Machine Learning for Link Adaptation Problem Formulation in VANETs

Vehicular Ad Hoc Networks (VANETs) have emerged as a promising technology for improving road safety, traffic efficiency, and the overall driving experience. In VANETs, vehicles communicate with each other and with roadside infrastructure to exchange critical safety messages and traffic information. However, the dynamic nature of vehicular environments, including varying vehicular speeds, channel conditions, and network topologies, poses challenges to maintaining reliable and efficient communication links. The current work presents an approach to analyze a specific domain-related problem, formulate it, and develop a machine learning model for Link Adaptation (LA) that could be used in the future to improve communication efficiency in VANETs. As a result, the analysis derived from the developed model demonstrates some consistency in predicting optimal MCS values, accounting for both the relative mobility of the involved nodes and the available signal-to-noise ratio (SNR) level. The proposed Machine learning-based LA model presents a promising avenue to optimize vehicular communication performance, thereby contributing to the realization of safer and smarter transportation systems.