Deep reinforcement learning based resource allocation for cloud edge collaboration fault detection in smart grid

Real-time fault detection is important for the operation of smart grid. It has become a trend of future development to design an anomaly detection system based on deep learning by using the powerful computing power of cloud. However, the delay of Internet transmission is large, which may make the delay time of detection and transmission go beyond the limit. However, the edge-based scheme may not be able to undertake all the data detection tasks due to the limited computing resources of edge devices. Therefore, we propose a cloud-edge collaborative smart grid fault detection system, next to which edge devices are placed, and equipped with the lightweight neural network with different precision for fault detection. In addition, a sub-optimal and real time communication and computing resources allocation method is proposed based on deep reinforcement learning. This method greatly speeds up the solution time, can meet the requirements of data transmission delay, maximizes the system throughput, and improves the communication efficiency. The simulation results show that the scheme is superior in transmission delay and improves the real-time performance of the smart grid detection system.