Forecasting of renewable energy-related time series by NARX ANN for electrical grid management

Forecasting of meteorological variables is crucial for accurate planning and management of electrical power grids, aiming at improving overall efficiency and performance. In this paper, an artificial neural network (ANN)-based technique is investigated for short-term forecasting of the hourly wind speed and solar radiation. Specifically, the non-linear autoregressive network with exogenous inputs (NARX) ANN is considered, compared to other models, and then selected to perform multi-step-ahead forecasting. Different time horizons have been considered in the range between 8 and 24 hours ahead. The main advantage of the proposed method is that it reconciles good forecasting performance with a very simple network structure, which is potentially implementable on a low-cost processing platform.