Semantic Web-Based Energy-Efficient Design of Dual-Mode Vehicles Based on Deep Neural Networks

Abstract

Dual-Mode Vehicles (DMVs) represent a new and sustainable solution to the problems of urban mobility, and energy consumption. This proposed work of a DMV can operate without a conventional battery. Instead, it uses a combination of energy management technology, renewable energy systems, and other energy sources to ensure continuous operation. The efficiency and the working statistics of such DMV could also be sufficiently monitored through semantic techniques. The user can freely choose the type of working of the vehicle based on the current inputs given by the users. These semantics serve a crucial role in establishing a reference model for seamless data exchange between the trained Bald Eagle Search (BES) algorithm and the deep neural network (DNN). This proposed work has been implemented and the performance has been analyzed concerning the State Of Charging (SOC), generator voltage, and DC-DC converter voltage. The proposed work yields higher SOC and voltage than other existing schemes.