Optimized control of hybrid energy storage systems for electric vehicles using BWPOA-MFPIDNN approach

The pure electric vehicle (EV) lies in its energy storage system (ESS), with batteries being the predominant choice for ESS implementation. Nonetheless, a pure EV equipped with a battery energy storage system (BESS) encounters challenges such as constrained driving range, diminished battery lifespan, and diminished power density. To solve this issue, this study proposed a hybrid method with Optimization of a Power-split management system for light electric vehicles with a hybrid energy storage system. The proposed hybrid method is the joint execution of both the Binary Waterwheel Plant Optimization Algorithm (BWPOA) and Prediction Using Multi-Fidelity Physics Informed Deep Neural Network (MFPIDNN). Hence, it is named as BWPOA-MFPIDNN. The proposed technique's main goal is to increase battery life and lower the system's overall operating costs. For electric vehicles with hybrid energy storage systems, the best power-split management system is obtained using the BWPOA method, while the rate of battery degradation is predicted using the MFPIDNN algorithm. By then, the MATLAB working platform has incorporated the proposed strategy, and the current process is utilized to determine the execution. The proposed technique displays better outcomes than all existing methods like Heap-based optimizer (HBO), Particle swarm optimization (PSO) and Slap Swarm Algorithm (SSA). The existing strategy shows the cost of 1.9$, 2.9$, 3.9$ and the proposed method shows the 0.9$. The existing methods demonstrate costs of $1.90, $2.90, and $3.90, whereas the proposed method is priced at $0.90. Battery life, the existing methods provide 15.35 %, 13.45 %, and 10.75 %, while the proposed method achieves a battery life of 17.91 %. These findings indicate that the proposed method not only presents a more cost-effective solution but also significantly improves battery life compared to the existing approaches. •The BWPOA-MFPIDNN hybrid method optimizes power-split management in hybrid energy storage.•It improves battery life (17.91 %) and reduces operational costs ($0.90), outperforming other methods.•BWPOA optimizes power, and MFPIDNN predicts battery degradation for better efficiency.•MATLAB implementation confirms superior performance in both cost and battery life.