A Sustainable Renewable Energy Assessment Framework Using Novel Machine Learning Algorithm

In the quest for sustainable energy solutions, accurate prediction of renewable energy outputs is essential for the seamless integration of these resources into the energy grid. This paper presents a Squirrel Search-Optimized Gradient Boosted Decision Tree (SS-GBDT) model, designed to enhance the precision of renewable energy forecasts. The SS-GBDT model leverages the search capabilities of the squirrel search algorithm to optimize the parameters of gradient boosted decision trees, thereby improving their predictive performance. Comparative analyses against established forecasting methods such as DNN, BiLSTM, CNN-BiLSTM, and AB-Net are conducted, with the SS-GBDT model consistently demonstrating superior accuracy, lower error metrics, and an overall robust performance. The findings suggest that the SS-GBDT model could be an invaluable asset for energy sector stakeholders, aiding in the advancement of reliable and efficient renewable energy systems. This study contributes to the growing body of knowledge in renewable energy forecasting and underscores the potential of advanced machine learning techniques in fostering sustainable energy transitions.