Power management for fuel-cell electric vehicle using Hybrid SHO-CSGNN approach

The increasing connectivity of vehicles through intelligent transportation systems presents a significant research challenge: how to simultaneously optimize power management operations and vehicle dynamics to enhance energy efficiency. This paper proposes a novel approach to address this challenge by integrating the Sea-Horse Optimization Algorithm (SHO) and Contrastive Self-Supervised Graph Neural Network (CSGNN), referred to as the SHO-CSGNN technique. The primary objectives of this approach are to reduce computation time and improve energy efficiency in electric vehicles (EVs) powered by fuel cells. The SHO is employed to optimize the power consumption of the EV by dynamically adjusting power management operations based on real-time data and vehicle dynamics. On the other hand, the CSGNN is utilized to predict the vehicle's range performance by analyzing various factors such as road conditions, traffic patterns, and driving behavior. By combining these two approaches, the SHO-CSGNN technique can effectively optimize power management operations while considering the dynamic nature of the driving environment. The proposed technique is implemented and evaluated on the MATLAB platform, where it is compared with existing methods, including the Salp Swarm Algorithm (SSA), Firefly Algorithm (FFA), and Genetic Algorithm (GA). Experimental results demonstrate that the SHO-CSGNN technique outperforms all current methods, achieving a computation time reduction of 3.3 seconds compared to existing techniques. This study contributes to the advancement of power management strategies for EVs, highlighting the effectiveness of the SHO-CSGNN technique in enhancing energy efficiency and computational efficiency in real-world applications. The findings of this research have implications for the development of more efficient and sustainable transportation systems, paving the way for the widespread adoption of electric vehicles.