Design and Optimisation of A Hybrid Renewable Energy System For Off-Grid Applications

This research addresses the global energy crisis by advancing renewable energy solutions, focusing on the optimization of off-grid Hybrid Renewable Energy Systems (HRES) that integrate photovoltaic (PV) technology with energy storage. This work contributes to the optimization of off-grid PV system design by integrating solar irradiance forecasting with advanced MPPT algorithms, thereby facilitating the development of more efficient and sustainable energy solutions for regions with high solar potential. Four machine learning models—Artificial Neural Networks (ANN), Support Vector Machines (SVM), Gaussian Process Regression (GPR), and Autoregressive Integrated Moving Average (ARIMA)—were evaluated for predicting solar irradiance, with GPR demonstrating the highest predictive accuracy, as indicated by the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Additionally, the research compares two Maximum Power Point Tracking (MPPT) algorithms, Particle Swarm Optimization (PSO) and Perturb and Observe (P&O), demonstrating that PSO outperforms P&O in both tracking efficiency and power output.