Key points are not available for this paper at this time.
Hybrid electric vehicles (HEVs) are set to play a critical role in the future of the automotive industry. To operate efficiently, HEVs require a robust energy management strategy (EMS) that decides whether the vehicle is powered by the engine or electric motors while managing the battery’s state of charge. The EMS must rapidly adapt to driver demands and optimize energy usage, ideally predicting battery charge rates and fuel consumption to adjust the powertrain in real time, even under unpredictable driving conditions. As HEVs become more prevalent, EMS technologies will advance to improve predictive capabilities. This analysis provides an overview of current EMS systems, including both rule-based and optimization-based approaches. It explores the evolution of EMS development through a technology roadmap, highlighting the integration of advanced algorithms such as reinforcement learning and deep learning. The analysis addresses the technologies that underly this evolution, including machine learning, cloud computing, computer vision, and swarm technology. Key advances and challenges in these technologies are discussed, along with their implications for the next generation of EMS systems for HEVs. The analysis of these technologies indicates that they will play a key role in the evolution of EMS technology, allowing it to better optimize driver needs and fuel economy.
Mittal et al. (Wed,) studied this question.