Charging pile charging and discharging control method and system based on vehicle-to-network technology

Abstract

The invention discloses a charging pile charging and discharging control method and system based on a vehicle-to-network technology, and relates to the technical field of intelligent charging, and the method comprises the steps: employing an edge computing device and a machine learning model to judge a state, carrying out the automatic charging when the state is normal, adjusting a strategy when the state is abnormal, and carrying out the continuous monitoring till a battery is fully charged, and uploading data to evaluate the performance of the charging pile. According to the method, automation of the charging process under the normal condition is ensured through automatic charging and exception handling, the safety of the battery is protected by adjusting the charging strategy when the exception occurs, and the safety and efficiency of the charging process are improved. Intellectualization and automation of the charging process are achieved through dynamic charging control and data uploading, charging is automatically stopped after charging is completed, detailed charging data are uploaded for further analysis, the self-adaptive capacity of the charging pile is improved, and a data basis is provided for optimizing the performance of the charging pile.

Description

Technical Field

[0001] The present invention relates to the field of intelligent charging technology, and in particular to a charging pile charging and discharging control method and system based on vehicle-to-grid technology. Background Art

[0002] With the advancement of big data and artificial intelligence technology, intelligent charging systems have become a research hotspot. Existing intelligent charging solutions focus on remote monitoring of charging piles and basic fault diagnosis, but there are still certain limitations in the status monitoring and intelligent adjustment of electric vehicles during the charging process, resulting in the inability to improve charging efficiency.

[0003] Traditional charging pile control systems lack edge computing capabilities, and data processing mainly relies on cloud servers. In addition, after an electric vehicle is connected to a charging pile, when an abnormal situation occurs during the charging process, the existing system can only simply stop charging and cannot solve the problem by adjusting the charging strategy. This not only reduces charging efficiency, but may also cause problems such as battery damage. Therefore, how to adjust the charging strategy and improve charging efficiency has become a problem to be solved. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a charging pile charging and discharging control method and system based on vehicle-to-grid technology to solve the problem of real-time status monitoring and charging strategy adjustment of electric vehicles during the charging process.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a charging and discharging control method for a charging pile based on vehicle-to-network technology, which includes connecting an electric vehicle to a charging pile, acquiring operating data of the electric vehicle through a sensor, and uploading the data to an edge computing device;

[0008] The edge computing device receives and pre-processes the operating status data, and uses the machine learning model to identify whether the operating status is normal;

[0009] When the operating status is normal, the electric vehicle starts to charge automatically;

[0010] When the operating status is abnormal, the algorithm parameters are set to adjust the initial value of the charging power, and the self-healing mechanism is started to adjust the charging strategy;

[0011] The charging pile starts charging according to the adjusted charging strategy, and the system continues to monitor the charging pile and battery status changes until the electric vehicle reaches the battery charge state;

[0012] When the electric vehicle reaches the battery charge state, the system automatically stops charging and saves the charging data, uploads the charging data to the cloud server for analysis and statistics, evaluates the performance of the charging pile and sends the evaluation information to the user's mobile phone.

[0013] As a preferred solution of the charging and discharging control method of the charging pile based on the vehicle-to-grid technology of the present invention, wherein: connecting the electric vehicle to the charging pile, obtaining the operating data of the electric vehicle through the sensor, and uploading it to the edge computing device, including the following steps,

[0014] Park the electric vehicle next to an available charging station, remove the charging cable from the charging station, and insert one end of the charging cable into the charging port of the electric vehicle;

[0015] Deploy current sensors, voltage sensors, power state sensors, and motion state sensors on electric vehicles to monitor key parameters of electric vehicles, and use analog-to-digital conversion to convert the physical quantities of key parameters into digital signals;

[0016] The on-board computer is used to remove noise from the received digital signal, package the processed digital signal data into a standard format, and upload it to the edge computing device using a wireless network.

[0017] As a preferred solution of the charging and discharging control method of the charging pile based on the vehicle-to-grid technology of the present invention, wherein: the edge computing device receives and pre-processes the data of the operation status, and uses the machine learning model to identify whether the operation status is normal, including the following steps:

[0018] The edge device parses the received operation data into JSON and CSV formats, removes errors and invalid data, and stores the processed data in the local database;

[0019] Select the random forest machine learning model, extract the processed data and input the recognition probability value into the model;

[0020] The probability threshold is set according to the distribution of the operating status of the electric vehicle. When the probability value of the operating status of the electric vehicle is greater than the probability threshold, it indicates that the operating status of the electric vehicle is normal. When the probability value of the operating status of the electric vehicle is less than or equal to the probability threshold, it indicates that the operating status of the electric vehicle is abnormal.

[0021] As a preferred solution of the charging and discharging control method of the charging pile based on the vehicle-to-grid technology of the present invention, when the operating state is normal, the electric vehicle starts to charge automatically, and when the operating state is abnormal, the algorithm parameters are set to adjust the initial value of the charging power, and the self-repair mechanism is started to adjust the charging strategy, including the following steps:

[0022] According to the current state of charge of the electric vehicle and the battery characteristics, the algorithm parameters are set to adjust the initial value of the charging power;

[0023] After adjusting the charging power, the support vector machine model is used to predict the faults that occur in the operation state of the electric vehicle, and a self-repair algorithm is designed according to the fault type to adjust the charging time.

[0024] As a preferred solution of the charging and discharging control method of the charging pile based on the vehicle-to-grid technology of the present invention, the charging pile starts charging according to the adjusted charging strategy, and the system continuously monitors the charging pile and battery state changes until the electric vehicle reaches the battery charge state, including the following steps:

[0025] The charging strategy of the adjusted charging time and battery temperature is updated to the control system of the charging pile, and the charging pile starts charging the electric vehicle according to the new charging strategy;

[0026] During the charging process, the system continuously monitors changes in the charging pile and battery status. If there is no abnormal situation, the charging pile continues to charge the electric vehicle. If there is an abnormal situation, the charging power of the charging pile is reduced and the charging duration is adjusted according to the battery status to avoid battery overheating. Charging will continue after the battery temperature cools down to a safe range until the electric vehicle reaches the battery charge state.

[0027] As a preferred solution of the charging and discharging control method of the charging pile based on the vehicle-to-network technology of the present invention, wherein: after the electric vehicle reaches the battery charge state, the system automatically stops charging and saves the charging data, and uploads the charging data to the cloud server for analysis and statistics, including the following steps:

[0028] Set the specified value of battery power. When the battery power reaches the specified value, the system will automatically stop charging and upload the charging data to the cloud server;

[0029] After receiving the charging data, the cloud server uses cluster analysis to identify abnormal data points and classify them, thereby analyzing the user's charging habits in terms of charging time, frequency, and charging amount.

[0030] As a preferred solution of the charging and discharging control method of the charging pile based on the vehicle-to-grid technology of the present invention, wherein: evaluating the performance of the charging pile and sending the evaluation information to the user's mobile phone, including the following steps,

[0031] Calculate the success rate and failure rate of the charging pile according to the user's charging habits;

[0032] Based on the calculated success rate and failure rate of the charging pile, the average time required for the charging pile to complete the charging task and the performance of the stability of the charging pile's output power during the charging process are evaluated, and the evaluation information is sent to the user's mobile phone using a cloud server.

[0033] In a second aspect, the present invention provides a charging pile charging and discharging control system based on vehicle-to-network technology, including a data acquisition module responsible for connecting an electric vehicle to a charging pile, obtaining operating data of the electric vehicle through a sensor, and uploading the data to an edge computing device;

[0034] The data preprocessing module is responsible for receiving and preprocessing the operation data of the edge computing device;

[0035] The status recognition module is responsible for using machine learning models to identify whether the operating status is normal;

[0036] Automatic charging module, responsible for automatically charging the electric vehicle when the operating status is normal;

[0037] The exception handling module is responsible for setting algorithm parameters to adjust the initial value of charging power and starting the self-healing mechanism to adjust the charging strategy when an abnormality occurs in the operating state;

[0038] The dynamic charging control module is responsible for the charging pile to start charging according to the adjusted charging strategy. The system continuously monitors the charging pile and battery status changes until the electric vehicle reaches the battery charge state;

[0039] The data upload and analysis module is responsible for automatically stopping charging and saving charging data after the electric vehicle reaches the battery charge state, uploading the charging data to the cloud server for analysis and statistics, evaluating the performance of the charging pile and sending the evaluation information to the user's mobile phone.

[0040] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the charging pile charging and discharging control method based on vehicle-to-grid technology as described in the first aspect of the present invention is implemented.

[0041] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the charging and discharging control method of a charging pile based on vehicle-to-grid technology as described in the first aspect of the present invention is implemented.

[0042] The beneficial effects of the present invention are as follows: the automation of the charging process under normal circumstances is ensured through automatic charging and exception handling, and the battery safety is protected by adjusting the charging strategy when an exception occurs, thereby improving the safety and efficiency of the charging process. The intelligent and automated charging process is realized by using dynamic charging control and data uploading, and charging is automatically stopped after charging is completed, while detailed charging data is uploaded for further analysis, which improves the adaptive ability of the charging pile and provides a data basis for optimizing the performance of the charging pile. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0044] Figure 1 This is a flow chart of the charging and discharging control method of a charging pile based on vehicle-to-grid technology in Example 1.

[0045] Figure 2 This is a determination diagram of the charging and discharging control method of a charging pile based on vehicle-to-grid technology in Example 1. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0047] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a charging pile charging and discharging control method based on vehicle-to-grid technology, comprising the following steps:

[0048] S1. Connect the electric vehicle to the charging station, obtain the operating data of the electric vehicle through the sensor, and upload it to the edge computing device, including the following steps:

[0049] Park the electric vehicle next to an available charging station, remove the charging cable from the charging station, and insert one end of the charging cable into the charging port of the electric vehicle;

[0050] Deploy current sensors, voltage sensors, power state sensors, and motion state sensors on electric vehicles to monitor key parameters of electric vehicles, and use analog-to-digital conversion to convert the physical quantities of key parameters into digital signals;

[0051] The received digital signal is processed by the on-board computer to remove noise, the processed digital signal data is packaged into a standard format, and uploaded to the edge computing device using a wireless network;

[0052] Analog-to-digital conversion is a method of converting a continuous analog signal into a discrete digital signal.

[0053] S2. The edge computing device receives and pre-processes the operating status data and uses the machine learning model to identify whether the operating status is normal, including the following steps:

[0054] The edge device parses the received operation data into JSON (data exchange) and CSV formats, removes errors and invalid data, and stores the processed data in the local database;

[0055] Select the random forest machine learning model, extract the processed data and input the recognition probability value into the model. The expression is:

[0056]

[0057] Among them, P n represents the probability value of the electric vehicle's operating state, and Z represents the normalized constant of the probability value of the electric vehicle's operating state, which is used to determine P n The value range is between [0,1], n represents the number of data points, i represents the index of the data point, which is used to identify each specific data point, and x i represents the eigenvalue of the data point, φ(x i ) represents the conversion of the feature value of the data point into a mapping value that describes the distribution, which is used to convert the feature value into a form suitable for probability calculation. m represents the total number of decision trees in the random forest model, indicating the number of decision trees contained in the random forest. j represents the index of the decision tree, which is used to identify each tree in the random forest. d j Indicates the depth of the decision tree, which is used to reflect the number of layers of the decision tree. g(d j ) represents the complexity metric of the decision tree, which is used to measure the complexity of the decision tree. k represents the decision tree index used for normalization when calculating the complexity metric of the decision tree, which is used as an index when calculating the sum of the complexity metric of the decision tree. d k represents the depth of the decision tree, g(d k ) represents the relative value of the complexity of calculating the decision tree;

[0058] The derivation process of the expression of probability value is:

[0059] First, the eigenvalue x of each data point i Converted into a mapping value φ(x i), whose purpose is to convert the original eigenvalue into a form suitable for probability calculation, the expression is:

[0060]

[0061] The random forest model consists of m decision trees, each with a specific depth d. j The depth of the decision tree is d j It can be used to measure the complexity of the tree and define a complexity metric g(d j ), that is, the complexity of a decision tree is proportional to its depth, for example:

[0062] g(d j ) = d j ;

[0063] In order to ensure the comparability of complexity measures, it is necessary to calculate the sum of the complexity measures of all decision trees, expressed as:

[0064]

[0065] Then, for each tree j, the weight of the complexity metric relative to the total is calculated, expressed as:

[0066]

[0067] This step ensures that even though the decision trees have different complexity, their contributions to the final result are balanced.

[0068] The normalization constant Z is to ensure that P n The value range of is in [0,1]. For simplicity, assume that Z is composed of the sum of all decision tree complexity metrics, expressed as:

[0069]

[0070] Combined with the above derivation, we finally get the calculated probability value P n , this probability value consists of two parts: the sum of the feature value mapping value and the sum of the decision tree complexity measure value, expressed as:

[0071]

[0072] According to the distribution of the operating status of the electric vehicle, a ROC curve (receiver operating characteristic curve) is drawn to select the largest Youden Index. The probability threshold is set according to the largest Youden Index. The specific range of the probability threshold is 0.7. When the probability value of the operating status of the electric vehicle is greater than the probability threshold, it indicates that the operating status of the electric vehicle is normal. When the probability value of the operating status of the electric vehicle is less than or equal to the probability threshold, it indicates that the operating status of the electric vehicle is abnormal.

[0073] S3. When the operation status is normal, the electric vehicle starts to charge automatically. When the operation status is abnormal, the algorithm parameters are set to adjust the initial value of the charging power, and the self-repair mechanism is started to adjust the charging strategy, including the following steps:

[0074] According to the current state of charge of the electric vehicle and the battery characteristics, the algorithm parameters are set to adjust the initial value of the charging power. The expression is:

[0075] P a =P l ×(1-α×T);

[0076] Among them, P a Indicates the adjusted charging power, P l represents the initial value of the charging power, α represents the adjustment coefficient for controlling the influence of temperature change on the charging power. A larger α value means that the temperature change has a greater influence on the charging power, and vice versa. T represents the current battery temperature;

[0077] After adjusting the charging power, the support vector machine model is used to predict the faults that occur in the operation state of the electric vehicle. The specific fault types are battery short circuit, abnormal charging rate, and drive system failure. According to the fault type, a self-repair algorithm is designed to adjust the charging time. The expression is:

[0078]

[0079] Among them, C dj represents the adjusted charging time, and N represents the normalization constant of the adjusted charging time, which is used to normalize the integral result to ensure that C dj The value is within a reasonable range, t0 represents the charging start time, t f represents the charging end time, SOC(t) represents the change of the state of charge over time, and φ(SOC(t)) represents the mapping of the change of the state of charge over time into a value that describes the distribution of the state of charge, which is used to convert the change of the state of charge into a form that is easier to handle.

[0080] The derivation process of the expression for adjusting the charging time is:

[0081] During the charging process, the battery state of charge will change over time, so this change needs to be mapped into a value that describes the state of charge distribution. This can be achieved by defining a mapping value φ(SOC(t)) that describes the state of charge distribution.

[0082] Next, it is necessary to calculate the time from the start time t0 to the end time t f, the integral of the mapping value φ(SOC(t)) of the state of charge changing over time. The purpose of this step is to evaluate the change of the state of charge during the entire charging process, and the expression is:

[0083]

[0084] In order to ensure that the integration result can reflect the actual charging time adjustment value, it needs to be normalized. This step is achieved by dividing by the normalization constant N. The normalization constant N can be a specified value or adjusted according to the specific situation. The expression is:

[0085]

[0086] Combining the above derivation steps, we get the final expression C dj , the expression is:

[0087]

[0088] S4. The charging pile starts charging according to the adjusted charging strategy, and the system continues to monitor the charging pile and battery status changes until the electric vehicle reaches the battery charge state, including the following steps:

[0089] The charging strategy of the adjusted charging time and battery temperature is updated to the control system of the charging pile, and the charging pile starts charging the electric vehicle according to the new charging strategy;

[0090] During the charging process, the system continuously monitors changes in the charging pile and battery status. If there is no abnormal situation, the charging pile continues to charge the electric vehicle. If there is an abnormal situation, the charging power of the charging pile is reduced and the charging duration is adjusted according to the battery status to avoid battery overheating. Charging will continue after the battery temperature cools down to a safe range until the electric vehicle reaches the battery charge state.

[0091] S5. After the electric vehicle reaches the battery charge state, the system automatically stops charging and saves the charging data, and uploads the charging data to the cloud server for analysis and statistics, including the following steps:

[0092] Set the specified value of battery power, which is between 97% and 99%. When the battery power reaches the specified value, the system will automatically stop charging and upload the charging data to the cloud server;

[0093] After receiving the charging data, the cloud server filters out the data on the time, frequency and amount of each user's charging. It uses K-Means (unsupervised learning algorithm) to identify and classify abnormal data points. Based on the classification results, it determines the usage characteristics of different user groups and uses a time series graph to display the changing trends of charging time, frequency and amount, thereby analyzing the user's charging habits.

[0094] A time series graph is a type of chart used to visualize time series data. It can clearly show data trends and other patterns that change over time. It is widely used in many fields such as finance, economics, meteorology, and scientific research.

[0095] S6. Evaluate the performance of the charging station and send the evaluation information to the user's mobile phone, including the following steps:

[0096] According to the user's charging habits, the success rate and failure rate of the charging pile are calculated, and the expression is:

[0097]

[0098] R f =1-R s ;

[0099] Among them, R s Indicates the success rate of the charging pile, Represents the normalized constant of the success rate of the charging pile, which is used to ensure R s Within a reasonable range, t0 represents the charging start time, t f represents the end time of charging, κ represents the mapping relationship of the Gaussian kernel function, which is used to describe the degree of deviation of the state of charge from the average value, SOC(t) represents the change of the state of charge over time, represents the average value of the state of charge, σ SOC represents the standard deviation of the state of charge, p represents the number of battery temperature data points, y represents the index of the battery temperature data point, which is used to traverse all battery temperature data points, T y Indicates the measured battery temperature value. represents the average value of battery temperature, σ T Indicates the standard deviation of the battery temperature, which is used to reflect the fluctuation of the battery temperature. The larger the standard deviation, the greater the change in battery temperature. f Indicates the failure rate of the charging pile;

[0100] The derivation process of the expression for the success rate of the charging pile is:

[0101] First, we need to calculate these statistics, including,

[0102] Average value of power state The expression is:

[0103]

[0104] Where n represents the number of charge states recorded during the charging process.

[0105] Standard deviation of state of charge σ SOC , the expression is:

[0106]

[0107] Among them, SOC(t i ) represents the time point t i The power status at that time.

[0108] Average battery temperature The expression is:

[0109]

[0110] Standard deviation of battery temperature σ T , the expression is:

[0111]

[0112] The mapping relationship of the Gaussian kernel function is used to describe the degree of deviation of the state of charge and battery temperature from the average value, which is defined as follows:

[0113]

[0114] Where x represents the state of charge and battery temperature, μ represents the mean value, and σ represents the standard deviation.

[0115] Calculate the time from the start of charging t0 to the end of charging t f The integral of the Gaussian kernel function mapping value of the power state during the period is expressed as:

[0116]

[0117] This integral represents the cumulative effect of the degree of deviation of the state of charge from the average value over the entire charging process.

[0118] Calculate all battery temperature data points T during the charging period y The average value of the Gaussian kernel function mapping value is expressed as:

[0119]

[0120] This sum represents the average effect of how much the battery temperature deviates from the average temperature during the charging period.

[0121] The integration result and the summation result are normalized to obtain the success rate of the complete charging pile, which is expressed as:

[0122]

[0123] According to the success rate and failure rate of the charging pile, the average charging time and the standard deviation of the output power are calculated. The expression is:

[0124]

[0125] Among them, avgT represents the average charging time, which is used to reflect the change of the power state during the charging process, t0 represents the charging start time, t f represents the end time of charging, SOC(t) represents the change of the state of charge over time, φ(SOC(t)) represents the mapping of the change of the state of charge over time into a value describing the distribution of the state of charge, which is used to convert the change of the state of charge into a form that is easier to handle, and σ P It represents the standard deviation of the output power. The larger the standard deviation, the greater the power variation. The smaller the standard deviation, the smaller the power variation. d represents the number of charging powers recorded during the charging process, which is the number of samples used to calculate the standard deviation. v represents an integer index from 1 to d, which is used to traverse all charging power records when calculating the standard deviation. P a Indicates the adjusted charging power, Indicates the average value of the adjusted charging power;

[0126] The derivation process of the expression for the standard deviation of the charging output power is:

[0127] First, we need to calculate the adjusted charging power P a The average value of all measurement points during the entire charging process The expression is:

[0128]

[0129] Next, the deviation between the adjusted charging power and the average charging power at each measurement point needs to be calculated, and the expression is:

[0130]

[0131] Now, we calculate the sum of squared deviations, which is done to eliminate the effect of the negative sign and emphasize the importance of measurements far from the mean. This is expressed as:

[0132]

[0133] Finally, the unbiased estimate of the standard deviation is calculated by dividing the sum of squared deviations by the degrees of freedom d-1. The concept of degrees of freedom is to more accurately estimate the standard deviation of the population rather than simply dividing by d. Therefore, the expression for the standard deviation of the output power is:

[0134]

[0135] Combined with the expressions of charging time and output power standard deviation, the average time required for the charging pile to complete the charging task and the performance of the stability of the output power of the charging pile during the charging process are evaluated, and the evaluation information is sent to the user's mobile phone using a cloud server.

[0136] This embodiment also provides a charging pile charging and discharging control system based on vehicle-to-network technology, including: a data acquisition module, which is responsible for connecting an electric vehicle to a charging pile, obtaining operating data of the electric vehicle through a sensor, and uploading it to an edge computing device;

[0137] The data preprocessing module is responsible for receiving and preprocessing the operation data of the edge computing device;

[0138] The status recognition module is responsible for using machine learning models to identify whether the operating status is normal;

[0139] Automatic charging module, responsible for automatically charging the electric vehicle when the operating status is normal;

[0140] The exception handling module is responsible for setting algorithm parameters to adjust the initial value of charging power and starting the self-healing mechanism to adjust the charging strategy when an abnormality occurs in the operating state;

[0141] The dynamic charging control module is responsible for the charging pile to start charging according to the adjusted charging strategy. The system continuously monitors the charging pile and battery status changes until the electric vehicle reaches the battery charge state;

[0142] The data upload and analysis module is responsible for automatically stopping charging and saving charging data after the electric vehicle reaches the battery charge state, uploading the charging data to the cloud server for analysis and statistics, evaluating the performance of the charging pile and sending the evaluation information to the user's mobile phone.

[0143] This embodiment also provides a computer device, which is suitable for the case of a charging pile charging and discharging control method based on vehicle-to-grid technology, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the charging pile charging and discharging control method based on vehicle-to-grid technology proposed in the above embodiment.

[0144] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0145] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the charging and discharging control method of a charging pile based on vehicle-to-grid technology proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0146] In summary, the present invention ensures the automation of the charging process under normal circumstances through automatic charging and exception handling, and protects the battery safety by adjusting the charging strategy when an exception occurs, thereby improving the safety and efficiency of the charging process. The intelligent and automated charging process is realized by using dynamic charging control and data uploading, and charging is automatically stopped after charging is completed, while detailed charging data is uploaded for further analysis, which improves the adaptive ability of the charging pile and provides a data basis for optimizing the performance of the charging pile.

[0147] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a charging pile charging and discharging control method based on vehicle-to-grid technology is provided.

[0148] In order to verify the effectiveness and superiority of the invention, the following experiments were conducted:

[0149] Choose between two models of electric vehicles, Model X and Model Y, and two types of charging stations, Type A and Type B.

[0150] Current sensors, voltage sensors, power state sensors, and motion state sensors are installed on the electric car Model X, and an on-board computer is configured for data collection and preprocessing.

[0151] Ten electric vehicles of each model were selected for testing, for a total of 20 electric vehicles.

[0152] Park the electric vehicle next to an available charging station, remove the charging cable from the charging station, and plug one end of the charging cable into the charging port of the electric vehicle.

[0153] Activate the sensors on the electric vehicle to collect data on the operation of the electric vehicle, including information such as current, voltage, charge status and motion status.

[0154] The collected analog signals are converted into digital form using the on-board computer, and noise interference is removed. The processed data is packaged into a standard format and uploaded to the edge computing device via the wireless network.

[0155] The edge computing device receives and preprocesses the operating status data and uses the random forest model to identify whether the operating status is normal.

[0156] When the operating status is normal, the electric vehicle starts to charge automatically; when the operating status is abnormal, the algorithm parameters are set to adjust the initial value of the charging power, and the self-repair mechanism is started to adjust the charging strategy.

[0157] The charging pile starts charging according to the adjusted charging strategy, and the system continuously monitors the charging pile and battery status changes until the electric vehicle reaches the battery's charge state.

[0158] When the electric vehicle reaches the battery charge state, the system automatically stops charging and uploads the charging data to the cloud server for analysis and statistics, evaluates the performance of the charging pile, and sends the evaluation information to the user's mobile phone.

[0159] During each charging process, the charging start time and end time are recorded, and the power status and charging power P are recorded every five minutes during the charging process. a, calculate the average charging time avgT and the standard deviation σ of the output power in each charging process P , and record the corresponding data for comparative analysis.

[0160] The details are shown in Table 1 below:

[0161] Table 1 Comparison of electric vehicle charging performance

[0162]

[0163] Through the data records of the above embodiment, it can be concluded that:

[0164] On a Type A charger, the average charging time for Model X is 30 minutes, while for Model Y it is 25 minutes. On a Type B charger, the average charging time for Model X is 35 minutes, while for Model Y it is 30 minutes.

[0165] It can be seen that the Type A charging pile using the content of the present invention has a shorter charging time for both Model X and Model Y than the Type B charging pile, which shows that the charging strategy of the present invention optimizes the charging time.

[0166] On a Type A charger, the standard deviation of Model X's output power is 0.12kW, while that of Model Y is 0.10kW. On a Type B charger, the standard deviation of Model X's output power is 0.15kW, while that of Model Y is 0.12kW.

[0167] The smaller the standard deviation, the smaller the power variation, which means that the power is more stable during the charging process. From the data, the Type A charging pile using the content of the present invention has a smaller standard deviation of output power than the Type B charging pile, whether it is Model X or Model Y, indicating that the power is more stable during the charging process.

[0168] By comparison with current technology, it is found that the charging pile using the content of the present invention is superior to conventional methods in terms of average charging time and output power stability. In particular, the standard deviation is significantly reduced in terms of charging power stability, indicating that the present invention can better maintain power stability during the charging process.

[0169] The content of the present invention has obvious creativity and novelty in optimizing charging strategy, shortening charging time and improving power stability during charging, and is superior to current related technologies.

[0170] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A charging and discharging control method for a charging pile based on vehicle-to-grid technology, characterized in that: include, Connect electric vehicles to charging piles, obtain operating data of electric vehicles through sensors, and upload them to edge computing devices; The edge computing device receives and pre-processes the operating status data, and uses the machine learning model to identify whether the operating status is normal; When the operating status is normal, the electric vehicle starts to charge automatically; When the operating status is abnormal, the algorithm parameters are set to adjust the initial value of the charging power, and the self-healing mechanism is started to adjust the charging strategy; The charging pile starts charging according to the adjusted charging strategy, and the system continues to monitor the charging pile and battery status changes until the electric vehicle reaches the battery charge state; When the electric vehicle reaches the battery charge state, the system automatically stops charging and saves the charging data, uploads the charging data to the cloud server for analysis and statistics, evaluates the performance of the charging pile and sends the evaluation information to the user's mobile phone.

2. The charging pile charging and discharging control method based on vehicle-to-grid technology according to claim 1, characterized in that: Connecting an electric vehicle to a charging station, obtaining the operating data of the electric vehicle through sensors, and uploading it to the edge computing device includes the following steps: Park the electric vehicle next to an available charging station, remove the charging cable from the charging station, and insert one end of the charging cable into the charging port of the electric vehicle; Deploy current sensors, voltage sensors, power state sensors, and motion state sensors on electric vehicles to monitor key parameters of electric vehicles, and use analog-to-digital conversion to convert the physical quantities of key parameters into digital signals; The on-board computer is used to remove noise from the received digital signal, package the processed digital signal data into a standard format, and upload it to the edge computing device using a wireless network.

3. The charging pile charging and discharging control method based on vehicle-to-grid technology as claimed in claim 2, characterized in that: The edge computing device receives and pre-processes the operating status data and uses the machine learning model to identify whether the operating status is normal, including the following steps: The edge device parses the received operation data into JSON and CSV formats, removes errors and invalid data, and stores the processed data in the local database; Select the random forest machine learning model, extract the processed data and input the recognition probability value into the model; The probability threshold is set according to the distribution of the operating status of the electric vehicle. When the probability value of the operating status of the electric vehicle is greater than the probability threshold, it indicates that the operating status of the electric vehicle is normal. When the probability value of the operating status of the electric vehicle is less than or equal to the probability threshold, it indicates that the operating status of the electric vehicle is abnormal.

4. The charging pile charging and discharging control method based on vehicle-to-grid technology as claimed in claim 3 is characterized in that: When the operating status is normal, the electric vehicle starts to charge automatically. When the operating status is abnormal, the algorithm parameters are set to adjust the initial value of the charging power, and the self-repair mechanism is started to adjust the charging strategy, including the following steps: According to the current state of charge of the electric vehicle and the battery characteristics, the algorithm parameters are set to adjust the initial value of the charging power; After adjusting the charging power, the support vector machine model is used to predict the faults that occur in the operation state of the electric vehicle, and a self-repair algorithm is designed according to the fault type to adjust the charging time.

5. The charging and discharging control method of a charging pile based on vehicle-to-grid technology according to claim 4, characterized in that: The charging pile starts charging according to the adjusted charging strategy, and the system continuously monitors the charging pile and battery status changes until the electric vehicle reaches the battery charge state, including the following steps: The charging strategy of the adjusted charging time and battery temperature is updated to the control system of the charging pile, and the charging pile starts charging the electric vehicle according to the new charging strategy; During the charging process, the system continuously monitors changes in the charging pile and battery status. If there is no abnormal situation, the charging pile continues to charge the electric vehicle. If there is an abnormal situation, the charging power of the charging pile is reduced and the charging duration is adjusted according to the battery status to avoid battery overheating. Charging will continue after the battery temperature cools down to a safe range until the electric vehicle reaches the battery charge state.

6. The charging and discharging control method of a charging pile based on vehicle-to-grid technology as claimed in claim 5, characterized in that: When the electric vehicle reaches the battery charge state, the system automatically stops charging and saves the charging data, and uploads the charging data to the cloud server for analysis and statistics, including the following steps: Set the specified value of battery power. When the battery power reaches the specified value, the system will automatically stop charging and upload the charging data to the cloud server; After receiving the charging data, the cloud server uses cluster analysis to identify abnormal data points and classify them, thereby analyzing the user's charging habits in terms of charging time, frequency, and charging amount.

7. The charging and discharging control method of a charging pile based on vehicle-to-grid technology according to claim 6, characterized in that: Evaluate the performance of the charging station and send the evaluation information to the user's mobile phone, including the following steps: Calculate the success rate and failure rate of the charging pile according to the user's charging habits; Based on the calculated success rate and failure rate of the charging pile, the average time required for the charging pile to complete the charging task and the performance of the stability of the charging pile's output power during the charging process are evaluated, and the evaluation information is sent to the user's mobile phone using a cloud server.

8. A charging pile charging and discharging control system based on vehicle-to-grid technology, based on the charging pile charging and discharging control method based on vehicle-to-grid technology according to any one of claims 1 to 7, characterized in that: include, The data acquisition module is responsible for connecting the electric vehicle to the charging pile, obtaining the operating data of the electric vehicle through sensors, and uploading it to the edge computing device; The data preprocessing module is responsible for receiving and preprocessing the operation data of the edge computing device; The status recognition module is responsible for using machine learning models to identify whether the operating status is normal; Automatic charging module, responsible for automatically charging the electric vehicle when the operating status is normal; The exception handling module is responsible for setting algorithm parameters to adjust the initial value of charging power and starting the self-healing mechanism to adjust the charging strategy when an abnormality occurs in the operating state; The dynamic charging control module is responsible for the charging pile to start charging according to the adjusted charging strategy. The system continuously monitors the charging pile and battery status changes until the electric vehicle reaches the battery charge state; The data upload and analysis module is responsible for automatically stopping charging and saving charging data after the electric vehicle reaches the battery charge state, uploading the charging data to the cloud server for analysis and statistics, evaluating the performance of the charging pile and sending the evaluation information to the user's mobile phone.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the charging and discharging control method of a charging pile based on vehicle-to-grid technology as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the charging and discharging control method of a charging pile based on vehicle-to-grid technology according to any one of claims 1 to 7 are implemented.

Images