Solar Radiation Prediction Using Satin Bowerbird Optimization with Modified Deep Learning

Abstract

Solar energy will be a great alternative to fossil fuels since it is clean and renewable. The photovoltaic (PV) mechanism produces sunbeams' green energy without noise or pollution. The PV mechanism seems simple, seldom malfunctioning, and easy to install. PV energy productivity significantly contributes to smart grids through many small PV mechanisms. Precise solar radiation (SR) prediction could substantially reduce the impact and cost relating to the advancement of solar energy. In recent times, several SR predictive mechanism was formulated, namely artificial neural network (ANN), autoregressive moving average, and support vector machine (SVM). Therefore, this article develops an optimal Modified Bidirectional Gated Recurrent Unit Driven Solar Radiation Prediction (OMBGRU-SRP) for energy management. The presented OMBGRU-SRP technique mainly aims to accomplish an accurate and time SR prediction process. To accomplish this, the presented OMBGRU-SRP technique performs data preprocessing to normalize the solar data. Next, the MBGRU model is derived using BGRU with an attention mechanism and skip connections. At last, the hyperparameter tuning of the MBGRU model is carried out using the satin bowerbird optimization (SBO) algorithm to attain maximum prediction with minimum error values. The SBO algorithm is an intelligent optimization algorithm that simulates the breeding behavior of an adult male Satin Bowerbird in the wild. Many experiments were conducted to demonstrate the enhanced SR prediction performance. The experimental values highlighted the supremacy of the OMBGRU-SRP algorithm over other existing models.