Optimizing fuel cell power: an online energy management strategy for extended range in fuel cell hybrid electric vehicles

The automotive business is growing continuously along with the global economy. One way to lessen environmental pollution in recent times is to look for clean energy to replace traditional fossil fuels as the vehicle's power source. This is because there is a lack of environmental energy among other issues. This manuscript proposes an Energy Management Strategy of Fuel Cell Hybrid Electric Vehicles. The proposed hybrid technique is the joint execution of both the Giant Trevally Optimizer (GTO) and Hierarchically Gated Recurrent Neural Network (HGRNN). Hence, it is named as GTO-HGRNN technique. This proposed method's principal objective is to reduce hydrogen use and raise battery longevity. The proposed GTO approach is used to optimize the DC/DC converter parameter and fuel consumption and the HGRNN approach is used to predict the optimal parameter of the DC/DC converter parameter. By then, the MATLAB platform has the proposed method been implemented, and the existing method is used to compute the execution. Better outcomes are shown by the proposed strategy in all existing systems like Genetic Algorithm, Global Optimisation Algorithms, and Particle Swarm Optimization. The existing method shows hydrogen consumption of 0.4%, 0.3%, and 0.2% the proposed method shows a hydrogen consumption of 0.1% which is lower than another existing system. The existing method shows the cost of 14.90$, 15.90$, and 16.90$ the proposed method shows the cost of 13.90$, which is lower than another existing system.