Vehicular ad hoc networks (VANETs), a wireless technology for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, are integral to the development of emerging Intelligent Transportation Systems (ITS) that aim to improve road safety and driver experience. Safety applications require reliable dissemination of periodic basic safety messages (BSMs) and event-driven warnings over a dynamic and bandwidth-constrained network. Therefore, effective strategies are needed to balance channel load with the need for up-to-date vehicle information to maintain adequate situational awareness. In this paper, we present a novel congestion control approach, where reinforcement learning is used to train the model to select suitable transmission power levels for transmitting each BSM. The goal of the proposed algorithm is to utilize the channel bandwidth intelligently, by maintaining the channel load at or near a specified threshold, without exceeding it. Our simulation results indicate that the proposed technique is able to maintain a balanced channel load and achieve lower beacon error rates and inter-packet delays.
Transmission Power Based Congestion Control Using Q-Learning Algorithm in Vehicular Ad Hoc Networks (VANET)
Lect.Notes Mechanical Engineering
International Conference Innovation in Engineering ; 2024 ; Povoação , Portugal June 26, 2024 - June 28, 2024
2024-07-16
12 pages
Article/Chapter (Book)
Electronic Resource
English