A Cloud-Edge Collaboration Framework for External Force Damage Detection in Distribution Network

In the power grid industry, the safety of overhead transmission lines has always been of crucial importance. The safety of overhead transmission lines is significant for the safe and reliable operation of the power grid; therefore, monitoring the operational status of overhead transmission lines is extremely important. At the same time, some more time-consuming neural-symbolic reasoning approaches has been proposed and can achieve a better accuracy. Therefore, a cloud-edge collaboration framework is proposed in this paper, which takes the advantage of both the edge devices and the cloud computing ability. In the edge side, compressed deep learning models are employed for a fast result. While in the cloud side, a neural-symbolic approach is employed which can achieve a better result with more time consuming. The experimental results indicate that this framework delivers an efficient and stable detection of external hidden hazards in the distribution network, while also maintaining a reasonable time cost.