ML-based Minimization of AoI in a Vehicular Communication Network

The self-driving cars have increased the need for better intelligent transportation systems. To facilitate the usage of these automated vehicles, very efficient real-time data monitoring in the network is required in the Intelligent Transportation System (ITS). In various applications of ITS, it is critical to maintain the information’s freshness. Similarly, sensory devices on vehicles produce a huge amount of information in a short time, and half of the data received is redundant. Storing all the received information is a waste of time and resources. In this paper, we propose a system for better transfer of data between vehicles and the Road Side Unit (RSU) through Vehicle to Infrastructure (V2I) communication by Efficiently Minimizing the Age of Information. We propose a method to Efficiently Minimize the Age of Information by considering two factors, the delay, and throughput of a data packet to calculate the weighted sum of the AoI. We further use the Alpha-Beta pruning algorithm, an ML-based optimization algorithm to find an optimal solution. The proposed system is verified by simulating the proposed system in the OMNET++ network simulator and the reliability of its efficiency is concluded by comparing the computation time with another algorithm.