Minimum‐features‐based ANN‐PSO approach for islanding detection in distribution system. Issue 9 (5th July 2016)

• Record Type: Journal Article
• Authors: Raza, Safdar; Mokhlis, Hazlie; Arof, Hamzah; Naidu, Kanendra; Laghari, Javed Ahmed; Khairuddin, Anis Salwa Mohd
• Is Part Of: IET renewable power generation. Volume 10:Issue 9(2016)
• Page Start: 1255
• Page End: 1263
• Publication Date: 2016-07-05
• Subjects: particle swarm optimisation -- neural nets -- distributed power generation -- power distribution faults -- power engineering computing -- regression analysis -- induction motors -- power distribution reliability -- power generation reliability; minimum‐feature‐based ANN‐PSO approach -- distribution system -- distributed energy resources -- DER -- fault detection -- DER tripping -- induction motor starting -- capacitor switching -- load variation -- nonislanding event -- islanding event -- regression value -- ANN‐EP -- stand‐alone ANN -- particle swarm optimisation -- evolutionary programming -- artificial neural network -- intelligent islanding detection technique; Renewable energy sources -- Periodicals; 333.79405
• DOI: 10.1049/iet-rpg.2016.0080
• Languages: English
• ISSNs: 1752-1416

Abstract

Abstract : Islanding detection is important for the protection of any distribution system connected to distributed energy resources (DER's). This study proposes an intelligent islanding detection technique based on artificial neural network (ANN) that employs minimal features from the power system. The accuracy of the trained ANN is improved by optimising the learning rate, momentum and number of neurons in the hidden layers using evolutionary programming (EP) and particle swarm optimisation (PSO). The performance comparison between stand‐alone ANN, ANN‐EP and ANN‐PSO in the form of regression value is performed to obtain the best feature combination for an efficient islanding detection. The proposed technique is tested on‐ and off‐line for various islanding and non‐islanding events. The simulation results indicate that the proposed technique can successfully distinguish islanding from other non‐islanding events such as load variation, capacitor switching, faults, induction motor starting and DER tripping.