An efficient self-organized traffic maintenance scheme employing positive selection algorithm.

Virtual Traffic Lights (VTLs) come under the umbrella of Vehicular Adhoc Networks (VANETs) and are self-organized systems to implement traffic light control systems at a road intersection. During a VTL lifetime, VTLs may fail to maintain the uninterrupted working of the traffic light system. The vehicles arriving after a stable cluster formation and ongoing operation of VTL may go unattended which can weaken its application effect. If a new vehicle approaches the intersection, it either needs to get re-clustered with the current VTL cluster or has to form a new cluster with other arriving vehicles. In this paper, we aim to incorporate the Positive Selection Algorithm (PSA) scheme which is flourished with Artificial Immune System (AIS) behaviour to detect and control this anomalous clustering condition of the VTL traffic management systems. We propose the Adaptive Layer Positive Selection Algorithm (ALPSA) for monitoring the participating and non-participating vehicles; which are detected by appropriate detectors, generated through the algorithm. The algorithm works in layers and has two phases. Prior to the algorithm, we present a mobility model to generate the metrics for appropriate clustering. We extensively evaluate the ALPSA where results validate the management with reduced 'similarity detection time' and better 'similarity detection rate'. The similarity detection time is the response time given to the vehicles to decide whether to join the VTL cluster or not. Therefore, reduction in this time has shown better working for VTLs. [ABSTRACT FROM AUTHOR]