Artificial Intelligence based Sensor Data Analytics Framework for Remote Electricity Network Condition Monitoring

TL;DR

This paper presents an AI-driven sensor data analytics framework for remote electricity network monitoring, enhancing fault detection, load identification, and energy disaggregation with high accuracy and low latency.

Contribution

It introduces a comprehensive AI-based platform for real-time fault detection, load identification, and energy disaggregation in remote electricity networks, improving accuracy and response times.

Findings

HIF detection accuracy of 98.67%

Load identification accuracy of 98%

Energy disaggregation error reduction by 44%

Abstract

Rural electrification demands the use of inexpensive technologies such as single wire earth return (SWER) networks. There is a steadily growing energy demand from remote consumers, and the capacity of existing lines may become inadequate soon. Furthermore, high impedance arcing faults (HIF) from SWER lines can cause catastrophic bushfires such as the 2009 Black Saturday event. As a solution, reliable remote electricity networks can be established through breaking the existing systems down into microgrids, and existing SWER lines can be utilised to interconnect those microgrids. The development of such reliable networks with better energy demand management will rely on having an integrated network-wide condition monitoring system. As the first contribution of this thesis, a distributed online monitoring platform is developed that incorporates power quality monitoring, real-time HIF identification and transient classification in SWER network. Artificial Intelligence (AI) based techniques are developed to classify faults and transients. The proposed approach demonstrates higher HIF detection accuracy (98.67%) and reduced detection latency (115.2 ms). Secondly, a remote consumer load identification methodology is developed to detect the load type from its transients. An edge computing-based architecture is proposed to facilitate the high-frequency analysis for load identification. The proposed approach is evaluated in real-time, and it achieves an average accuracy of 98% in identifying different loads. Finally, a deep neural network-based energy disaggregation framework is developed to separate the load specific energy usage from an aggregated signal. The proposed framework is evaluated using a real-world data set. It improves the signal aggregate error by 44% and mean aggregate error by 19% in comparison with the state-of-the-art techniques.