Solar Radiation Prediction Using Boosted Coyote Optimization Algorithm with Deep Learning for Energy Management

Solar radiation is the main source of energy on Earth and plays a major role in the hydrological cycles, surface radiation balance, weather and climate changes, and vegetation photosynthesis. Accurate solar radiation prediction is of paramount importance for both climate research and the solar industry. This prediction includes forecasting techniques and advanced modeling to evaluate the amount of solar energy available at a specific location during a given period. Solar energy is the cheapest form of clean energy, and due to the intermittent nature of the energy, accurate forecasting across multiple timeframes is necessary for efficient generation and demand management. Solar radiation prediction using deep learning (DL) includes the applications of neural network methods, namely Convolutional Neural Network (CNN) or Long Short-Term Memory (LSTM) models, to forecast and model solar irradiance patterns. By leveraging meteorological variables and historical solar radiation data, DL algorithms can capture complex spatial and temporal dependencies, resulting in accurate predictions. This article presents a novel Solar Radiation Prediction model utilizing a Boosted Coyote Optimization Algorithm with Deep Learning (SRP-BCOADL). The SRP-BCOADL model initially normalizes the input data using a min-max normalization approach to improve the robust nature under different scales. Besides, the SRP-BCOADL technique uses a Deep Long Short-Term Memory Autoencoder (DLSTM-AE) system for precisely forecasting solar radiation levels. The model’s accuracy is further improved through hyperparameter optimization using the BCOA. The performance analysis of the SRP-BCOADL technique is tested using solar radiation data. Extensive experimental outcomes prove that the SRP-BCOADL method obtains better results over other techniques. The Mean Squared Error (MSE) is just 0.13 kWh/m2, is much lower when compared to other models. The Root Mean Squared Error (RMSE) is also reduced to 0.36 kWh/m2, and the Mean Absolute Error (MAE) reaches a minimal level of 0.276 kWh/m2.