Abstract
Vehicular Ad-hoc Network (VANET) is an emerging technique dedicated to wireless vehicular communication to improve transportation safety by exchanging driving information between vehicles. For safety purposes, vehicles periodically broadcast a safety packet via Vehicle-to-Vehicle (V2V) communication. Accordingly, VANET safety applications demand a reliable exchange of the safety packet with high Packet Delivery Ratio (PDR), acceptable latency, and communication fairness. However, the communication performance significantly degrades due to numerous packet collisions when a large number of vehicles simultaneously access limited channel resources for the safety broadcast. In particular, the problem grows more severe in congested VANETs absent infrastructures since vehicles must control channel access using a self-adaptive scheme without external assistance. Thus, a robust and decentralized channel access protocol for VANETs is required to achieve road safety. In this paper, we propose an intelligent channel access algorithm empowered by cooperative Reinforcement Learning (RL), in which vehicles coordinate the channel access in a fully-decentralized manner. We also consider a proper interaction scheme between vehicles for enhancing the V2V safety broadcast in infrastructure-less congested VANETs. We provide evaluation results with extensive simulations according to various levels of traffic congestion. Simulations confirm the superior performance of the algorithm: the algorithm has a 20% increase in PDR compared to the latest RL-based channel access scheme. Furthermore, the algorithm satisfies the low latency requirement of VANET safety applications as well as both short-term and long-term communication fairness.
Highlights
Vehicular ad-hoc Network (VANET) is an emerging technique that allows vehicular wireless communication to achieve transportation safety by exchanging traffic information between vehicles with infrastructures [1]
We propose a novel cooperative Reinforcement Learning (RL)-based channel access algorithm employing Dec-Partially Observable MDP (POMDP) modeling to achieve high Packet Delivery Ratio (PDR), acceptable end-to-end delay, and communication fairness for the safety broadcast in infraless congested VANETs
We introduce the basics of VANETs including multi-channel Dedicated Short-Range Communication (DSRC), various communication requirements, and the principle of Carrier-Sense Multiple Access with Collision Avoidance (CSMA/CA)
Summary
Vehicular ad-hoc Network (VANET) is an emerging technique that allows vehicular wireless communication to achieve transportation safety by exchanging traffic information between vehicles with infrastructures [1]. CCA-based protocols [8] provide the highly stable performance on the safety broadcast, these may not be optimal solutions due to the following two distinctive features of VANETs: (1) infrastructures are sparsely located, and these cannot provide unlimited communication coverage [9]; (2) network topology and components are frequently changed by the dynamic movement of vehicles, so the synchronization and connection cannot be steady state [10]. We propose a novel cooperative RL-based channel access algorithm employing Dec-POMDP modeling to achieve high PDR, acceptable end-to-end delay, and communication fairness for the safety broadcast in infraless congested VANETs. The proposed algorithm enables cooperation among vehicles by exchanging minimal additional data following an alternative multi-channel protocol of DSRC, which does not interfere with the safety broadcast.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
