Solar PV power generation forecast using a hybrid intelligent approach

A significant role of a smart grid is to substantially increase the penetration of environmentally-friendly renewable energy sources, such as solar photovoltaic (PV) power. One of the major challenges associated with the integration of PV power into the grid is the intermittent and uncontrollable nature of PV power output. Therefore, developing a reliable forecasting algorithm can be extremely beneficial in system planning and market operation of grid-connected PV systems. This paper presents a novel hybrid intelligent algorithm for short-term forecasting of PV-generated power. The algorithm uses a combination of a data filtering technique based on wavelet transform (WT) and a soft computing model based on fuzzy ARTMAP (FA) network, which is optimized using an optimization technique based on firefly (FF) algorithm.