Grey wolf fuzzy optimal energy management for electric vehicles based on driving condition prediction

Abstract

An energy management strategy (EMS) plays a decisive role in the performance of pure electric vehicles. Meanwhile, the effectiveness of EMS is directly affected by prospective driving conditions. This paper conducted research on grey wolf fuzzy optimal energy management strategy optimization for electric vehicles based on driving condition prediction. In order to improve the accuracy of driving condition prediction, a combined prediction method was proposed which combines fixed state transition matrix prediction and rolling prediction based on cycling conditions. The evaluation results show that the proposed solution has better prediction accuracy than previous approach. Then, this paper adopted the fuzzy logic control strategy based on driving condition prediction, which is optimized by using the grey wolf optimizer (GWO) algorithm. The results of simulation analysis revealed that the energy management strategy combining condition prediction and GWO algorithm had significant improvement in energy consumption rate and other indicators. Finally, the hardware-in-the-loop (HIL) experiments were conducted and the results had good coherence to that of the simulation. This verified the feasibility and effectiveness of the proposed control strategy in a real-time environment.