Energy Optimization of the Multi-objective Control System for Pure Electric Vehicles based on Deep Learning

Abstract

Advancements in information technology have revolutionized multiple sectors such as healthcare, industrial control, and environmental monitoring. With the advent of smaller, more sophisticated and wireless sensors, their applications have expanded across various industries. These sensors offer numerous advantages like cost-effectiveness, easy setup, reliable transmission, and high capacity for data processing. However, despite their benefits, there are certain limitations to consider. The primary constraint that affects their lifespan is energy availability, as replacing or recharging power sources for nodes can be challenging or infeasible. The reliance on batteries hampers data analysis by network nodes, hindering the exchange of information. Hence, prolonging the network's overall lifespan is crucial for optimizing its performance. The existing approaches, with their tried-and-tested practices and heterogeneity, require enhancements to address specific characteristics. In every application, two critical aspects are the duration of network operation and energy consumption for data routing. Through comparative analysis, it is evident that various algorithms and techniques can reduce energy usage to different extents. Based on these findings, a recommended strategy is to achieve a significant 70% reduction in energy consumption.