A Comprehensive Review of Energy Management Strategy for Plug-in Hybrid Electric Vehicles Using Snow Geese Optimization and Relational Bi-level Aggregation Graph Convolutional Network

Abstract

Energy management strategies (EMS) play a critical role in enhancing the efficiency, fuel economy, and emission reduction of plug-in hybrid electric vehicles (PHEVs). With the increasing demand for sustainable transportation, intelligent optimization techniques and deep learning models have gained significant attention in EMS design. This paper presents a comprehensive review of an advanced EMS framework that integrates Snow Geese Optimization (SGO) and Relational Bi-level Aggregation Graph Convolutional Networks (RBAGCN). The proposed hybrid approach aims to optimize power distribution between internal combustion engines and electric motors while capturing complex relational dependencies among vehicle states. Traditional EMS approaches, including rule-based and dynamic programming methods, often suffer from scalability and real-time implementation challenges. In contrast, modern AI-based techniques such as reinforcement learning and graph neural networks provide adaptive and data-driven solutions. Studies show that incorporating driving conditions and intelligent learning mechanisms can significantly improve energy efficiency and reduce fuel consumption in PHEVs. Furthermore, neural network-based EMS models have demonstrated strong generalization capabilities across diverse driving cycles. This review highlights recent advancements, challenges, and future directions in integrating bio-inspired optimization algorithms with graph-based deep learning architectures for efficient and intelligent energy management in next-generation hybrid vehicles.