A Reliable Sensor Network Infrastructure for Electric Vehicles to Enable Dynamic Wireless Charging Based on Machine Learning Technique

Abstract

In this paper, a hybrid scheme of Dynamic wireless charging (DWC) for electric vehicles EV(s) is proposed to resolve this issue in a network topological infrastructure. The proposed hybrid scheme uses different parameters to allow DWC in EVs. The network infrastructure was established through an enhanced destination sequential distance vector (Enhanced-DSDV) protocol for participating EVs. The DWC charge between paired EV(s) was enabled by magnetic coupling, where the Charge State Estimator (CSE) was used as an unsupervised machine learning technique to learn the current charging status of each EV. Similarly, the captured data of CSE is shared via embedded wireless nodes in the network following enhanced-DSDV routing protocol. Moreover, the proposed model enables each participating EV to transfer charge to another EV participating in the network in DWC environment. To allow, the drivers to monitor the participating EVs in close proximity with their current charge status, location, and distance information, we have have used a dashboard screen in each EV. In addition, each EV uses a generator to produce a magnetic field for magnetic coupling between paired EV(s) to exchange power in wireless environment. The feasibility of the proposed model was thoroughly examined in the real environment of DWC. The results show that the proposed scheme is reliable in terms of DWC in both static and dynamic. Moreover, the enhanced-DSDV routing protocol performed significantly well than existing schemes particularly in terms of throughput, packet lost ratio and latency.

Keywords

• Electric vehicles
• network topology
• charging estimator
• electric generator
• machine learning
• enhanced-DSDV routing protocol