Solar power plant generation forecasting using NARX neural network model: A case study

Abstract

New technologies have been developed and adopted to generate energy from renewable sources to satisfy the increasing demand without causing environmental damage. However, estimating the power output of inherently intermittent, weather-driven, and non-dispatchable renewable energy sources is a major scientific and societal concern. In this study, a neural network model to enable short-to-middle term forecasts of a photovoltaic (PV) power system is provided. Using historical weather and power generation data, a non-linear autoregressive network with exogenous input (NARX) model is built to forecast the non-linear photovoltaic system output. The performance of the model is then analyzed by different statistical evaluation parameters. It is shown that the PV system power output estimation method can be successfully employed.