Charging pile charging abnormity real-time monitoring and early warning system of edge computing architecture

Abstract

The invention discloses a charging pile charging abnormity real-time monitoring and early warning system of an edge computing architecture, and relates to the field of new energy charging infrastructure, edge computing and intelligent safety management. Aiming at the problems of large delay and slow response of traditional cloud centralized monitoring, the system locally collects key data such as charging current and voltage through edge nodes, deploys an intelligent algorithm to identify anomalies such as over-current and over-temperature in real time, triggers sound-light alarm and remote pushing at a millisecond level, and synchronously links a cloud management platform and a visual operation and maintenance terminal. And multi-level collaborative early warning is realized. Through trial verification, the abnormal detection response time is only 0.2 second, the identification accuracy rate reaches 98.5%, the charging safety accident rate is reduced by 60%, and the operation and maintenance efficiency is improved by more than 30%. The system has been popularized in public charging stations, enterprise parks and other scenes, the safety risk is effectively reduced, and the real-time safety monitoring requirements of large-scale charging piles are met.

Description

Technical Field

[0001] This invention relates to the technical fields of new energy vehicle charging infrastructure, edge computing, intelligent monitoring, Internet of Things and artificial intelligence, specifically to a real-time monitoring and early warning system for charging pile anomalies based on an edge computing architecture, which falls under the category of intelligent operation and maintenance and safety management of charging piles. Background Technology

[0002] With the popularization of new energy vehicles, charging piles have been widely deployed as critical infrastructure. During actual operation, charging piles may experience charging anomalies due to factors such as equipment aging, environmental changes, improper user operation, and power grid fluctuations. These anomalies may include overcurrent, overvoltage, undervoltage, overtemperature, communication failures, and charging interruptions. Traditional charging anomaly monitoring systems mostly rely on centralized cloud processing, which suffers from problems such as large data transmission latency, poor real-time performance, high bandwidth pressure, and untimely anomaly response, making it difficult to meet the high security and real-time requirements of large-scale charging pile networks. Edge computing technology can push data processing and intelligent analysis down to edge nodes closer to the devices, enabling local real-time monitoring and rapid early warning of charging anomalies, effectively improving the system's response speed and security capabilities. Therefore, there is an urgent need for a real-time monitoring and early warning system for charging pile anomalies based on an edge computing architecture to achieve efficient, intelligent, and real-time management of charging anomalies. Summary of the Invention

[0003] This invention proposes a real-time monitoring and early warning system for charging pile anomalies based on an edge computing architecture. By deploying edge computing nodes at or near the charging pile, key data during the charging process is collected in real time. Local intelligent algorithms are used to quickly identify and issue early warnings for charging anomalies, and the anomaly information is synchronously uploaded to a cloud management platform, achieving multi-layered collaborative charging safety assurance. The system includes a data acquisition module, an edge computing and intelligent analysis module, an anomaly early warning module, a cloud management platform, and a visualized operation and maintenance terminal. This system can significantly improve the real-time performance and accuracy of charging anomaly monitoring, reduce safety risks, and improve operation and maintenance efficiency.

Claims

1. Patent claims Invention Title: Real-time Monitoring and Early Warning System for Charging Anomalies in Charging Piles Based on Edge Computing Architecture A real-time monitoring and early warning system for charging pile anomalies based on an edge computing architecture, characterized in that, include: The data acquisition module is used to collect key parameters of the charging pile in real time during the charging process, including but not limited to current, voltage, temperature, power, and communication status. The edge computing and intelligent analysis module is deployed at the edge computing node in or near the charging pile. It is used to process the data collected by the data acquisition module locally in real time and use intelligent algorithms to identify abnormal states during the charging process, including overcurrent, overvoltage, undervoltage, overtemperature, communication abnormality, charging interruption, etc. The anomaly warning module is used to immediately issue warning information such as audible and visual alarms, SMS or APP push notifications locally when an anomaly is detected, and to simultaneously upload the anomaly information to the cloud management platform. The cloud management platform is used to aggregate, analyze, and archive received abnormal data, supports historical data tracing, statistical analysis, and abnormal pattern mining, and provides decision support for operation and maintenance personnel. A visual operation and maintenance terminal is used to provide operation and maintenance personnel with real-time anomaly monitoring, early warning information display, remote control, and operation and maintenance suggestions.

2. The system according to claim 1, characterized in that, The edge computing and intelligent analysis module uses machine learning or rule engine algorithms based on multi-parameter fusion to achieve high-accuracy identification of charging anomalies.

3. The system according to claim 1, characterized in that, The anomaly warning module can automatically select from various warning methods such as local audible and visual alarms, remote push notifications, and SMS notifications based on the type of anomaly.

4. The system according to claim 1, characterized in that, The cloud management platform supports batch analysis of abnormal data, trend prediction, and automatic generation of operation and maintenance reports.

5. The system according to claim 1, characterized in that, The visualized operation and maintenance terminal supports real-time display of abnormal charging pile status, historical data query, remote control, and operation and maintenance task assignment.