Islanding detection review using intelligence classifier in distribution network

• Main Authors: Zainudin, H.N., Mekhilef, Saad, Mokhlis, Hazlie, Raza, S.
• Format: Article
• Published: Springer Nature 2021
• Subjects: T Technology (General); TA Engineering (General). Civil engineering (General); TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.um.edu.my/35805/; https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107765911&doi=10.1007%2f978-981-16-0749-3_25&partnerID=40&md5=d8cad30e9a75a443dc34493fc63eb5f1
• Institution: Universiti Malaya

Islanding detection method is the most crucial aspect in distribution network. Generally, it can be categorized as remote, passive, active, and hybrid methods. From all these methods, islanding preferable inclined to the passive method since it is cheaper and able to maintain a power quality of the system. There are few drawbacks of passive techniques such as a high non-detection zone and its required onset setting. In order to overcome the drawback and limitation, various signal processing and intelligent techniques are introduced. Intelligent classifier techniques are particular to resolve the issues including the detection accuracy, speed of detection, and compatibility of detecting islanding in hybrid distributed energy resources. This paper offers a general summary of conventional islanding detection methods and focuses on islanding detection using intelligence classifier methods. Intelligence classifier will increase capability of common passive islanding detection methods hence upgrading the signal processing techniques. A comparison between the intelligence classifier methods with an existing techniques is also provided. In conclusions, this paper summarizes advantages and disadvantages of the intelligence classifier techniques for providing initial strategies to those researchers or power engineers for them to select the best option for their system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.