Artificial Intelligence-Based Energy Management and Real-Time Optimization in Electric and Hybrid Electric Vehicles

Document Type


Publication Date



The depletion of fossil fuel and growing environmental pollution has led to the transformation of the transportation industry with the development of electric vehicles that run on clean and green energy. The rapid development in this field is driven towards replacing traditional power structures with smart power management models. This directs towards improving the efficiency of fuel cells and the system output performance in electric and hybrid electric vehicles. The fuel cell life is affected by the drive system and its control characteristics in a hybrid power system. The system operation is ensured by optimization of performance and strategical energy management in the hybrid system using power train model, dynamic programming (DP), and deep learning schemes. Tuning the equivalent factor (EF) dynamically can be done by equivalent consumption minimum strategy (ECMS) in plug-in hybrid electric vehicles (PHEVs) for achieving near-optimal fuel efficiency. Artificial intelligence is used for determining the EF in ECMS by analysis of available data. The State of Charge (SoC) values are varied to perform simulation under diverse conditions. When compared to the existing optimization techniques, the proposed model offers improved fuel economy. The energy management scheme is also time-conscious as the computational time for the entire trip duration is optimized. The training sample size and its impact on the performance of the AI module are also discussed.

Publication Title

EAI/Springer Innovations in Communication and Computing

First Page Number


Last Page Number




This document is currently not available here.