Abstract—Abstract: This paper proposes a novel methodology for forecasting of one hourly global solar irradiance (GSI). This methodology is a combination of k-NN decompotition method and artificial neural network (ANN) algorithm modelling. The k-NN Decomposition-ANN method is designed to forecast GSI for 60 min ahead based on meteorology data for the target PV station which position is surrounded by eight other adjacent PV stations. The novelty of this method is taking into account the meteorology data. A set of GSI measurement samples was available from the PV station in Taiwan which is used as test data. The first method implements k-NN Decomposition as a preprocessing technique prior to ANN method. The error statistical indicators of k-NN Decomposition- ANN model and the root-mean-square error (RMSE) is 20 W/m2. The models forecasts are then compared to measured data and simulation results indicate that the k-NN Decomposition-ANN-based model presented in this research can calculate hourly GSI with satisfactory accuracy.

Index Terms—Key words: Forecasting, decomposition, artificial neural network, global solar irradiance, meteorological, photovoltaic.

National Taipei University of Technology, 1, Section. 3, Zhong-Xiao (Chung-Hsiao) E. Rd., Da’an Dist., Taipei 106, Taiwan.

Cite:Unit Three Kartini, Chao Rong Chen, "K-NN Decomposition Artificial Neural Network Models for Global Solar Irradiance Forecasting Based on Meteorological Data," International Journal of Computer and Electrical Engineering vol. 9, no. 1, pp. 351-359, 2017.