Abstract:

In this manuscript, a hybrid technique is proposed for the energy management (EM) of hybrid energy storage systems (HESS) in electric vehicles (EVs). The proposed technique, named SCSO-RERNN, combines sand cat swarm optimization (SCSO) and recalling enhanced recurrent neural networks (RERNN) to optimize the energy allocation and control strategy of HESS in EVs. The objective of the proposed system is to regulate the direct current (DC) bus voltage and track the battery and supercapacitor (SC) with desired references under various load conditions. The SCSO-RERNN technique optimizes the SC reference voltage, SC voltage, battery current magnitude, fuel cell (FC) voltage, and battery power and current variations. By utilizing this hybrid energy management unit, optimal EM of HESS in EVs is achieved. The proposed approach significantly reduces computation time and algorithm complexity while maintaining dc-bus voltage regulation and power balance. The performance of the hybrid ESS is measured by comparing it with existing approaches. The result shows that the proposed hybrid method shows the best solution with the least amount of computing time. The execution of the proposed method is carried out in MATLAB, and further, it is validating its effectiveness and feasibility.