Intelligent charging pile power supply power dynamic allocation system and method

Abstract

The invention provides an intelligent charging pile power supply power dynamic allocation system. The system comprises a data acquisition module, an edge calculation module, a data compression module, a data transmission module, a data analysis module, an intelligent analysis module and a power allocation decision module. And the data acquisition module is used for acquiring charging power data of the charging pile in real time through a sensor. By deploying the data acquisition module and the edge calculation module at the front end of the charging pile, charging power data can be acquired in real time, preliminary data cleaning, denoising and screening are performed, the amount of data needing to be transmitted to the rear end is reduced, the processing pressure of a processing background is reduced, and compared with the prior art, the processing efficiency is improved. According to the invention, the collected data of the front end does not need to be transmitted to the rear end immediately, but key data is sent as required after primary processing is completed through edge calculation, so that the real-time requirement of data transmission is reduced, and a rear-end platform can process the data more flexibly.

Description

Technical Field

[0001] The present invention relates to a deployment system and method, specifically an intelligent charging pile power supply dynamic deployment system and method, belonging to the technical field of charging pile control and management. Background Art

[0002] The dynamic deployment system of the charging pile power supply intelligently adjusts the charging power according to the actual situation to provide charging services for electric vehicles more efficiently and safely. The system dynamically adjusts the charging power by real-time monitoring of the grid load, the usage of charging piles, and the battery status of electric vehicles, so as to maximize the charging efficiency. Its core lies in the intelligent algorithm, which can analyze and predict the changes in the grid load and the charging demand of electric vehicles, and calculate the optimal charging power distribution plan based on these data.

[0003] The existing dynamic deployment systems of charging pile power supply still have the following problems in the actual operation process:

[0004] It is necessary to collect a large amount of charging power change data in real time and continuously. Since the data generation frequency during the charging process of electric vehicles is extremely high, and each charging pile may generate a large amount of data, the data volume involved in the entire system is extremely huge. If the traditional data processing method is adopted, that is, the charging power data collected at the charging pile end is directly transmitted to the processing background for processing, determination, and then the charging power is changed accordingly, the processing background will bear a huge data processing pressure. This pressure not only comes from the huge data volume, but also because the data processing needs to be carried out in real time to ensure the continuity and safety of the charging process;

[0005] Therefore, in this context, if the data processing process is not optimized, the processing background often experiences performance degradation or even paralysis due to its inability to bear such a huge data processing load, which will not only affect the normal operation of the charging piles, but also have a negative impact on the charging experience of users. For this reason, an intelligent charging pile power supply dynamic deployment system and method are proposed. Summary of the Invention

[0006] In view of this, the present invention provides an intelligent charging pile power supply dynamic deployment system and method to solve or alleviate the technical problems existing in the prior art, and at least provide a beneficial option.

[0007] The technical solution of the embodiment of the present invention is realized as follows: An intelligent charging pile power supply dynamic deployment system includes a data acquisition module, an edge computing module, a data compression module, a data transmission module, a data parsing module, an intelligent analysis module, and a power deployment decision module. The signal ends of the data acquisition module, the edge computing module, the data compression module, the data transmission module, the data parsing module, the intelligent analysis module, and the power deployment decision module are connected in sequence;

[0008] The data acquisition module is used to collect the charging power data of the charging pile in real time through sensors. The charging power data includes current, voltage, power, and temperature. The sensors include a current sensor, a voltage sensor, a power sensor, and a temperature sensor;

[0009] The edge computing module is used to perform preliminary analysis and screening on the charging power data by using edge computing algorithms to obtain key data. The key data includes data that exceeds the threshold and shows an abnormal trend;

[0010] The data compression module is used to receive the key data that has been screened and perform compression processing on the key data;

[0011] The data transmission module is used to transmit the compressed key data to the data parsing module in the processing background;

[0012] The data parsing module is used to receive compressed data from different charging piles and different types and convert them into a unified data coding format;

[0013] The intelligent analysis module is used to analyze the parsed data by using prediction algorithms to predict the grid load changes and electric vehicle charging demands. The intelligent analysis module predicts the future grid load changes based on historical data and current trends. The intelligent analysis module analyzes the charging behavior, usage patterns of electric vehicles, and the distribution of charging facilities to predict the electric vehicle charging demands;

[0014] The power allocation module is used to formulate an optimal charging power allocation plan according to the results of the intelligent analysis module.

[0015] Further preferably, the current sensor is used to monitor the magnitude and direction of the output current of the charging pile;

[0016] The voltage sensor is used to monitor the magnitude of the output voltage of the charging pile;

[0017] The power sensor is used to calculate the measured power value output by the charging pile. By combining the measurement results of current and voltage, the real-time power value is calculated;

[0018] The temperature sensor is used to monitor the temperature of the charging pile.

[0019] Further preferably, the edge computing algorithm includes the following steps:

[0020] Data preprocessing: Receive the charging data from the data acquisition module, and perform denoising, formatting, and outlier detection on the received data;

[0021] Feature extraction: Extract features related to charging power from the preprocessed data, including the instantaneous value, average value, maximum value, minimum value, and change rate of the charging power;

[0022] Threshold judgment: Set a charging power threshold. When the charging power data exceeds or is lower than the threshold, it indicates that the charging pile is in an abnormal state or there is a problem during the charging process;

[0023] Trend analysis: Analyze the change trend of the charging power data. When the data shows abnormal fluctuations or sudden changes, it indicates that the charging pile is experiencing a fault or an abnormal situation;

[0024] Data screening: Obtain key data by screening the charging power data;

[0025] Data upload and storage: Upload the screened key data to the processing background, and store the original data and screening results in the local storage of the charging pile.

[0026] Further preferably, the data transmission module uses the TCP / IP protocol to transmit data. Before data transmission, the identities of the sender and the receiver are verified through an authentication mechanism, and the access rights to the data are restricted through an authorization mechanism. At the same time, a detailed log record and monitoring are carried out for the data transmission process to promptly detect and handle any abnormal behavior or potential security threat.

[0027] Further preferably, the data parsing module first receives the compressed data packet, then calls the corresponding decompression algorithm to decompress the data packet, restores the compressed data to its original, uncompressed data format, and then converts the data into a unified data encoding format.

[0028] Further preferably, the prediction algorithm includes the following steps:

[0029] Data collection: Collect historical data from charging piles and grid operators, and perform cleaning and preprocessing;

[0030] Model construction: Construct a prediction model, use historical data to train a machine learning algorithm. During the training process, the prediction model learns the patterns and trends in the data and adjusts the model parameters to minimize the prediction error;

[0031] Model evaluation and optimization: Evaluate the prediction model through cross-validation, confusion matrix, and ROC curve. According to the evaluation results, optimize and adjust the model;

[0032] Prediction and result analysis: Apply the trained prediction model to new data to generate prediction results.

[0033] Further preferably, the charging power distribution scheme includes:

[0034] Charging pile power distribution: For each charging pile, allocate a reasonable charging power according to its current charging demand, historical charging records, and the load condition of the power grid;

[0035] Power grid load balancing: When allocating charging power, take into account the load balancing of the power grid;

[0036] Priority setting: Allocate charging power according to specific priority settings;

[0037] Dynamic adjustment strategy: Dynamically adjust the allocation plan according to the real-time analysis results of the intelligent analysis module.

[0038] Further preferably, it further includes an instruction issuing module and an execution module, and the signal terminal of the instruction issuing module is connected to the signal terminal of the execution module;

[0039] The instruction issuing module is used to issue the instructions of the power allocation decision module to the execution module, and the execution module is used to adjust the charging power of the charging pile.

[0040] Further preferably, it further includes a status monitoring module and an early warning module, and the signal terminal of the status monitoring module is connected to the signal terminal of the early warning module;

[0041] The status monitoring module is used to monitor the operation status of the charging pile and the load condition of the processing background in real time. When an abnormal situation is detected, it sends a signal to the early warning module, and the early warning module automatically triggers an alarm mechanism when receiving the abnormal signal.

[0042] An intelligent charging pile power supply dynamic allocation method includes the following steps:

[0043] Step 1: Obtain the charging power data of the charging pile, and the charging power data includes current, voltage, power, and temperature;

[0044] Step 2: Initially analyze and screen the charging power data to obtain key data, and the key data includes data that exceeds the threshold and shows an abnormal trend;

[0045] Step 3: Compress the key data and transmit the compressed key data to the processing background;

[0046] Step 4: The processing background receives the compressed data from different charging piles and different types and converts it into a unified data coding format;

[0047] Step 5: Use a prediction algorithm to analyze the parsed data, predict the power grid load change and the electric vehicle charging demand, and formulate an optimal charging power allocation plan according to the prediction results;

[0048] Step 6: Send the instructions of the power allocation decision module to the execution module in the charging pile, and the execution module adjusts the charging power of the charging pile.

[0049] Due to the adoption of the above technical solutions in the embodiments of the present invention, it has the following advantages:

[0050] By deploying a data acquisition module and an edge computing module at the front end of the charging pile, the present invention can collect charging power data in real time, and perform preliminary data cleaning, denoising and screening, reducing the amount of data that needs to be transmitted to the backend, thereby reducing the processing pressure on the processing background, reducing the occupancy of network bandwidth and transmission costs, improving the efficiency and reliability of data transmission. Through the intelligent analysis module, the charging demand and grid load changes in the short term can be predicted, which reduces the amount of data that needs to be transmitted to the backend for in-depth analysis, and at the same time speeds up the decision-making process. Compared with the prior art, the collected data at the front end of the present invention does not need to be immediately transmitted to the backend, but after preliminary processing by edge computing, the key data is sent on demand, which reduces the real-time requirement of data transmission, enables the processing background to process data more flexibly, and through intelligent analysis and decision-making, can provide users with more personalized and efficient charging services, reduce charging interruptions caused by data processing delays, and improve user satisfaction.

[0051] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 It is a structural diagram of an intelligent charging pile power supply dynamic allocation system of the present invention;

[0054] Figure 2 It is a step flow chart of the edge computing algorithm of the present invention;

[0055] Figure 3 It is a step flow chart of an intelligent charging pile power supply dynamic allocation method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] In the following, only some exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the accompanying drawings and the description are considered to be exemplary in nature rather than restrictive.

[0057] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0058] As Figures 1 - 3 shown, the embodiment of the present invention provides an intelligent charging pile power dynamic allocation system, which includes a data acquisition module, an edge computing module, a data compression module, a data transmission module, a data parsing module, an intelligent analysis module, and a power allocation decision module. The signal ends of the data acquisition module, the edge computing module, the data compression module, the data transmission module, the data parsing module, the intelligent analysis module, and the power allocation decision module are connected in sequence;

[0059] The data acquisition module is used to collect the charging power data of the charging pile in real time through sensors. The charging power data includes current, voltage, power, and temperature. The sensors include current sensors, voltage sensors, power sensors, and temperature sensors;

[0060] The current sensor is used to monitor the magnitude and direction of the current output by the charging pile. The current sensor is installed at the output end of the charging pile, and can capture the current signal in real time and convert it into a digital signal for processing by the data acquisition module;

[0061] The voltage sensor is used to monitor the magnitude of the voltage output by the charging pile. The voltage sensor is installed inside the charging pile, and can capture the voltage signal in real time and transmit it after converting it into a digital signal. The accuracy and stability of the voltage sensor are of great significance for evaluating the voltage change during the charging process, protecting the battery pack, and optimizing the charging strategy, etc.;

[0062] The power sensor is used to calculate and measure the power value output by the charging pile. By combining the measurement results of current and voltage, the real-time power value is calculated;

[0063] The temperature sensor is used to monitor the temperature of the charging pile, which helps to detect potential safety hazards such as overheating in a timely manner and take corresponding protection measures;

[0064] When the charging pile starts to work, the above sensors will capture the changes of various physical quantities during the charging process in real time. These analog signals are then converted into digital signals and aggregated, processed, and stored by the data acquisition module. The data acquisition module will also perform a preliminary quality check on these data to ensure the accuracy and integrity of the data;

[0065] The edge computing module is used to preliminarily analyze and screen the charging power data using edge computing algorithms to obtain key data, including data that exceeds the threshold and shows abnormal trends;

[0066] The edge computing algorithm includes the following steps:

[0067] Data preprocessing: Receive charging data from the data acquisition module, and perform denoising, formatting, and outlier detection on the received data;

[0068] Feature extraction: Extract features related to the charging power from the preprocessed data, including instantaneous value, average value, maximum value, minimum value, and change rate of the charging power;

[0069] Threshold judgment: Set the charging power threshold. When the charging power data exceeds or is lower than the threshold, it indicates that the charging pile is in an abnormal state or there are problems during the charging process;

[0070] Trend analysis: Analyze the change trend of the charging power data. When the data shows abnormal fluctuations or sudden changes, it indicates that the charging pile is experiencing a fault or abnormal situation;

[0071] Data screening: Obtain key data by screening the charging power data;

[0072] Data upload and storage: Upload the screened key data to the processing background, and store the original data and screening results in the local storage of the charging pile;

[0073] The edge computing algorithm has real-time, high-efficiency, and scalability. The edge computing algorithm can process data in real-time at the front end of the charging pile, reduce data transmission latency, improve the system response speed. Through preliminary analysis and screening, the edge computing algorithm can reduce the data processing pressure on the back-end platform, improve the overall system efficiency, and can also be extended and optimized according to actual needs to adapt to different charging pile models and charging scenarios.

[0074] The data compression module is used to receive the already screened key data and perform compression processing on the key data. The data compression module uses lossless compression technology and can compress the data without losing any original data information. It mainly achieves the compression effect by removing redundant information in the data (such as duplicate data blocks, invalid codes, etc.);

[0075] Through the data compression module, the data transmission volume can be reduced, the occupancy of network bandwidth and transmission cost can be lowered, the efficiency and reliability of data transmission can be improved. At the same time, the compressed data is also easier to store and manage, which helps to reduce storage costs and improve data security.

[0076] The data transmission module is used to transmit the key data after compression processing to the data parsing module in the processing background;

[0077] The data transmission module uses the TCP / IP protocol to transmit data. The TCP / IP protocol has a powerful error detection and recovery mechanism, which can ensure the integrity and accuracy of data during transmission;

[0078] Before data transmission, the identity authentication mechanism is used to verify the legality of the sender and receiver, and the authorization mechanism is used to restrict the access rights to data, preventing unauthorized access and leakage;

[0079] At the same time, a detailed log record and monitoring of the data transmission process are carried out to promptly detect and handle any abnormal behavior or potential security threats.

[0080] The data parsing module is used to receive compressed data from different charging piles and different types, and convert it into a unified data encoding format;

[0081] The data parsing module first receives the compressed data packet, and then calls the corresponding decompression algorithm to decompress the data packet. The compressed data is restored to its original, uncompressed data format, and then the data is converted into a unified data encoding format. The specific steps include:

[0082] Data reception: The data parsing module first receives the compressed data packet sent by the data transmission module;

[0083] Decompression processing: After receiving the compressed data packet, the data parsing module will call the corresponding decompression algorithm to decompress the data packet. The purpose of this step is to restore the compressed data to its original, uncompressed data format. The selection of the decompression algorithm should match the compression algorithm used in the data compression module to ensure the accurate restoration of data;

[0084] Data format conversion: After decompression is completed, the data parsing module also needs to perform format conversion processing on the data. Since the original data may be stored and transmitted in a specific encoding or format, the data parsing module needs to convert this data into a format that can be recognized and processed by the backend platform. This step usually involves operations such as data decoding, recombination of decoded data, and conversion of data types;

[0085] Data verification and validation: To ensure the accuracy and integrity of data, the data parsing module will also perform data verification and validation during the parsing process. This includes integrity checks of data (such as checksums, hash values, etc.) and logical consistency verification of data (such as data range, data type, etc.). Through these verification and validation steps, the data parsing module can promptly detect and handle any data errors or abnormalities, ensuring the accuracy and reliability of subsequent analysis.

[0086] The intelligent analysis module is used to analyze the parsed data using prediction algorithms to predict the changes in grid load and the charging demand of electric vehicles;

[0087] Based on historical data and current trends, the intelligent analysis module predicts future grid load changes, which helps grid operators adjust power supply strategies in advance, ensure the stable operation of the grid, and avoid possible power shortages or surpluses;

[0088] By analyzing the charging behavior, usage patterns of electric vehicles, and the distribution of charging facilities, the intelligent analysis module predicts the charging demand of electric vehicles, which helps optimize the layout of charging facilities, improve charging efficiency, and meet user needs;

[0089] The prediction algorithm includes the following steps:

[0090] Data collection: Collect historical data from charging piles and grid operators, and perform cleaning and preprocessing. This step ensures the quality and consistency of the data and provides a reliable basis for subsequent model training;

[0091] Model construction: Build a prediction model and train machine learning algorithms using historical data. During the training process, the prediction model learns the patterns and trends in the data and adjusts the model parameters to minimize the prediction error. Among them: for grid load prediction, time series analysis, linear regression, or neural network algorithms are used; for electric vehicle charging demand prediction, classification algorithms, clustering algorithms, or association rule mining, etc. are used;

[0092] Model evaluation and optimization: Evaluate the prediction model through cross-validation, confusion matrix, and ROC curve. According to the evaluation results, optimize and adjust the model to improve its prediction accuracy;

[0093] Prediction and result analysis: Apply the trained prediction model to new data, generate prediction results, and conduct in-depth analysis of the prediction results to reveal the potential patterns and trends in the data and provide a scientific basis for decision-making;

[0094] The power allocation module is used to formulate an optimal charging power allocation plan based on the results of the intelligent analysis module;

[0095] The charging power allocation plan includes:

[0096] Charging pile power allocation: For each charging pile, allocate a reasonable charging power according to its current charging demand, historical charging records, and the load situation of the grid;

[0097] Grid load balance: When allocating charging power, take into account the grid load balance;

[0098] Priority setting: Allocate the charging power according to specific priority settings;

[0099] Dynamic adjustment strategy: Dynamically adjust the allocation plan according to the real-time analysis results of the intelligent analysis module;

[0100] The basis for formulating the optimal charging power is:

[0101] Results of the intelligent analysis module: The intelligent analysis module can predict the grid load changes and electric vehicle charging demands through the analysis of historical data and real-time monitoring data. The power allocation decision module will formulate a reasonable charging power allocation plan according to these prediction results;

[0102] Charging capacity of the charging pile: Each charging pile has its specific charging capacity. When formulating the allocation plan, the power allocation decision module will consider the charging capacity of the charging pile to ensure that the allocated power does not exceed its bearing range;

[0103] Grid load conditions: The grid load conditions have an important impact on the allocation of charging power. The power allocation decision module will dynamically adjust the allocation of charging power according to the real-time load conditions of the grid to maintain the stable operation of the grid;

[0104] User needs and priorities: The user needs and priorities are also factors to be considered when formulating the charging power allocation plan. For example, for electric vehicles in urgent need of charging or charging piles during special periods, higher priorities and more charging power will be given.

[0105] In one embodiment, it further includes an instruction issuing module and an execution module. The signal terminal of the instruction issuing module is connected to the signal terminal of the execution module;

[0106] The instruction issuing module is used to issue the instructions of the power allocation decision module to the execution module, and the execution module is used to adjust the charging power of the charging pile.

[0107] In one embodiment, it further includes a status monitoring module and an early warning module. The signal terminal of the status monitoring module is connected to the signal terminal of the early warning module;

[0108] The status monitoring module is used to monitor the operating status of the charging pile and the load conditions of the background in real time. When an abnormal situation is detected, it sends a signal to the early warning module. When the early warning module receives the abnormal signal, it automatically triggers the alarm mechanism;

[0109] The triggering conditions of the alarm mechanism include:

[0110] Equipment failure: When a failure occurs in the charging pile or related equipment, such as abnormal power or communication interruption, the alarm mechanism will be triggered;

[0111] Grid load anomaly: When the grid load is too high or too low and exceeds the preset safe range, the alarm mechanism will also be activated;

[0112] Security threats: When potential security threats such as illegal access and malicious attacks are detected, the alarm mechanism will respond immediately;

[0113] Data anomaly: During data parsing or intelligent analysis, if abnormal data such as data loss and data inconsistency is found, it may also trigger the alarm mechanism;

[0114] Once the alarm mechanism is triggered, the system will process according to the following process:

[0115] Alarm information recording: First, the system will record the alarm information, including the triggering conditions, alarm time, alarm location, etc.;

[0116] Automatic processing measures: According to the preset rules and strategies, the system will automatically take some preliminary processing measures, such as cutting off the power supply and starting standby equipment;

[0117] Manual intervention: If the automatic processing measures cannot solve the problem, the system will notify the relevant personnel for manual intervention. The operation and maintenance personnel will go to the site or remotely conduct fault troubleshooting and handling according to the alarm information;

[0118] Problem tracking and feedback: During the entire processing process, the system will track the processing progress of the problem and send feedback information to the relevant personnel after the problem is solved.

[0119] An intelligent charging pile power dynamic allocation method includes the following steps:

[0120] Step 1: Obtain the charging power data of the charging pile. The charging power data includes current, voltage, power, and temperature;

[0121] Step 2: Initially analyze and screen the charging power data to obtain key data. The key data includes data that exceeds the threshold and shows an abnormal trend;

[0122] Step 3: Compress the key data and transmit the compressed key data to the processing background;

[0123] Step 4: The processing background receives the compressed data from different charging piles and different types and converts it into a unified data coding format;

[0124] Step 5: Use the prediction algorithm to analyze the parsed data, predict the grid load change and the electric vehicle charging demand, and formulate the optimal charging power allocation plan according to the prediction results;

[0125] Step 6: Send the instructions of the power allocation decision module to the execution module in the charging pile, and the execution module adjusts the charging power of the charging pile.

[0126] When the present invention is in operation: the charging power data of the charging pile, including current, voltage, power, and temperature, is obtained through the data acquisition module. Then, the data compression module preliminarily analyzes and screens the charging power data to obtain key data, including data that exceeds the threshold and shows an abnormal trend. The key data is compressed by the data transmission module and the compressed key data is transmitted to the processing background. The processing background receives compressed data from different charging piles and different types, and converts it into a unified data coding format through the data parsing module. The intelligent analysis module analyzes the parsed data through a prediction algorithm to predict the change of the power grid load and the charging demand of electric vehicles, formulates an optimal charging power allocation plan according to the prediction results, and finally issues the instruction of the power allocation decision module to the execution module in the charging pile, and the execution module adjusts the charging power of the charging pile.

[0127] As mentioned above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claimed rights.

Claims

1. A smart charging pile power supply dynamic allocation system, including a data acquisition module, an edge computing module, a data compression module, a data transmission module, a data analysis module, an intelligent analysis module and a power allocation decision module, characterized in that: The signal ends of the data acquisition module, edge computing module, data compression module, data transmission module, data parsing module, intelligent analysis module and power allocation decision module are connected in sequence; The data acquisition module is used to collect charging power data of the charging pile in real time through sensors, wherein the charging power data includes current, voltage, power and temperature, and the sensors include current sensors, voltage sensors, power sensors and temperature sensors; The edge computing module is used to use an edge computing algorithm to perform preliminary analysis and screening on the charging power data to obtain key data, wherein the key data includes data that exceeds a threshold and presents an abnormal trend; The data compression module is used to receive the selected key data and compress the key data; The data transmission module is used to transmit the compressed key data to the data analysis module in the processing background; The data parsing module is used to receive compressed data from different charging piles and different types, and convert it into a unified data encoding format; The intelligent analysis module is used to analyze the parsed data using a prediction algorithm to predict changes in grid load and electric vehicle charging demand. The intelligent analysis module predicts future grid load changes based on historical data and current trends. The intelligent analysis module analyzes the charging behavior, usage patterns, and distribution of charging facilities of electric vehicles to predict the charging demand of electric vehicles. The power allocation module is used to formulate an optimal charging power allocation plan based on the results of the intelligent analysis module.

2. According to claim 1, a smart charging pile power supply dynamic allocation system is characterized by: The current sensor is used to monitor the magnitude and direction of the output current of the charging pile; The voltage sensor is used to monitor the output voltage of the charging pile; The power sensor is used to calculate the power value output by the charging pile, and calculates the real-time power value by combining the measurement results of current and voltage; The temperature sensor is used to monitor the temperature of the charging pile.

3. According to claim 1, a smart charging pile power supply dynamic allocation system is characterized by: The edge computing algorithm comprises the following steps: Data preprocessing: receiving charging data from the data acquisition module, and performing denoising, formatting, and outlier detection on the received data; Feature extraction: Extract features related to charging power from the preprocessed data, including the instantaneous value, average value, maximum value, minimum value, and change rate of charging power; Threshold judgment: Set the charging power threshold. When the charging power data exceeds or falls below the threshold, it means that the charging pile is in an abnormal state or there is a problem in the charging process. Trend analysis: Analyze the changing trend of charging power data. When the data shows abnormal fluctuations or sudden changes, it means that the charging pile is experiencing a fault or abnormal situation. Data screening: Get key data by screening charging power data; Data upload and storage: upload the filtered key data to the processing background, and store the original data and filtered results in the local storage of the charging pile.

4. The intelligent charging pile power supply dynamic allocation system according to claim 1 is characterized in that: The data transmission module uses the TCP / IP protocol to transmit data. Before data transmission, the identity of the sender and receiver is verified to be legitimate through an identity authentication mechanism, and access rights to the data are restricted through an authorization mechanism. At the same time, the data transmission process is logged and monitored in detail to promptly detect and handle any abnormal behavior or potential security threats.

5. According to claim 1, a smart charging pile power supply dynamic allocation system is characterized by: The data parsing module first receives a compressed data packet, then calls a corresponding decompression algorithm to decompress the data packet, restores the compressed data to its original, uncompressed data format, and then converts the data into a unified data encoding format.

6. The intelligent charging pile power supply dynamic allocation system according to claim 1 is characterized in that: The prediction algorithm comprises the following steps: Data collection: Collect historical data from charging piles and grid operators, and perform cleaning and preprocessing; Model building: Build a predictive model and use historical data to train the machine learning algorithm. During the training process, the predictive model learns the patterns and trends in the data and adjusts the model parameters to minimize the prediction error; Model evaluation and optimization: Evaluate the prediction model through cross-validation, confusion matrix, and ROC curve, and optimize and adjust the model based on the evaluation results; Prediction and result analysis: Apply the trained prediction model to new data to generate prediction results.

7. The intelligent charging pile power supply dynamic allocation system according to claim 1 is characterized by: The charging power allocation scheme includes: Charging pile power allocation: For each charging pile, reasonable charging power is allocated according to its current charging demand, historical charging records and grid load conditions; Grid load balance: When allocating charging power, the load balance of the grid is taken into account; Priority setting: Allocate charging power according to specific priority settings; Dynamic adjustment strategy: Dynamically adjust the allocation plan based on the real-time analysis results of the intelligent analysis module.

8. The intelligent charging pile power supply dynamic allocation system according to claim 1 is characterized by: It also includes an instruction issuing module and an execution module, wherein the signal end of the instruction issuing module is connected to the signal end of the execution module; The instruction issuing module is used to issue the instruction of the power allocation decision module to the execution module, and the execution module is used to adjust the charging power of the charging pile.

9. The intelligent charging pile power supply dynamic allocation system according to claim 1 is characterized in that: It also includes a status monitoring module and an early warning module, wherein the signal end of the status monitoring module is connected to the signal end of the early warning module; The status monitoring module is used to monitor the operating status of the charging pile and process the load status of the background in real time. When an abnormal situation is detected, a signal is sent to the early warning module. When the early warning module receives the abnormal signal, it automatically triggers the alarm mechanism.

10. A method for dynamically allocating power supply of a smart charging pile, applied to the system for dynamically allocating power supply of a smart charging pile as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Obtain charging power data of the charging pile, wherein the charging power data includes current, voltage, power, and temperature; Step 2: Preliminary analysis and screening of charging power data to obtain key data, including data exceeding a threshold and showing an abnormal trend; Step 3: compress the key data and transmit the compressed key data to the processing background; Step 4: The processing background receives compressed data from different charging piles and different types, and converts it into a unified data encoding format; Step 5: Use the prediction algorithm to analyze the parsed data, predict the grid load changes and electric vehicle charging needs, and formulate the optimal charging power allocation plan based on the prediction results; Step 6: Send the instruction of the power allocation decision module to the execution module in the charging pile, and the execution module adjusts the charging power of the charging pile.

Images