Integrating Machine Learning With Vanet For Enhanced Decision Making: A Review

---

Abstract

Transmissions are one of the most challenges to address in VANET. VANETs are subject to frequent topology and communication link modifications as a consequence of the rapid mobility of vehicles. The best routes may not be the most efficient if researchers are unable to get exact real time traffic densities because vehicle densities fluctuate so frequently; consequently, the best routes may not be the most efficient. By predicting automobile movements, research may then use machine learning to choose the most effective paths for transferring packets. VANET-based smart automobiles have made commuting safer, more efficient, more fun, more environmentally friendly, and more cost-effective than it has ever been. If crucial events are communicated on a regular basis, high safety may be attained in this setting. Reduced traffic and pollution, as well as more predictable travel times, are all necessary if we are to enhance productivity. Research paper focused on machine learning and wireless ad hoc networks, VANET and VANET routing protocols. Then past studies have been expressed along with methodologies and limitations. Vanet's routing protocols have been categorized and issues in prior studies are taken into account.

---

Keywords

Wireless ad hoc Network, VANET and Routing Protocols, Machine Learning.