Cloud platform-based electric vehicle charging pile intelligent management method and system

Abstract

This application provides a cloud-based intelligent management method and system for electric vehicle charging piles, relating to the field of charging pile management technology. The method includes: acquiring charging pile status datasets and vehicle charging demand datasets in real time using a cloud platform; making charging control decisions based on the charging pile status datasets and vehicle charging demand datasets to determine a charging scheduling scheme; simultaneously acquiring updated charging pile data and vehicle status data while executing the charging scheduling scheme; and adjusting the charging scheduling scheme based on the updated charging pile data and vehicle status data. This application solves the technical problem in existing technologies where charging pile resource scheduling is typically based on the idle status of charging piles, leading to uneven use of charging pile resources, excessively long user waiting times, and further affecting the efficiency of charging pile utilization. By combining a cloud platform to dynamically generate charging scheduling schemes and adjusting the schemes based on real-time feedback, the efficiency of charging pile utilization is improved.

Description

Technical Field

[0001] This application relates to the field of charging pile management technology, specifically to a cloud-based intelligent management method and system for electric vehicle charging piles. Background Technology

[0002] Currently, the resource scheduling of electric vehicle charging stations largely relies on the idle status of charging stations to allocate charging tasks. While this scheduling method is simple and easy to implement, it often leads to uneven use of charging station resources due to the lack of comprehensive consideration of multiple factors such as charging station load, battery charging status, and charging demand. Some charging stations become overloaded during peak demand periods, while others remain idle, resulting in resource waste and excessively long waiting times for users. This not only affects the efficiency of charging station utilization but also reduces the user's charging experience. The difficulty in dynamically optimizing resource scheduling based on real-time charging demand and charging station status leads to unreasonable resource allocation during peak charging periods, impacting the overall operational efficiency of charging stations.

[0003] In summary, existing technologies suffer from the technical problem that charging pile resource scheduling is usually based on the idle status of charging piles, which leads to uneven use of charging pile resources, excessively long waiting times for users, and further affects the efficiency of charging pile utilization. Summary of the Invention

[0004] The purpose of this application is to provide a cloud-based intelligent management method and system for electric vehicle charging piles, in order to solve the technical problems in the prior art where charging pile resource scheduling is usually based on the idle state of the charging piles, resulting in uneven use of charging pile resources, excessively long waiting times for users, and further affecting the efficiency of charging pile use.

[0005] To achieve the above objectives, this application provides a cloud-based intelligent management method and system for electric vehicle charging piles.

[0006] Firstly, this application provides a cloud-based intelligent management method for electric vehicle charging piles. This method is implemented through a cloud-based intelligent management system for electric vehicle charging piles. The cloud-based intelligent management method includes: acquiring charging pile status datasets and vehicle charging demand datasets in real time using a cloud platform; making charging control decisions based on the charging pile status datasets and vehicle charging demand datasets to determine a charging scheduling scheme; simultaneously acquiring updated charging pile data and updated vehicle status data while executing the charging scheduling scheme; and adjusting the charging scheduling scheme based on the updated charging pile data and updated vehicle status data.

[0007] Optionally, the edge acquisition module deployed at the charging pile can be interacted with to obtain the charging pile status dataset; and the user terminal can be interacted with to obtain the vehicle charging demand dataset.

[0008] Optionally, the charging pile status dataset and the vehicle charging demand dataset are subjected to timestamp alignment and data standardization to obtain a structured charging vector; a charging scheduling historical log set is loaded according to the cloud platform; a charging control decision network is trained according to the charging scheduling historical log set; and the structured charging vector is input into the charging control decision network to obtain the charging scheduling scheme.

[0009] Optionally, anomaly detection is performed based on the updated charging pile data to obtain charging pile anomaly characteristics; charging anomaly risk assessment is performed based on the charging pile anomaly characteristics to obtain a first charging anomaly risk coefficient; if the first charging anomaly risk coefficient is greater than or equal to the charging anomaly risk threshold, the charging scheduling scheme is adjusted based on the charging pile anomaly characteristics.

[0010] Optionally, anomaly detection is performed based on the vehicle status update data to obtain vehicle anomaly characteristics; charging anomaly risk assessment is performed based on the vehicle anomaly characteristics to obtain a second charging anomaly risk coefficient; if the second charging anomaly risk coefficient is greater than or equal to the charging anomaly risk threshold, the charging scheduling scheme is adjusted based on the vehicle anomaly characteristics.

[0011] Optionally, if the first risk coefficient of the charging anomaly is greater than or equal to the risk threshold of the charging anomaly, a charging pile early warning signal is generated.

[0012] Optionally, if the second risk coefficient of the charging anomaly is greater than or equal to the risk threshold of the charging anomaly, a vehicle warning signal is generated.

[0013] Secondly, this application also provides a cloud-based intelligent management system for electric vehicle charging piles, used to execute the cloud-based intelligent management method for electric vehicle charging piles as described in the first aspect. The cloud-based intelligent management system for electric vehicle charging piles includes: a data acquisition module, used to acquire charging pile status datasets and vehicle charging demand datasets in real time based on the cloud platform; a charging control decision module, used to make charging control decisions based on the charging pile status datasets and the vehicle charging demand datasets to determine a charging scheduling scheme; a data update acquisition module, used to simultaneously acquire updated charging pile data and updated vehicle status data when executing the charging scheduling scheme; and a charging management module, used to provide feedback adjustments to the charging scheduling scheme based on the updated charging pile data and the updated vehicle status data.

[0014] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0015] By acquiring charging pile status datasets and vehicle charging demand datasets in real time through a cloud platform, and making charging control decisions based on these datasets to determine a charging scheduling scheme, the system simultaneously acquires updated charging pile and vehicle status data during the execution of the scheduling scheme. Furthermore, the system provides feedback adjustments to the charging scheduling scheme based on these updated data. In other words, by dynamically scheduling charging tasks using charging pile status and vehicle charging demand datasets acquired through a cloud platform, and by simultaneously acquiring updated charging pile and vehicle status data and dynamically adjusting the charging scheduling scheme based on feedback information, the system improves the utilization efficiency of charging piles, maximizes resource utilization, and reduces idle and queuing times.

[0016] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the intelligent management method for electric vehicle charging piles based on a cloud platform according to this application.

[0019] Figure 2 This is a schematic diagram of the structure of the cloud-based intelligent management system for electric vehicle charging piles in this application.

[0020] Explanation of reference numerals in the attached diagram: Data acquisition module 11, charging control decision module 12, data update acquisition module 13, charging management module 14. Detailed Implementation

[0021] This application provides a cloud-based intelligent management method and system for electric vehicle charging piles, solving the technical problem in existing technologies where charging pile resource scheduling is typically based on the idle status of charging piles, leading to uneven use of charging pile resources, excessively long user waiting times, and further impacting charging pile utilization efficiency. By acquiring charging pile status datasets and vehicle charging demand datasets through a cloud platform for dynamic scheduling of charging tasks, and simultaneously acquiring updated charging pile and vehicle status data, the application dynamically adjusts the charging scheduling scheme based on feedback information, thereby improving charging pile utilization efficiency, maximizing resource utilization, and reducing idle and queuing times.

[0022] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0023] Example 1, please refer to the appendix. Figure 1 This application provides a cloud-based intelligent management method for electric vehicle charging piles, wherein the cloud-based intelligent management method for electric vehicle charging piles is applied to a cloud-based intelligent management system for electric vehicle charging piles, and the cloud-based intelligent management method for electric vehicle charging piles specifically includes the following steps:

[0024] S100: Based on the cloud platform, it obtains charging pile status datasets and vehicle charging demand datasets in real time.

[0025] Furthermore, S100 of this application includes: interacting with an edge acquisition module deployed at the charging pile to obtain the charging pile status dataset; and interacting with a user terminal to obtain the vehicle charging demand dataset.

[0026] Specifically, the edge acquisition module of a charging pile collects real-time status data from the charging pile using sensors and hardware devices. Sensors, such as current sensors, temperature sensors, and power sensors, are installed in the electrical components of the charging pile to collect real-time status information such as current, voltage, load, and temperature. The edge computing module processes the data collected by the sensors locally, determining whether the data meets preset threshold requirements, such as triggering an alarm when the voltage is too high or the current is overloaded. Then, the processed data is uploaded to a cloud platform or central control system for further decision analysis. The charging pile status data includes historical and real-time data, stored in the edge computing device or cloud platform database. Edge computing is a technology that processes data near the data source (such as at the charging pile itself). The edge acquisition module is a hardware device or system installed at the charging pile, responsible for collecting and processing the charging pile's status data (such as power, temperature, and load) in real time, and transmitting the data to a higher-level computing system for further analysis and decision-making. The charging pile status dataset includes the charging pile's operational data, such as voltage, current, temperature, load, battery health status, and fault information, which helps to understand the current working status of the charging pile.

[0027] Interactive user terminals, such as mobile phones, smart apps, or in-vehicle systems, allow users to input charging needs or check the status of charging stations. Users input their charging needs via mobile apps or in-vehicle systems, including selecting a charging station, specifying charging power, and battery level, and a charging task is generated based on these needs. The user terminal transmits the charging need data to a cloud platform or control system via the internet or other communication methods, and the charging task is scheduled based on this data. The user terminal receives feedback information after scheduling, such as the charging station's availability, estimated charging time, and charging cost, allowing users to further operate or adjust their needs.

[0028] The edge acquisition module at the charging pile exchanges data with the user terminal via a cloud platform or direct communication. The status data at the charging pile provides the basis for charging task scheduling, while user demand data determines the scheduling priority and the selection of charging piles. By acquiring real-time status data of charging piles and user charging demand data, the system avoids situations where some charging piles are overloaded while others are idle, ensuring the rational use of charging piles.

[0029] S200: Make charging control decisions based on the charging pile status dataset and the vehicle charging demand dataset, and determine the charging scheduling scheme.

[0030] Furthermore, S200 of this application includes: performing timestamp alignment and data standardization processing on the charging pile status dataset and the vehicle charging demand dataset to obtain a structured charging vector; loading a charging scheduling historical log set according to the cloud platform; training a charging control decision network according to the charging scheduling historical log set; and inputting the structured charging vector into the charging control decision network to obtain the charging scheduling scheme.

[0031] Specifically, since charging pile status data and vehicle charging demand data come from different sources and may be collected at different times, the first step is to align these data with timestamps. This involves matching the charging pile status data and the electric vehicle charging demand data using timestamps, ensuring that each charging task is compared with the corresponding charging pile status within the same time period. For example, if charging pile data is collected every 10 seconds, while vehicle charging demand data is uploaded every 5 minutes, timestamp alignment unifies the time points of both, guaranteeing that each charging demand data corresponds to the accurate charging pile status data. Timestamp alignment is necessary because data collected at different times may have time differences; therefore, data from different sources (such as charging pile and vehicle demand data) needs to be unified to the same timestamp for comparison and processing.

[0032] The aligned data undergoes standardization to adjust it to a uniform range, such as mapping voltage and current values ​​to the 0-1 interval. Data standardization unifies data from different scales into a standardized range, such as 0 to 1, to facilitate unified processing and calculation. The structured charging vector is a structured data representation containing charging tasks and charging pile status, obtained by aligning and standardizing charging pile status data and vehicle charging demand data through timestamps.

[0033] Based on the cloud platform, the historical charging scheduling log set is retrieved, which records the historical dataset of past charging pile scheduling, including scheduling decisions, completion status of charging tasks, and changes in charging pile status over a period of time. The loaded historical charging scheduling log data is used to train the charging control decision network. The historical charging scheduling log set is cleaned and formatted to ensure it is structured and suitable for training the model. Missing values ​​and outlier data are deleted or corrected. For example, if voltage or current data for some charging piles is missing, interpolation or averaging is required; timestamp alignment ensures that each charging task is aligned with the corresponding charging pile status data in time; standardization processing standardizes or normalizes all numerical data, such as normalizing current, voltage, and battery power data to the [0,1] range to avoid scale differences between data affecting model training.

[0034] Based on the nature of the charging scheduling problem, reinforcement learning, specifically a deep Q-network, is chosen for training. During training, the environment represents the charging station scheduling process. A state space, action space, and reward function are defined. The state space includes the charging station's state (e.g., voltage, current, load, temperature) and the electric vehicle's charging needs (e.g., battery level, charging power). The action space includes the charging scheduling decisions, such as which charging station to assign the task to and the allocation of charging power. The reward function reflects the quality of the scheduling decisions. Common designs are based on factors such as charging station resource utilization, timely completion of charging tasks, and user waiting time. The goal is to minimize overload and user waiting time through training.

[0035] Define a deep neural network as the Q-value network. The input includes the current state of the environment, the charging station status, and battery charging demand data. The output is the Q-value for each possible action, representing the expected long-term reward for performing that action. The input layer consists of the charging station status (current, voltage, load, etc.) and battery charging demand data (battery capacity, power demand, etc.). The hidden layers consist of multiple fully connected neural networks used to extract features from the input data. The output layer is the Q-value corresponding to each charging scheduling action. Initialize the weight parameters of the Q-network. Select an action based on the current state, such as selecting a charging station and allocating charging power, then execute the action to obtain the next state and reward. Calculate the Q-value using the Bellman equation. Update the Q-network parameters based on the calculated Q-value; the Adam optimization algorithm is commonly used. To ensure effective network training, an ε-greedy strategy is typically employed: selecting a random action (exploration) with probability ε and selecting the action with the highest current Q-value (utilization) with probability 1-ε. As training progresses, gradually decrease ε to increase network utilization. Repeat the above steps until the Q-network converges. In each iteration, the network minimizes the overall scheduling cost of the system by continuously optimizing its decision-making strategy. During training, selecting appropriate hyperparameters is crucial, including the learning rate, discount factor, decay rate of ε, and the neural network structure (number of hidden layers and nodes). After training, the performance of the trained Q-network is evaluated using test set data. Evaluation criteria include: whether the charging pile load balancing successfully avoids overload, whether users complete all charging tasks in the shortest possible time, and whether the utilization rate of charging pile resources is reasonable. Based on the evaluation results, if the model performance is unsatisfactory, it can be optimized. For example, by adjusting the Q-network structure, reward function, or further optimizing hyperparameters during training, such as the learning rate and discount factor.

[0036] After standardization and timestamp alignment, the charging pile status data and vehicle charging demand data are combined into a structured charging vector, which is then fed into the trained charging control decision network. Based on the input structured charging vector, the charging control decision network generates a charging scheduling scheme, determines the allocation of charging tasks, the selection of charging piles, the power and duration of each charging task, etc., to ensure that the charging piles are load-balanced and meet the user's charging needs.

[0037] Through timestamp alignment and data standardization, the status data of charging piles and the charging demand data of vehicles are aligned on the same timeline, and standardization ensures the uniformity and comparability of data processing. Based on the charging scheduling historical logs loaded on the cloud platform, the trained decision network can achieve intelligent scheduling through structured charging vectors, optimize the allocation of charging pile resources, improve charging efficiency, reduce user waiting time, avoid resource overload, and ensure the smooth completion of charging tasks. This not only improves the utilization efficiency of charging piles but also provides users with a more convenient charging experience.

[0038] S300: When executing the charging scheduling scheme, simultaneously acquire charging pile update data and vehicle status update data.

[0039] Specifically, after obtaining the charging schedule, the charging task begins. Charging stations are allocated to electric vehicles according to the predetermined charging plan, and the charging power and time are set. During this process, the charging stations begin to provide the corresponding power output, and the electric vehicle's battery begins to charge.

[0040] During charging, the charging station's status changes dynamically, including voltage, current, and load. To ensure smooth charging, the charging station's status is monitored in real time. The charging station continuously collects its own operating status information, such as voltage, current, and temperature, through built-in sensors and a control system. This updated data is uploaded in real time to the control system via a communication interface with a cloud platform or local management system. Continuous monitoring of the charging station's load and current changes ensures it is operating normally. If the charging station experiences overload, overheating, or other abnormalities, immediate measures are taken, such as reducing charging power or rescheduling to another charging station.

[0041] Meanwhile, the charging status of electric vehicles is constantly changing. To understand the charging progress in real time and obtain updated status data, the vehicle's communication system, such as an onboard intelligent charging management system or an app, periodically reports charging progress information, such as battery level, charging power, and charging time, to the cloud platform or management system. Based on the vehicle's charging status, it is determined whether the charging power needs to be adjusted, the charging time extended, or other charging stations reassigned to optimize the charging process.

[0042] During the charging process, the status data of both the charging station and the vehicle changes in real time. Therefore, the charging strategy is dynamically adjusted by synchronously acquiring this data. For example, if a charging station malfunctions or is overloaded, the charging task is automatically reassigned based on the real-time updated charging station data, selecting other charging stations with lower loads. Simultaneously, if a vehicle's charging progress is faster than expected—for example, a faster charging speed or more efficient battery charging—the charging power is adjusted accordingly to improve charging efficiency. By synchronously monitoring the status of both the charging station and the vehicle, charging scheduling is optimized in real time, improving the efficiency of the entire charging process.

[0043] By synchronously acquiring status update data of charging piles and vehicles, the charging process can be monitored in real time, and the charging power can be adjusted in a timely manner to avoid overloading of charging piles, ensure that charging tasks are completed on time, improve charging efficiency, reduce resource waste, and provide users with a better charging experience.

[0044] S400: Adjust the charging scheduling scheme based on the updated charging pile data and the updated vehicle status data.

[0045] Furthermore, S400 of this application includes: performing anomaly detection based on the updated charging pile data to obtain charging pile anomaly characteristics; performing charging anomaly risk assessment based on the charging pile anomaly characteristics to obtain a first charging anomaly risk coefficient; and if the first charging anomaly risk coefficient is greater than or equal to the charging anomaly risk threshold, performing feedback adjustment on the charging scheduling scheme based on the charging pile anomaly characteristics.

[0046] Furthermore, this application also includes the following steps: if the first risk coefficient of charging abnormality is greater than or equal to the risk threshold of charging abnormality, a charging pile early warning signal is generated.

[0047] Specifically, during the charging process, the charging station continuously outputs status data. These parameters are analyzed through real-time data monitoring to detect potential anomalies. Statistical analysis or machine learning methods are typically used to identify anomalies in the data. For example, if the charging station's current suddenly exceeds the set maximum value, or if the temperature sensor reads a temperature value exceeding a safe range, such as above 70°C, these are considered abnormal signals. By comparing and analyzing the charging station's status data, abnormal characteristics are extracted. These include, for example, sudden current increases, frequent load fluctuations, and excessively high temperatures.

[0048] A risk assessment will be conducted based on the abnormal characteristics of the charging pile, such as overload, large current fluctuations, and excessively high temperatures. A primary risk coefficient for charging anomalies will be calculated by setting weights and rules. Each abnormal characteristic of the charging pile will be assigned a different weight; for example, overload will account for 40%, excessively high temperature for 30%, and load fluctuation for 30%. These abnormal characteristics will be combined according to their weights to form a comprehensive risk coefficient.

[0049] By analyzing the abnormal characteristics of charging piles, the potential risks during the charging process are assessed, resulting in a first risk coefficient for charging anomalies. This coefficient measures the current level of risk associated with the charging pile and is typically composed of weighted combinations of multiple abnormal characteristics. A higher value indicates a higher risk of charging pile anomalies.

[0050] The charging anomaly risk threshold is a preset standard value. When the anomaly risk coefficient of a charging pile exceeds this threshold, it indicates a significant anomaly risk, requiring intervention and adjustment. When the first charging anomaly risk coefficient exceeds or equals the preset risk threshold, the original charging scheduling plan is adjusted based on the anomaly characteristics of the charging pile. This includes adjusting charging tasks, such as reducing charging power, changing charging pile allocation, or switching to a backup charging pile.

[0051] If the first risk factor for a charging anomaly exceeds a set threshold, a warning signal for the charging station will be automatically generated. When the risk factor exceeds the threshold, a warning signal will be sent to the maintenance or management personnel of the charging station, indicating a potential malfunction or risk that requires timely inspection and handling. Warning signals can be sent in various ways, such as via SMS, email, or system alerts. Maintenance personnel will respond quickly based on the warning signal, checking the charging station's operational status and performing necessary repairs or adjustments to prevent further malfunctions.

[0052] Real-time anomaly detection and risk assessment can identify potential charging pile malfunctions or overload risks in advance, thus preventing equipment damage or safety accidents. Dynamic adjustments to the charging scheduling plan based on risk coefficients prevent overload and resource waste, ensuring charging piles operate under reasonable load conditions. Generating charging pile early warning signals promptly notifies maintenance personnel, preventing risk amplification and improving fault response speed.

[0053] Furthermore, this application also includes the following steps: performing anomaly detection based on the vehicle status update data to obtain vehicle anomaly characteristics; performing charging anomaly risk assessment based on the vehicle anomaly characteristics to obtain a second charging anomaly risk coefficient; if the second charging anomaly risk coefficient is greater than or equal to the charging anomaly risk threshold, adjusting the charging scheduling scheme based on the vehicle anomaly characteristics.

[0054] Furthermore, this application also includes the following step: if the second risk coefficient of charging abnormality is greater than or equal to the risk threshold of charging abnormality, a vehicle warning signal is generated.

[0055] Specifically, during the charging process, electric vehicles provide real-time status data. This data is used for anomaly detection to identify abnormalities in the battery or the charging process. Predefined thresholds or machine learning algorithms are used to determine if any anomalies exist in the charging process. For example, if the battery charging speed is too slow, below the expected value, or the battery temperature is too high, exceeding 70°C, these are identified as abnormal situations. Abnormal fluctuations or trends in the detected data are used to extract anomalous features, such as slower-than-expected battery charge growth (characterized by a smaller increase in battery charge); excessively high battery temperature (characterized by excessively high temperature); and large fluctuations in charging power (characterized by power instability).

[0056] Based on the extracted abnormal vehicle characteristics, an assessment of charging anomaly risks is conducted. A second risk coefficient for charging anomalies is calculated based on anomalies in data such as battery charge growth, temperature, and charging power. Each abnormal vehicle characteristic is assigned a weight, and its contribution to the charging process risk is evaluated according to different anomaly types. For example, slow battery charge growth has a 40% risk weight; excessively high battery temperature has a 30% risk weight; and large fluctuations in charging power have a 30% risk weight.

[0057] If the calculated risk coefficient is greater than or equal to the preset charging anomaly risk threshold, the charging process is considered to have a high risk and requires adjustment. If the second risk coefficient for charging anomalies exceeds or equals the preset risk threshold, the charging scheduling plan is adjusted based on the vehicle's anomaly characteristics. The anomaly risk is mitigated by reducing charging power, extending charging time, or switching charging stations. For example, when the battery temperature is too high, the charging power is reduced; or when the charging power fluctuates significantly, the system switches to a stable charging station.

[0058] When the second risk coefficient for charging anomalies exceeds the charging anomaly risk threshold, a vehicle warning signal is generated. By analyzing whether the charging anomaly risk coefficient exceeds the threshold, if so, a warning signal is immediately generated and the user or staff is notified through various means, such as app push notifications, SMS, or email. Timely anomaly detection and feedback adjustments can prevent issues such as battery overheating and decreased charging efficiency, improving charging safety. By dynamically adjusting charging power and charging strategies, the battery charging environment is optimized in real time during charging, avoiding overload or instability.

[0059] In summary, the cloud-based intelligent management method for electric vehicle charging piles provided in this application has the following technical effects:

[0060] By acquiring charging pile status datasets and vehicle charging demand datasets in real time through a cloud platform, and making charging control decisions based on these datasets to determine a charging scheduling scheme, the system simultaneously acquires updated charging pile and vehicle status data during the execution of the scheduling scheme. Furthermore, the system provides feedback adjustments to the charging scheduling scheme based on these updated data. In other words, by dynamically scheduling charging tasks using charging pile status and vehicle charging demand datasets acquired through a cloud platform, and by simultaneously acquiring updated charging pile and vehicle status data and dynamically adjusting the charging scheduling scheme based on feedback information, the system improves the utilization efficiency of charging piles, maximizes resource utilization, and reduces idle and queuing times.

[0061] Example 2: Based on the same inventive concept as the cloud-based intelligent management method for electric vehicle charging piles in Example 1, this application also provides a cloud-based intelligent management system for electric vehicle charging piles. Please refer to the appendix. Figure 2 The cloud-based intelligent management system for electric vehicle charging piles includes:

[0062] The data acquisition module 11 is used to acquire charging pile status datasets and vehicle charging demand datasets in real time from the cloud platform; the charging control decision module 12 is used to make charging control decisions based on the charging pile status datasets and vehicle charging demand datasets to determine the charging scheduling scheme; the data update acquisition module 13 is used to synchronously acquire charging pile update data and vehicle status update data when executing the charging scheduling scheme; and the charging management module 14 is used to provide feedback adjustment to the charging scheduling scheme based on the charging pile update data and vehicle status update data.

[0063] Furthermore, the data acquisition module 11 in the cloud-based intelligent management system for electric vehicle charging piles is also used to: interact with the edge acquisition module deployed at the charging pile to acquire the charging pile status dataset; and interact with the user terminal to acquire the vehicle charging demand dataset.

[0064] Furthermore, the charging control decision module 12 in the cloud-based intelligent management system for electric vehicle charging piles is also used for: performing timestamp alignment and data standardization processing on the charging pile status dataset and the vehicle charging demand dataset to obtain a structured charging vector; loading a charging scheduling historical log set according to the cloud platform; training a charging control decision network according to the charging scheduling historical log set; and inputting the structured charging vector into the charging control decision network to obtain the charging scheduling scheme.

[0065] Furthermore, the charging management module 14 in the cloud-based intelligent management system for electric vehicle charging piles is also used for: performing anomaly detection based on the updated charging pile data to obtain charging pile anomaly characteristics; performing charging anomaly risk assessment based on the charging pile anomaly characteristics to obtain a first charging anomaly risk coefficient; and if the first charging anomaly risk coefficient is greater than or equal to the charging anomaly risk threshold, adjusting the charging scheduling scheme based on the charging pile anomaly characteristics.

[0066] Furthermore, the charging management module 14 in the cloud-based intelligent management system for electric vehicle charging piles is also used for: performing anomaly detection based on the vehicle status update data to obtain vehicle anomaly characteristics; performing charging anomaly risk assessment based on the vehicle anomaly characteristics to obtain a second charging anomaly risk coefficient; and if the second charging anomaly risk coefficient is greater than or equal to the charging anomaly risk threshold, adjusting the charging scheduling scheme based on the vehicle anomaly characteristics.

[0067] Furthermore, the charging management module 14 in the cloud-based intelligent management system for electric vehicle charging piles is also used to generate a charging pile early warning signal if the first risk coefficient of the charging anomaly is greater than or equal to the risk threshold of the charging anomaly.

[0068] Furthermore, the charging management module 14 in the cloud-based intelligent management system for electric vehicle charging piles is also used to generate a vehicle warning signal if the second risk coefficient of the charging anomaly is greater than or equal to the risk threshold of the charging anomaly.

[0069] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The cloud-based intelligent management method and specific examples of electric vehicle charging piles in the aforementioned Embodiment 1 are also applicable to the cloud-based intelligent management system of electric vehicle charging piles in this embodiment. Through the foregoing detailed description of the cloud-based intelligent management method of electric vehicle charging piles, those skilled in the art can clearly understand the cloud-based intelligent management system of electric vehicle charging piles in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0070] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0071] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A cloud platform-based intelligent management method for electric vehicle charging piles, characterized in that, include: Based on the cloud platform, real-time data sets of charging pile status and vehicle charging demand are obtained. Based on the charging pile status dataset and the vehicle charging demand dataset, charging control decisions are made to determine the charging scheduling scheme; When executing the charging scheduling scheme, charging pile update data and vehicle status update data are acquired simultaneously; The charging scheduling scheme is adjusted based on the updated charging pile data and the updated vehicle status data. 2.The cloud platform-based intelligent management method for electric vehicle charging piles according to claim 1, characterized in that, Based on the cloud platform, real-time data sets of charging pile status and vehicle charging demand are obtained, including: An edge acquisition module deployed at the charging pile terminal is used to acquire the charging pile status dataset. The user terminal interacts with the system to obtain the vehicle charging demand dataset. 3.The cloud platform-based intelligent management method for electric vehicle charging piles according to claim 1, characterized in that, Based on the charging pile status dataset and the vehicle charging demand dataset, charging control decisions are made to determine a charging scheduling scheme, including: The charging pile status dataset and the vehicle charging demand dataset are subjected to timestamp alignment and data standardization to obtain structured charging vectors; Based on the cloud platform, load the charging scheduling historical log set; Train the charging control decision network based on the charging scheduling history log set; The structured charging vector is input into the charging control decision network to obtain the charging scheduling scheme. 4.The cloud platform-based intelligent management method for electric vehicle charging piles according to claim 1, characterized in that, The charging scheduling scheme is adjusted based on the updated charging pile data and the updated vehicle status data, including: Anomaly detection is performed based on the updated charging pile data to obtain abnormal characteristics of the charging pile; Based on the abnormal characteristics of the charging pile, a charging anomaly risk assessment is performed to obtain the first risk coefficient of charging anomaly. If the first risk coefficient of the charging anomaly is greater than or equal to the risk threshold of the charging anomaly, the charging scheduling scheme is adjusted based on the characteristics of the charging pile anomaly.

5. The cloud platform-based intelligent management method for electric vehicle charging piles according to claim 1, characterized in that, The charging scheduling scheme is adjusted based on the updated charging pile data and the updated vehicle status data, including: Anomaly detection is performed based on the vehicle status update data to obtain abnormal vehicle characteristics; Based on the abnormal characteristics of the vehicle, a charging anomaly risk assessment is performed to obtain a second charging anomaly risk coefficient. If the second risk coefficient of charging anomaly is greater than or equal to the risk threshold of charging anomaly, the charging scheduling scheme is adjusted based on the characteristics of the vehicle anomaly.

6. The intelligent management method for electric vehicle charging piles based on a cloud platform as described in claim 4, characterized in that, If the first risk coefficient of the charging anomaly is greater than or equal to the risk threshold of the charging anomaly, a charging pile early warning signal is generated.

7. The intelligent management method for electric vehicle charging piles based on a cloud platform as described in claim 5, characterized in that, If the second risk coefficient of the charging anomaly is greater than or equal to the risk threshold of the charging anomaly, a vehicle warning signal is generated.

8. A cloud-based intelligent management system for electric vehicle charging piles, characterized in that: The steps for implementing the cloud-based intelligent management method for electric vehicle charging piles according to any one of claims 1 to 7, wherein the cloud-based intelligent management system for electric vehicle charging piles includes: The data acquisition module is used to acquire charging pile status datasets and vehicle charging demand datasets in real time from the cloud platform. The charging control decision module is used to make charging control decisions based on the charging pile status dataset and the vehicle charging demand dataset, and to determine the charging scheduling scheme. The data update acquisition module is used to synchronously acquire charging pile update data and vehicle status update data when executing the charging scheduling scheme. The charging management module is used to adjust the charging scheduling scheme based on the updated charging pile data and the updated vehicle status data.

Images