Abstract: Vehicular Ad hoc Network (VANET) could be a taxonomic category of Mobile Ad hoc Network (MANET) where vehicles are simulated as mobile nodes. VANET is an emerging new technology which has some unique characteristics that differs from other ad-hoc network. Aiming at the performance degradation in Vehicular Sensor Networks (VSNs) it causes delay in receiving the emergency alerts. In order to address this problem collaborative learning automata-based routing algorithm (a clustering formation) is proposed for sending information to the intended destination in an effective manner. This approach consists of dividing whole region into completely different clusters, based on which an optimized path is selected using collaborative LA having input parameters such as vehicle density, distance and delay. Performance can also be obtained from the above parameters. The values of these parameters are passed on to the neighboring vehicles based on reward/penalty action. In the reward function, high cumulative weight is assigned for every successful transmission. In penalty function the cumulative weight is decreased for every unsuccessful transmission. The solution of a route depends upon the output produced by LA (Learning Automata) with minimum delay and maximum throughput.
K. Aravindhan and B. Evangeline Prasanna, 2016. A Cluster Approach in Vanet Using Collaborative Learning Automata-Based Routing. Asian Journal of Information Technology, 15: 4269-4275.