A novel elephant herd optimization model with a deep extreme Learning machine for solar radiation prediction using weather forecasts

In recent times, the exploitation of solar resources has remained a major issue due to increasing energy utilization globally. For effective solar resource management, a globalized solar radiation (SR) predictive technique is needed to automatically determine the performance of the solar system. The misprediction of SR results in overestimation of the load, thereby resulting in an inadequate supply of energy. The SR prediction process can be handled by deep learning (DL) models. This paper presents a novel elephant herd optimization model with a deep extreme learning machine (EHO-DELM model) for solar radiation prediction using weather forecasts. The presented EHO-DELM model performs preprocessing to make the available data compatible with the regression process. In addition, the DELM model is applied to predict the SR using weather forecast data. Moreover, the EHO algorithm is utilized to optimally tune of the weights and biases of the DELM model. An extensive experimental analysis is conducted to evaluate the predictive performance of the EHO-DELM model. The obtained simulation values demonstrate the superior performance of the EHO-DELM model in terms of mean square error (MSE) and root mean square error (RMSE).