A Sliding Mode Controller for Prediction of the Maximum Power Point Tracking of Hybrid Renewable Sources

The integration of a fuel cell and solar cell into a generator system presents an effective solution to numerous energy-related challenges. This system consists of solar panels, fuel cells, voltage converters, and a battery or supercapacitor. The performance of this electricity generation system is influenced by various factors, including load nature, system connection, and energy management. This study focuses on maximizing power point tracking in a grid-independent mode. To optimize efficiency, a DC/DC voltage converter is employed to align the load with the characteristics of the maximum power point. The algorithms used for maximum power point tracking are categorized into three groups: perturbation and observation (P&O), incremental impedance, and artificial neural networks (ANN). In this study, we introduce two novel algorithms based on neural networks and evaluate their performance in comparison to other neural networks. Additionally, we propose a control strategy based on a selected slip level for photovoltaic generators. The proposed approach demonstrates superior and more efficient performance compared to other methods, making it a promising technology for sustainable energy generation.