Incipient Fault Detection on Transmission Lines Using Continual Machine Learning Technique: A Review and Future Directions

Abstract

Power system faults are highly undesirable but unavoidable property of any physical power system infrastructure due to the imperfection in the design, manufacture and operation of the associated physical equipment such as the relays, transmission lines and circuit breakers. In particular, the transmission lines serve the critical function of interconnecting various power system networks and any fault on it can be disastrous if not identified on time. Thus, steps have to be taken to mitigate such issues earlier on by following a real-time perspective. The problem of determining in advance, the likelihood of a fault in advance is introduced as the incipient fault detection problem. In this paper, a systematic review of the research on the important topic of incipient fault detection on power transmission lines is presented. The review addresses some of the popular Machine Learning (ML) algorithms or techniques applied both traditional and emerging. It further seeks to examine the problem of incipient fault detection and seeks to provide insight into the demographics and type of ML in use. It also specifically provides a succinct discussion of some of the emerging detection approaches based on the use of continual learning property. The benefits of the continual learning are equally highlighted.