Prediction of photovoltaic power output based on similar day analysis using RBF neural network with adaptive black widow optimization algorithm and K-means clustering

Solar photovoltaic power generation has become the focus of world energy market. However, weak continuity and variability solar data severely increase grid operating pressure. Therefore, it is necessary to propose a new refined targeted forecasting method broaden channels. In this paper, hybrid model (KM-SDA-ABWO-RBF) based on radial basis function neural networks (RBFNNs), adaptive black widow optimization algorithm (ABWO), similar day analysis (SDA) K-means clustering (KM) been developed. The ABWO develops factors optimize parameters RBFNNs avoid getting trapped in local optima. SDA determine similarity days optimal through meteorological historical datasets. Nine models compared forecast accuracy stability over four seasons. Experiments show that with other well-known indicators, proposed KM-SDA-ABWO-RBF highest prediction more stable.