![](http://icmc2024.kalasalingam.ac.in/wp-content/uploads/2023/05/Mahesh-HCL.jpeg)
Mohammad S. Obaidat
University of Texas-Permian Basin, USA
Smart Energy Harvesting and Traffic Flow Prediction Methodology for Plug-In Electric Vehicles
In order to maintain the reliability and transparency of power distribution to consumers, smart grids (SGs) are envisioned to become one of the leading technologies while the use of plug-in electric vehicles (PEVs) has increased exponentially. However, due to indeterminate demands for the use of resources of SGs, there may be a performance bottleneck at some points in SGs. An intelligent infrastructural support for PEVs is thus required so that the PEVs can perform energy trading from the SG control center. The energy can be generated from various conventional and nonconventional sources. Here, we present an intelligent energy harvesting and traffic flow forecasting for PEVs in a vehicle-to-grid (V2G) environment. In the proposed game, vehicles are assumed as the players of the game such that learning components are assumed to be deployed on these vehicles having cooperation with intermediate relay nodes. The choice of the relay nodes is completed using a Naive Bayes classifier having input parameters as the current payoff of the players in the game. The Payoff Value (PV) is given to the players using the link quality and mobility pattern. The proposed scheme is evaluated using the performance metrics of probability of data delivery, delay incurred, operational cost, and energy gap. The results corroborate the effectiveness of the proposed coalition game in a V2G environment.