Title: Vehicular cloud networking: evolutionary game with reinforcement learning-based access approach

Authors: Tesnim Mekki; Issam Jabri; Abderrezak Rachedi; Maher Ben Jemaa

Addresses: REDCAD Laboratory, National School of Engineers of Sfax, Sfax, Tunisia ' College of Engineering and Architecture, Al Yamamah University, King Fahd Branch Road, Al Qirwan, Riyadh 13541, KSA ' Universite Paris-Est Marne-la-Vallee, LIGM (UMR8049), CNRS, ENPC, UPEM, F-77454, France ' REDCAD Laboratory, National School of Engineers of Sfax, Sfax, Tunisia

Abstract: In this paper, we study the vehicular cloud access problem. We model it as an evolutionary game where the vehicles choose to cooperate or to access the conventional cloud through the LTE link. We focus on the centralised case, and we study the equilibrium of both homogeneous and heterogeneous players analytically. We propose an evolutionary game-based vehicular cloud access algorithm (EG-VCA). Moreover, we propose a distributed Q-learning-based vehicular cloud access algorithm (QL-VCA) that allows each vehicle to select the way to access independently to avoid the use of a centralised controller. The simulation results show that QL-VCA and EG-VCA algorithms present almost the same performances. Also, they offer better results compared to the cases of using and accessing only the CC or the VC. Numerical results are also established. They outline the convergence of the two algorithms to the same state of equilibrium.

Keywords: vehicular ad hoc network; VANET; vehicular cloud networks; evolutionary game; reinforcement learning; Q-learning.

DOI: 10.1504/IJBIC.2019.097730

International Journal of Bio-Inspired Computation, 2019 Vol.13 No.1, pp.45 - 58

Received: 01 Feb 2018
Accepted: 28 Jul 2018
Published online: 06 Feb 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article