The Internet of Vehicles (IoV) is defined as the interconnected system of smart vehicles and infrastructures. So many operational considerations such as scalability, data privacy, and high availability hinder the performance efficiency of intelligent transpiration systems. Federated learning solves such issues by enabling collaborative and distributed intelligence among multiple entities without leaking the privacy level of users. The federated learning meets the necessitated ITS performance with high security while maintaining privacy. It overcomes the faults and network failures quickly and assures intelligent communication service continuity. The federated learning models simultaneously address the performance and security issues of IoVs.