OTFS with Machine Learning for Efficient and Reliable Data Transmission in VANETs

Orthogonal time-frequency space modulation (OTFS) is a advance modulation technique using in the 5$^{\mathbf{th}}$ generation of wireless communications and beyond. In recent years, Vehicular Ad-hoc Networks (VANETs) have developed as a potentially useful technology for enhancing both the safety of roadways and the efficiency of traffic flow. In order for VANETs applications to function properly, such as the broadcast of real-time traffic information and the prevention of collisions, it is essential that data transmission be both efficient and trustworthy. In spite of this, VANETs are confronted with a distinct set of issues because of its dynamic architecture and the great mobility of vehicles. These traditional data transmission technologies often experience frequent connection breakdowns, which may result in the loss of data. Using a mix of random forest machine learning and Enhanced OTFS modulation, this research presents a unique way for efficient and reliable data transmission in VANETs. The approach is innovative since it combines the two techniques. In order to identify the ideal transmission parameters, such as transmission power and modulation scheme, for each vehicle, random forest machine learning is used. This allows for the enhanced data transmission, which is accomplished by the use of enhanced OTFS, provides improved spectral efficiency and reduces latency.