Authors: M.A. Chowdhury
Addresses: Faculty of Engineering, Computing and Science, Swinburne University of Technology Sarawak Campus, Jalan SimpangTiga, 93350 Kuching, Sarawak, Malaysia
Abstract: Wind energy has been receiving more acceptance as a reproducible, resourceful and clean energy source since last decade. Wind power is not constant and may fluctuate below the rated wind power when the wind speed is lower than the rated speed. This fact affects the stability of the power system, to which the wind generators are connected. This is becoming more significant with the increasing penetration of wind energy systems. Pitch angle control has been one of the most common methods for smoothing output power fluctuations during below rated wind incidents. An artificial neural network (ANN)-based pitch angle controller is proposed in this paper for smoothing wind power fluctuations during below rated wind incidents beside traditional power regulations during above rated wind incidents. Two smoothing methods have been presented: the determination of the command output power based on the exponential moving average with a proper selection of correction factor by neural network and the dynamic selection of target output power according to the wind incident. Simulation results show the effectiveness of the proposed ANN-based pitch angle controller in smoothing output power fluctuations with significantly small drop of output power.
Keywords: wind power; smoothing power fluctuations; pitch angle control; artificial neural networks; ANNs; wind energy; controller design; wind speed; simulation.
International Journal of Renewable Energy Technology, 2015 Vol.6 No.3, pp.276 - 294
Accepted: 18 Jun 2014
Published online: 28 Jun 2015 *