Congestion Articulation Control Using Machine Learning Technique

Abstract

Congestion is the most serious issue in both Adhoc mobile networking and regular road traffic systems. The definition of a vehicle is changing as the automotive industry advances. Nowadays, all automobiles are outfitted with the most up-to-date sensors and communication capabilities. Mobile Ad Hoc Network that avoids traffic jams and articulation issues while also saving time by receiving direction from the GPS system on the shortest path using various algorithms. It also provides information on road safety and where to go. It repeatedly recalculates the shortest way using multiple algorithms to ensure that the user does not become stuck and stranded in traffic. From the point of view of research, this paper defines the architecture and protocols. However, VANETs are a subset of MANETs and constitute the future of Intelligent Transportation Systems. The development of big data, the latest sensors and probing vehicle data, as well as the widespread use of machine learning technologies, has given articulation control measurement in the traffic congestion area a completely new and different direction. By examining multiple traffic metrics. With machine learning, it is straightforward to forecast traffic congestion. This study is based on traffic congestion forecasting in real-time. This paper presents a summary of recent research conducted using various AI approaches and machine learning models.