Hybrid PV Power Forecasting Methods: A Comparison of Different Approaches

Accurate photovoltaic (PV) prediction has a very positive effect on many problems that power grids can face when there is high penetration of variable energy sources. This problem be addressed with computational intelligence algorithms such as neural networks and Evolutionary Optimization. The purpose this article to analyze three different hybridizations between physical models artificial networks: the first hybridization combines output five-parameter model module in which parameters are obtained from datasheet. In second hybridization, matching procedure historical data exploiting Social Network Finally, third PHANN, clear sky irradiation used an input. These hybrid methods compared two approaches simple network-based forecasting. results show effective for achieving good forecasting results, while performance comparable.