt, and n.

[0079] The total charging time U is divided into n time nodes according to a set time interval Δt, and each time node is denoted as t1, t2, ... tt. n Simultaneously, the charging data information at each time point is formed into a multi-dimensional vector, i.e., t1=(a1,b1,c1…), where a1,b1,c1… are the specific values ​​of a charging data item at time t1. The multi-dimensional vector t1,t2,…tn is then input into the corresponding input method at time t1,t2,…tn. n The node at time point is used to make the input for that node.

[0080] Each node in the input layer 401 not only receives charging data information at its own time point, but may also capture the interaction and dependency between parameters through specific data encoding or feature engineering methods, such as embedding layers or feature crossing, which is beneficial to improving the model's evaluation capability and the completeness and comprehensiveness of the evaluation results.

[0081] Specifically, the number of hidden layers 402 inserted between the input layer 401 and the output layer 403 and the number of nodes included in each hidden layer 402 can be appropriately adjusted based on the training amount of the charging evaluation model and the accuracy required by the charging evaluation model, and the present invention does not limit this.

[0082] Specifically, the output layer 403 can output charging performance evaluation results, which may include multiple output results. For example, the output results may be represented as the optimal charging time, optimal charging temperature, optimal charging mode switching time, etc., evaluated by the charging performance evaluation model.

[0083] Specifically, in the charging performance evaluation model, a sigmoid function can be used as the activation function. Of course, various activation functions known in the art can also be used, such as the SiLU (sigmoid linear unit) function, ReLU (modified linear unit) function, Softplus function, ELU (exponential linear unit) function, SQLU (quadratic linear unit) function, etc., and this invention does not limit the use of such functions.

[0084] Specifically, in the charging performance evaluation model, the initial values ​​of the connection weights and biases between nodes can be randomly set. Furthermore, the connection weights and biases can be optimized during the training of the artificial neural network.

[0085] Specifically, the evaluation model can be trained using the backpropagation algorithm; in addition, the connection weights and biases can be optimized by an optimizer while the evaluation model is being trained.

[0086] In specific examples, the SGD (Stochastic Gradient Descent) algorithm can be used as the optimizer. Of course, algorithms such as NAG (Nesterov Accelerated Gradient), momentum algorithm, Nadam algorithm, Adagrad algorithm, RMSProp algorithm, Adadelta algorithm, and Adam algorithm can also be used, and this invention does not limit the scope of these algorithms.

[0087] Specifically, establishing a charging performance evaluation model includes setting up a training set for training the model. The training set partially utilizes charging data information; for example, 70% of all charging data information can be used as the training set.

[0088] Specifically, the training set can be stored in the storage unit of server 20. Furthermore, as charging data from multiple charging stations 40 continuously increases, the training set may grow larger and larger.

[0089] Specifically, the charging performance evaluation system can train sub-models of the charging performance evaluation model separately for each model of electric vehicle 30 and each model of battery, so as to reduce the training computation load of the evaluation model and improve the reliability of the charging performance evaluation model output through distributed data processing.

[0090] In some embodiments, the system further includes a blockchain 60 for storing charging data information uploaded from the server 20. One blockchain 60 can correspond to multiple servers 20, and multiple servers 20 can store and share data in the blockchain 60.

[0091] Specifically, the verification matches the first and second datasets, including:

[0092] (1) Obtain the encryption key generated by client 10.

[0093] The encryption key is an asymmetric encryption key, consisting of a public key Pkey and a private key Skey. When the electric vehicle 30 connects to the charging device 50, the electric vehicle 30 sends the public key Pkey to the charging device 50.

[0094] (2) Obtain the first charging data information from the second dataset based on the index of the encryption key.

[0095] After receiving the public key Pkey provided by the electric vehicle 30, the charging device 50 retrieves one or more required charging data information from the blockchain 60 based on the index of the public key Pkey. The public key Pkey has a unique index identifier Key_id. The server 20 retrieves the first charging data information based on the index identifier Key_id.

[0096] (3) Obtain the second charging data information from the first dataset according to the index of the first charging data information.

[0097] It's understandable that when retrieving the first charging information, the server will simultaneously obtain the index identifier Key_id. Therefore, the index of the first charging data information is consistent with the index of the public key Pkey. Each time information is retrieved, the server verifies the index identifier Key_id, which helps ensure the security of data retrieval.

[0098] (4) Hash the first charging data information to obtain the first hash value, and hash the second charging data information to obtain the second hash value.

[0099] (5) Match and verify the first hash value and the second hash value. By comparing the first hash value and the second hash value, the correctness of the charging data information obtained from Blockchain 60 can be confirmed.

[0100] More specifically, when the electric vehicle 30 is connected to the charging device 50, the server 20 uses the charging device 50 as a medium to exchange data with the electric vehicle 30 using an asymmetric encryption method.

[0101] In some embodiments, charging performance is evaluated based on charging data information using a charging performance evaluation model, including:

[0102] (1) Calculate the charging performance score for multiple charging rounds within a statistical period and the weight value corresponding to the charging performance score for each round.

[0103] Specifically, the formula for calculating the performance score for each charging cycle is as follows:

[0104]

[0105] In the above formula, score is the performance rating for a single charge, F(t) is the total charging time, G(D) is the deviation of the charging mode transition time, H(S) is the smoothness value of the charging mode transition, and η1, η2, and η3 are the weighting coefficients of F(t), G(D), and H(S), respectively. These weighting coefficients can be set according to needs and actual conditions, which will not be elaborated in this invention.

[0106] The calculation method for F(t) is as follows:

[0107]

[0108] In the above formula, t real That is, the total time required to complete this charging process, t pre To evaluate the time predicted by the model to complete the same amount of charging.

[0109] The calculation method for G(D) is as follows:

[0110] ,

[0111] In the above formula, M is the number of charging mode switching during the charging process, Drm is the actual time when the m-th charging mode switch is completed, and Dsm is the ideal time when the m-th charging mode switch is completed.

[0112] The calculation method for H(S) is as follows:

[0113] ,

[0114] In the above formula, M is the number of times the charging mode is switched during the charging process, ΔVm and ΔIm are the changes in voltage and current before and after the m-th charging mode switch, respectively, Δtl is the preset observation window length, and the value of Δtl is set according to the calculation accuracy of the rationality score Sc.

[0115] Specifically, the formula for calculating the weight value is as follows:

[0116]

[0117] Where W is the weight value, W E The ratio of the output energy of electric vehicle 30 during this charge to the average output energy of charging station 40 during each charge within a preset statistical period T is used to calculate the weight based on charging demand.

[0118] W TTo weight the charging time window, different weight values ​​are assigned according to the time period in which charging occurs (peak or off-peak hours). For example, a higher weight is set during peak hours. T Set a lower W value during off-peak hours. T value.

[0119] W R It is calculated based on the weight of the charging rate, by the ratio of the maximum charging rate of the electric vehicle 30 to the maximum charging rate supported by the charging station 40.

[0120] W H The weighting is based on the reliability of charging history and can be determined by the average of the reasonableness scores of the current electric vehicle's charging behavior over the past 30 years.

[0121] W F The weighting is based on charging frequency and can be calculated by the ratio of the number of times the electric vehicle 30 is charged within a preset statistical period T to the total number of times the charging station 40 is charged within the preset statistical period T.

[0122] λ1, λ2, λ3, λ4 and λ5 are W respectively E W T W R W H and W F The corresponding weighting coefficient can be set according to needs and actual conditions, which will not be elaborated upon in this invention.

[0123] (2) Calculate the rationality score of the power allocation strategy of charging station 40 based on the charging performance score and weight value within the statistical period.

[0124] Specifically, the formula for calculating the reasonableness score is as follows:

[0125]

[0126] In the above formula, Sc is the reasonableness score within one period, and score i W is the single reasonableness score for the i-th charging process within an I-cycle. i The weight value for the i-th charging process.

[0127] By calculating the rationality score of a single charge and the rationality score of the power consumption strategy to output the charging performance evaluation results, the charging strategy of electric vehicles can be adjusted in real time or a better charging strategy can be provided for this type of electric vehicle. In addition, the power consumption strategy of charging stations can also be optimized and adjusted.

[0128] In this invention, charging data information is generated by acquiring real-time charging data, and the charging data information is evaluated using an artificial intelligence model to obtain charging performance evaluation results. This allows for in-depth monitoring and evaluation of the electric vehicle charging process. Furthermore, the charging performance evaluation results can identify deficiencies in the current electric vehicle charging strategy. Based on the analysis of historical charging data and the charging performance evaluation model, more optimized charging modes and strategies can be proposed, which is beneficial for improving charging performance, increasing energy utilization efficiency, and reducing charging time. In addition, by using blockchain technology and asymmetric encryption methods to encrypt and verify data information at both the client and server ends, and synchronizing it between the electric vehicle and the charging station, not only is it beneficial for protecting data from unauthorized access and tampering, but it also ensures the security and integrity of charging data, thus ensuring the accuracy and reliability of the evaluation results.

[0129] Example 2

[0130] Please see Figure 3 The present invention also discloses a method for evaluating the charging performance of an electric vehicle charging station 40, the method comprising:

[0131] S1, obtain the first dataset to verify that it matches the first dataset and the second dataset.

[0132] S2, acquire real-time charging data for each electric vehicle 30 within the charging station 40.

[0133] S3 performs data preprocessing on the real-time charging data to obtain charging data information and stores it in the server 20.

[0134] S4 evaluates charging performance based on charging data using a charging performance evaluation model and outputs the charging performance evaluation results.

[0135] The client 10 is installed on the electric vehicle 30, the server 20 is connected to several charging devices 50 in the charging station 40, the first dataset and the second dataset are the charging data information of the electric vehicle 30, the first dataset is stored in the client 10 of the electric vehicle 30, the second dataset is stored in the server 20, and the charging performance evaluation model is an artificial intelligence model.

[0136] It should be understood that by collecting historical charging data of electric vehicle 30 through client 10, encrypting it, and sending it to server 20 through charging device 50 for data preprocessing, historical charging data information is obtained. Based on the historical charging data information, a first dataset is generated and stored in client 10, and a second dataset is generated and stored in server 20, thus realizing the sharing and synchronization of datasets at both ends.

[0137] When electric vehicle 30 connects to charging device 50, server 20 retrieves the first dataset stored on client 10 and the second dataset stored on server 20 for verification and matching to ensure data accuracy. The charging performance evaluation model is trained using historical charging information from the first dataset or the corresponding second dataset to obtain a model adapted to the brand or model of electric vehicle 30. Based on the trained charging performance evaluation model and real-time charging data, the charging process is evaluated. After the charging cycle ends, the generated charging performance data is also synchronously updated to both the first and second datasets.

[0138] Example 3

[0139] Please see Figure 4 This invention discloses an electronic device, comprising:

[0140] Processor 70;

[0141] The memory 80 stores executable instructions of the processor 70; wherein the processor 30 is configured to execute the charging performance evaluation method as in Embodiment 2 by executing the executable instructions.

[0142] Example 4

[0143] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the charging performance evaluation method as described in Embodiment 2.

[0144] It should be understood that, in the embodiments of the present invention, the processor may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by hardware related to computer program instructions. The program can be stored in a computer-readable storage medium, and when executed, it may include the processes of the embodiments of the above methods. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0145] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0146] The above-disclosed examples are merely preferred embodiments of the present invention, intended to facilitate understanding and implementation by those skilled in the art. They should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the scope of the present invention's patent are still within the scope of the present invention.

Claims

1. A charging performance evaluation system for electric vehicle charging stations, characterized in that, Includes both client and server; The client is installed on the electric vehicle and stores the first dataset. The server stores a second dataset of the electric vehicle. The server is communicatively connected to several charging devices at at least one charging station. The charging devices are configured to communicate with the client when charging the electric vehicle. The server is configured as follows: Obtain the first dataset to verify that it matches the first dataset and the second dataset; Obtain real-time charging data for each of the electric vehicles in the charging station; The real-time charging data is preprocessed to obtain charging data information and stored in the server; The charging performance is evaluated based on the charging data using a charging performance evaluation model, and the charging performance evaluation results are output. The first dataset and the second dataset are historical charging data of the electric vehicle, and the charging performance evaluation model is an artificial intelligence model.

2. The charging performance evaluation system as described in claim 1, characterized in that, The charging performance evaluation model is a neural network model, which is trained based on the historical charging data of the electric vehicle.

3. The charging performance evaluation system as described in claim 1, characterized in that, The system also includes a blockchain for storing charging data information uploaded from the server.

4. The charging performance evaluation system as described in claim 1, characterized in that, The verification matching of the first dataset and the second dataset includes: Obtain the encryption key generated by the client; The first charging data information is obtained from the second dataset based on the index of the encryption key; The second charging data information is obtained from the first dataset based on the index of the first charging data information; The first charging data information is hashed and encrypted to obtain a first hash value, and the second charging data information is hashed and encrypted to obtain a second hash value; The first hash value and the second hash value are matched and verified.

5. The charging performance evaluation system as described in claim 1, characterized in that, The charging data information includes one or more of the following parameters: charging electrical parameters, charging mode information, charging time parameters, battery status information, environmental parameters, and charging station information.

6. The charging performance evaluation system as described in claim 1, characterized in that, Based on the charging data information, a charging performance evaluation model is used to evaluate charging performance, including: Calculate the charging performance score for multiple charging rounds within a statistical period and the weight value corresponding to the charging performance score for each round; The rationality score of the power allocation strategy of the charging station is calculated based on the charging performance score and the weight value within the statistical period.

7. The charging performance evaluation system as described in claim 6, characterized in that, The relevant factors for calculating the weight value include charging demand, charging time window, charging rate, charging history reliability, and charging frequency.

8. A method for evaluating the charging performance of an electric vehicle charging station, characterized in that, include: Obtain the first dataset to verify that it matches the first dataset and the second dataset; Obtain real-time charging data for each electric vehicle within the charging station; The real-time charging data is preprocessed to obtain charging data information and stored in the server; The charging performance is evaluated based on the charging data using a charging performance evaluation model, and the charging performance evaluation results are output. The client is installed on the electric vehicle, the server is communicatively connected to several charging devices in the charging station, the first dataset and the second dataset are the charging data information of the electric vehicle, the first dataset is stored in the client of the electric vehicle, the second dataset is stored in the server, and the charging performance evaluation model is an artificial intelligence model.

9. An electronic device, characterized in that, include: processor; A memory in which executable instructions of the processor are stored; The processor is configured to execute the charging performance evaluation method of claim 8 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the charging performance evaluation method as described in claim 8.

Images