Seagull-optimized artificial neural network-based innovative energy management system using improvised boost converter and coupled inductor

The emergence of photovoltaic (PV)-driven grid systems signifies a paradigm shift in sustainable energy utilization. These systems admirably reduce reliance on finite fossil fuels and mitigate environmental impacts thereby minimizes greenhouse gas emissions. However, due to varying sunlight conditions, the inherent intermittency of solar power generation presents challenges in maintaining consistent energy output and managing voltage levels efficiently in grid connected systems. Furthermore, existing power converters do not adequately optimize voltage levels, resulting in increased total harmonic distortion (THD) and decreased overall system performance. Hence, the primary objective of this research is to develop and validate an efficient energy management system with enhanced voltage management and improved maximum power point tracking (MPPT) accuracy. Accordingly, this research proposes an efficient PV-assisted energy management system, with a novel improvised boost converter with coupled inductor, with a specific focus on refining voltage optimization. To ensure that the maximum power point (MPP) is tracked and maintained, enhancing the overall energy yield from the PV array, Seagull optimization algorithm-aided artificial neural network (SOA-ANN) MPPT method is implemented. By improving voltage management and optimizing MPPT accuracy, the system ensures a stable and efficient energy supply from PV arrays. This allows the PV system to contribute energy to the grid and enables efficient utilization of solar-generated power within the existing AC infrastructure. Additionally, a bidirectional battery converter in the energy storage system optimizes power delivery during peak demand. Validation through MATLAB showcases outstanding converter efficiency at 93.35%, coupled with a noteworthy reduction in THD to 2.33%, affirming the efficacy of the proposed system. On the whole, the findings contribute to the broader goal of reducing reliance on fossil fuels and addressing key challenges in integrating renewable energy into grid infrastructure.