Abstract—By the prediction of future location for a vehicle in Internet of Vehicles (IoV), data forwarding schemes can be further improved. Major parameters for vehicle position prediction includes traffic density, motion, road conditions, and vehicle current position. In this paper, therefore, our proposed system enforces the accurate prediction with the help of real- time traffic from the vehicles. In addition, the proposed Neural Network Model assists Edge Controller and centralized controller to compute and predict vehicle future position inside and outside of the vicinity, respectively. Last but not least, in order to get real-time data, and to maintain a quality of experience, the edge controller is explored with Software Defined Internet of Vehicles. In order to evaluate our framework, SUMO simulator with Open Street map is considered and the results prove the importance of vehicle position prediction for vehicular networks.

 

Index Terms—Vehicle to Anything (V2X), position prediction, SDN, edge controllers, internet of vehicles, GIS, neural network

Cite: Muhammad Ali Jibran, Muhammad Tahir Abbas, Adeel Rafiq, and Wang-Cheol Song, “Position Prediction for Routing in Software Defined Internet of Vehicles,”Journal of Communications vol. 15, no. 2, pp. 157-163, February 2020. Doi: 10.12720/jcm.15.2.157-163

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.