Daily solar radiation prediction based on Genetic Algorithm Optimization of wavelet neural network
Authors:
- 1 September 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 602-605
Abstract
Daily solar radiation prediction is a nonlinear and non-stationary process. It's hard to model with a single method. A Genetic Algorithm Optimization of Wavelet Neural Network (GAO-WNN) model was set in this paper. The nonlinear process of daily solar radiation was forecasted by neural network and the non-stationary process of daily solar radiation was decomposed into quasi-stationary at different frequency scales by multi-scale characteristics of wavelet transform. Input weights, output weights, scale factors and translation factors were optimized by genetic algorithm. Gradient descent method was used to make further training of the model with temperature, clearness index, and daily radiation data. Simulation results indicate that the method is satisfactory to the prediction of daily solar radiation.Keywords
This publication has 2 references indexed in Scilit:
- An ANFIS-based Forecasting for Solar Radiation Data from Sunshine Duration and Ambient Temperature2007 IEEE Power Engineering Society General Meeting, 2007
- Artificial neural network model for prediction solar radiation data: application for sizing stand-alone photovoltaic power system2005