Forecasting Solar Power Using Hybrid Firefly and Particle Swarm Optimization (HFPSO) for Optimizing the Parameters in a Wavelet Transform-Adaptive Neuro Fuzzy Inference System (WT-ANFIS)
Document Type
Article
Publication Date
1-1-2019
Abstract
Solar power generation deals with uncertainty and intermittency issues that lead to some difficulties in controlling the whole grid system due to imbalanced power production and power demand. The forecasting of solar power is an effort in securing the integration of renewable energy into the grid. This work proposes a forecasting model called WT-ANFIS-HFPSO which combines the wavelet transform (WT), adaptive neuro-fuzzy inference system (ANFIS) and hybrid firefly and particle swarm optimization algorithm (HFPSO). In the proposed work, the WT model is used to eliminate the noise in the meteorological data and solar power data whereby the ANFIS is functioning as the forecasting model of the hourly solar power data. The HFPSO is the hybridization of the firefly (FF) and particle swarm optimization (PSO) algorithm, which is employed in optimizing the premise parameters of the ANFIS to increase the accuracy of the model. The results obtained from WT-ANFIS-HFPSO are then compared with several other forecasting strategies. From the comparative analysis, the WT-ANFIS-HFPSO showed superior performance in terms of statistical error analysis, confirming its reliability as an excellent forecaster of hourly solar power data. © 2019 by the authors.
Keywords
adaptive neuro-fuzzy inference system, firefly, forecasting, hybrid firefly and particle swarm optimization, particle swarm optimization, photovoltaic, wavelet transform
Divisions
umpedac
Funders
Higher Institution Centre of Excellence (HICoE) Program Research Grant and Centre for Research Grant Management (PPGP) at the University of Malaya, grant number [UMPEDAC-2018 (MOHE HICoE-UMPEDAC) and RU005-2015]
Publication Title
Applied Sciences
Volume
9
Issue
16
Publisher
MDPI