A Review on Automated Estimation of Fault Location in HVDC Transmission Systems Using AI and ML Techniques

AI, Machine Learning (ML) and Deep Learning (DL) techniques are transforming various domains of life. One such domain in power generation and transmission, which is being made more efficient and robust against faults using AI, ML and DL techniques. In the present era of deregulation and competition, demand from every energy supplier is to have good continuity, dependability and reliability. Fault location can play a vital role in achieving this aim. As uninterrupted power supply is the prime demand by all consumers. However, faults in power system will leads to the interruption in power supply and it will make system vulnerable towards system outrage/collapsing and will lead to damage various electrical peripheral of switch gear/ electrical equipment. Hence all faults are required to be detected and clear as soon as possible to restart power supply to consumer. Having accuracy knowledge of fault location will come very handy in reducing system outrage time and they’re by improving continuity and reliability of system. Various researches has been done previously towards finding accurate result. In this paper presents a comprehensive survey on the existing work done in the domain of machine learning assisted fault location in HVDC systems. Machine Learning and Deep Learning models such as the SVM, CNN, LSTM, ARIMA etc. have been analyzed with their salient features, advantages and limitation. This review is expected to enable deciding