Evaluating Solar Power Forecasting Robustness: A Comparative Analysis of XGBoost, RNN, KNN, RF, and LSTM with emphasis on Lagged Steps, Sensitivity, and Cross-Validation Techniques

The transition towards renewable energies is inevitable in the face of global warming conditions and the increasing scarcity of fossil fuels, alongside their harmful impacts on the environment. Solar power, considered as a clean and its availability energy source, plays a vital role in this matter. However, due to the unpredictability nature of solar, influenced by environmental and temporal factors, energy production has faced significant challenges for its integration into microgrids. The present study works on addressing these obstacles by implementing advanced machine learning techniques to empower the predictability of solar energy. Utilizing one-month datasets of two power plants in India, Gandikota, Andhra, and Nasik, Maharashtra. This work focuses on various predictive models, including Support Vector Regression (SVR), Recurrent Neural Networks (RNN), eXtreme Gradient Boosting (XGBoost)m K-Nearest Neighbors (KNN), and Random Forest. These models are evaluated under different conditions, like incorporating lagged steps, and dynamics capturing. For the evaluation, a range of metrics is used. Mean Squared Log Error (MSLE), Mean Absolute Error (MAE), Mean Percentage Error (MPE), and R², for the identification of the most effective algorithm are used. The final goal of this work is not only to improve the forecasting accuracy of solar power generation, by advantageous model modification but also to contribute to the efficient management and optimization of renewable energy integrations. Overall, XGBoost emerges as the preferred method for forecasting, offering a balance of high accuracy and robustness across different forecasting scenarios.