Development Hybrid Model Deep Learning Neural Network (DL-NN) For Probabilistic Forecasting Solar Irradiance on Solar Cells To Improve Economics Value Added

Abstract

A new hybrid deep convolutional neural network (CNN) method for efficient probabilistic forecasting solar irradiance approach is proposed for research to accurately quantify of solar irradiance from solar cell systems. Distinguished from combination models, a Deep Convolutional Learning Neural Network optimization model with a multilayer-based prediction model for solar irradiance in PV generation system is constructed based on a learning machine and features high reliability and computational efficiency. The proposed using deep convolutional neural network approach is validated through the proposed approach is validated through the studies on PV data from Indonesia. From the computation, the proposed hybrid Deep Convolutional Neural Network model using solar irradiance performs RMSE maximal of 12.1 W/m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of solar irradiance.