Fusion wind and solar generation forecasting via neural network

Abstract

Wind and solar power are the most common renewable resources of energy and their usage for power generation is quickly growing all over the world. However, both wind and solar power are difficult to predict manually due to every time changes in weather condition; therefore. power output of wind and solar is associated with some uncertainty. A reliable wind-solar day ahead load prediction proposed in this paperwork to support a small microgrids system. The system is a combination of hardware of solar panel, wind turbine, hybrid charge controller, current sensor, voltage sensor circuit, battery, Arduino Mega and personal computer that is install with MATLAB along with artificial neural network model for load forecast. The prediction model is known as Feedforward back propagation (FFBP) artificial neural network (ANN), this method utilizes a learning relationship between wind-solar power output and predicted weather. The FFBP model trained ANN to recognize similar pattern and to predict the output power based on train and tested data and the results achieved 99.5 accuracy, 6.25% MAPE and 1.2 % MAD.