A VANET Collision Warning System with Cloud Aided Pliable Q-Learning and Safety Message

The international arab journal of information technology

article

Nalina Venkatamune¹  Jayarekha PrabhaShankar¹ 

[1] Department of Information Science and Engineering, BMS College of Engineering

关键词: VANETs;    collision warning system;    reinforcement learning;    pliable q-learning;    multi-attribute cost baseddisseminator selection;    reliable safety routing;   

DOI  :  10.34028/iajit/20/1/12

学科分类：计算机科学（综合）

来源: Zarqa University

【 摘 要 】

Ease of self-driving technological developments revives Vehicular Adhoc Networks (VANETs) and motivates theIntelligent Transportation System (ITS) to develop novel intelligent solutions to amplify the VANET safety and efficiency.Collision warning system plays a significant role in VANET due to the avoidance of fatalities in vehicle crashes. Differentkinds of collision warning systems have been designed for diverse VANET scenarios. Among them, reinforcement-basedmachine learning algorithms receive much attention due to the dispensable of explicit modeling about the environment.However, it is a censorious task to retrieve the Q-learning parameters from the dynamic VANET environment effectively. Tohandle such issue and safer the VANET driving environment, this paper proposes a cloud aided pliable Q-Learning basedCollision Warning Prediction and Safety message Dissemination (QCP-SD). The proposed QCP-SD integrates twomechanisms that are pliable Q-learning based collision prediction and Safety alert Message Dissemination. Firstly, thedesigning of pliable Q-learning parameters based on dynamic VANET factors with Q-learning enhances collision predictionaccuracy. Further, it estimates the novel metric named as Collision Risk Factor (CRF) and minimizes the driving risks due tovehicle crashes. The execution of pliable Q-learning only at RSUs minimizes the vehicle burden and reduces the designcomplexity. Secondly, the QCP-SD sends alerts to the vehicles in the risky region through highly efficient next-hopdisseminators selected based on a multi-attribute cost value. Moreover, the performance of QCP-SD is evaluated throughNetwork Simulator (NS-2). The efficiency is analyzed using the performance metrics that are duplicate packet, latency, packetloss, packet delivery ratio, secondary collision, throughput, and overhead.

【 授权许可】

Unknown