Design and Performance Analysis of Solar Charging Stations Using Artificial Neural Network (ANN) Control Methods.

Abstract

The increasing demand for sustainable energy solutions, particularly in the transport sector, highlights the critical need for innovative approaches to energy management. This research focuses on the design and performance analysis of solar charging stations utilizing ANN control methods. It aims to address the challenges posed by the rising use of Electric Vehicles (EVs) especially motorcycles in Rwanda, particularly in urban areas such as Kigali, where rapid urbanization elevates energy needs. This study proposes to build a Matlab Simulink model that leverages ANN to optimize solar energy capture and charging efficiency. Through a comparative analysis of Maximum Power Point Tracking (MPPT) methods, specifically the Perturb and Observe (P&O) and ANN control techniques, the research evaluates their effectiveness in varying environmental conditions. Data was collected from weather stations and charging stations across Kigali to inform model design and simulation. Key findings demonstrate that ANN significantly enhances energy extraction efficiency and charging performance, showcasing the viability of solar-powered EV charging solutions as an environmentally sustainable alternative to fossil fuels. The outcomes of this research contribute to the development of scalable solar charging station technologies, addressing energy scarcity in both urban and rural settings. By promoting the integration of renewable energy in the EV sector, this project not only supports Rwanda’s energy transition goals but also aims to mitigate environmental challenges associated with traditional fuel sources. The insights gained from this work pave the way for future advancements in sustainable transportation infrastructure.