Sustainable Deep Learning at Grid Edge for Real-Time High Impedance Fault Detection

High impedance faults (HIFs) on overhead power lines are known to cause fires. They are difficult to detect using conventional protection relays because the fault current is insufficient to cause tripping. The delay in detecting HIFs can result in severe bushfires and energy losses; hence a high throughput, low latency detection scheme needs to be developed for HIF detection. Moreover, the complexities associated with HIF detection demands signal processing techniques combined with artificial intelligence to achieve higher detection accuracy. This paper proposes a sustainable deep learning-based approach in an edge device, that can be mounted on top of a power pole to detect HIFs in real-time. Data acquisition, feature extraction, and deep learning based fault identification are performed in an embedded edge node to achieve higher throughput, reduced latency as well as offload the network traffic. Furthermore, optimization techniques such as hardware parallelism and pipelining are adapted to achieve real-time fault identification on edge devices while ensuring the efficient usage of its limited resources. Real-time implementation of the proposed system is validated through laboratory experiments and the results demonstrate the suitability of edge computing to detect HIFs in terms of reduced detection latency (115.2 ms) and higher detection accuracy (98.67 percent).