Short term solar power forecasting using hybrid minimum variance expanded RVFLN and Sine-Cosine Levy Flight PSO algorithm

Abstract

With the increase in solar power integration, the necessity for accurate solar power forecasting is of paramount importance for various energy markets, grid management system, power dispatching and so on. This paper analyses a new and efficient hybrid forecasting approach consisting of empirical wavelet transform (EWT) and Robust minimum variance Random Vector Functional Link Network (RRVFLN) with random weight vector for the enhancement nodes along with a functionally expanded direct link to the output node from input nodes. The RRVFLN contains dual activation functions in each hidden neuron of the network and its parameters are optimized by an efficient Sine Cosine and levy flight based particle swarm optimization (PSOLVSC). The proposed RRVFLN has some similarity with recently proposed broad learning system that can replace neural networks with deep architecture for handling big and time varying data bases. For examining the solar power prediction accuracy of the proposed EWT-RRVFLN model, the historical solar power data for different seasons of Alabama, Ikitelli, and Berlin are taken into consideration which are divided into three time horizon intervals of 5min, 15min, 30min and 60 min, respectively.