An improved MPC-based energy management strategy for hybrid vehicles using V2V and V2I communications

The energy management strategy (EMS) and its real-time adjustment ability accordingly influence a lot on the fuel economy of a hybrid electric vehicle. This paper proposes an improved model predictive control (MPC) framework for the EMS of plug-in hybrid electric buses (PHEB). It aims to achieve optimal energy distribution with increased prediction accuracy and optimized speed sequences by integrating the V2V and V2I information. Firstly, when PHEB is driving between two traffic intersections, the speed prediction accuracy is improved with the Particle Swarm Optimization (PSO) method optimizing the initial value of the Extreme Learning Machine (ELM). Based on the information from V2V, the instantaneous safe speed is calculated and used as a reference to update the predicted speed and reduce speed fluctuations. Secondly, when passing through a traffic intersection, the optimal speed sequence is planned in advance by the dynamic planning algorithm, with the PHEB's state at the traffic intersection is predicted based on the current signal state (red-yellow-green). Finally, combining speed prediction and speed planning with rolling optimization and feedback correction, MPC-based optimal energy management is achieved. The experimental results show that under the new MPC framework, fuel consumption is reduced by 13.55% relative to the rule-based strategy.