Nature-inspired grey wolf optimization for intelligent speed control and energy efficiency in electric vehicles

Abstract Heuristic optimization algorithms play a crucial role in smart systems due to their ability to quickly find optimal solutions to nonlinear problems that are difficult to address using traditional methods. This study applied the Grey Wolf Optimization (GWO) algorithm to determine the optimal set of parameters for the speed control loop in an electric vehicle model (EV). The main objective is to minimize overshoot, rise time, settling time, and static error of EV. In this study, the proposed algorithm is implemented on the MicroAutoBox III dSPACE hardware with a hardware-in-the-loop (HIL) to demonstrate the optimization of speed response and load disturbance rejection through testing at various motor speeds. Additionally, the proposed algorithm was compared with the ant colony optimization (ACO) algorithm, the Fuzzy PID, and the classical PID algorithm to evaluate the speed deviation, state-of-charge efficiency (SOC), and response speed of electric vehicles using the extra-urban driving cycle (EUDC), thereby demonstrating the superiority of the algorithm. Moreover, experimental results reveal that the proposed algorithm eliminates the overshoot phenomenon and significantly shortens the response time and settling time. Upon completion of the EUDC testing process, the GWO algorithm demonstrated superior energy efficiency, with a remaining battery capacity of 99.982233%. This performance notably surpassed ACO by 0.000010%, Fuzzy PID by 0.000574%, and the traditional PID by 0.000580%, thereby improving battery efficiency and extending the operating range of electric vehicles. Notably, these improvements confirm the superiority of the algorithm over traditional control methods such as ACO, Fuzzy PID, and PID.