Photovoltaic Power Forecasting Model Based on the Fusion of Bagging Algorithm and Generalized Regression Neural Networks

Abstract

Power prediction of photovoltaic (PV) power generation is very important for photovoltaic power generation to be connected to power grid. Based on this, this paper proposes a prediction model based on Bagging algorithm and GRNN to improve the prediction power of PV power generation. Generalized Regression Neural Network (GRNN) is a variant of Radial Basis Function Neural Network (RBFNN). Compared with RBFNN, GRNN has better nonlinear function approximation ability, and the network has higher robustness and fault tolerance. Bagging algorithm is a typical integrated learning algorithm, which can optimize the performance of a single prediction model. Through the simulation of an example, the simulation data show that the prediction model based on Bagging algorithm and GRNNs combination can obtain higher prediction accuracy.