Learning Automata-assisted Predictive Clustering approach for Vehicular Cyber-Physical System. (May 2016)

• Record Type: Journal Article
• Authors: Bali, Rasmeet Singh; Kumar, Neeraj
• Is Part Of: Computers & electrical engineering. Volume 52(2016)
• Page Start: 82
• Page End: 97
• Publication Date: 2016-05
• Subjects: Vehicular Adhoc Cyber-Physical Systems -- Predictive Clustering -- Learning Automata -- Stochastic environment -- Reward -- Penalty; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2015.09.007
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: LA-based predictive clustering is proposed by predicting the future mobility of the nodes in VANETs. Connecting dominating set is constructed to maintain connectivity of the vehicles. Predictive Clustering Algorithm using LA is proposed. The performance of the proposed scheme is evaluated in different network scenarios with respect to various metrics. Graphical abstract: Abstract: Vehicular Cyber-Physical Systems (VCPS) are the most popular systems of the modern era due to their abilities to disseminate the safety related information to the moving vehicles on time. For efficient data dissemination, vehicles form a cluster with other vehicles in VCPS environment. But, due to high velocity and constant topological changes, cluster maintenance is one of the most difficult tasks to be performed in this environment. To address this issue, in this paper, we propose a novel Learning Automata (LA)-based hybrid clustering scheme for vehicles in VCPS environment. We have improved our existing solution Energy Efficient Predictive Clustering (EEPC) approach, by incorporating the future mobility prediction computed by LA stationed on the vehicles. For this purpose, a Predictive Clustering Algorithm using Learning Automata (PCALA) is proposed. Extensive simulations are performed to evaluate the performance of the proposed scheme with respect to various metrics. Results obtained confirm the effectiveness of the proposed scheme in comparison to the existing EEPC scheme.