Safety information aggregation in VANETs using vehicle beliefs

Abstract

This paper proposes a safety information aggregation scheme in vehicular networks. We address the challenge in aggregating the collected safety information with minimum delay. Specifically, we consider the scenario of logical clusters on a lane where the number of vehicles sending periodic safety messages is too high. The scheme works over logically clustered vehicles by using a set of static and mobile agents. It operates in the following steps: (1) generation of beliefs based on collected safety information; (2) aggregating the beliefs to develop desire using a regression technique; (3) revision of desire for better quality of aggregation; and (4) finalizing the intention based on revised desire. Simulation results showed that the proposed scheme performs better in terms of critical information acquisition delay, aggregation delay and end-to-end delay.