Congestion Control System Optimization with the Use of Vehicle Edge Computing in VANET Powered by Machine Learning

Vehicular Ad Hoc Networks (VANETs) have recently given rise to a wide range of applications for security, infotainment, rescue, and safety-related reasons. The future of V2V communication systems and related applications relies heavily on VANET. Communication channel congestion concerns have had a negative influence on safety applications, which are a result of a range of network uses. Vehicle traffic is negatively impacted by channel congestion, which causes packet loss, delays, and unreliability. This in turn leads to traffic accidents, traffic bottlenecks, and incorrect traffic decisions. This paper introduces a new idea for VANET forwarding of packets and congestion control that is based on utilities. Therefore, an Optimization for Congestion Control System using Machine Learning [OCCS-ML] is proposed based on packet forwarding is introduced to solve the issues by the method for the secure and prompt transfer of data, as it pertains to security projects. A communication channel is the intended target of the proposed scheme, which aims to guarantee the timely and dependable delivery of messages to all network neighbors and serve as a medium for broadcasting safety alerts. Vehicles to vehicle communication is the intended use of the proposed scheme, which does not rely on any permanent infrastructure. Each data packet that is transferred contains quantitative utility information in a visible manner for all users in a local environment. This information is encoded using an applicationspecific utility function. There has been a substantial improvement in the accuracy and efficiency of information distribution.