Making a Case for Federated Learning in the Internet of Vehicles and Intelligent Transportation Systems

With the incoming introduction of 5G networks and the advancement in\ntechnologies, such as Network Function Virtualization and Software Defined\nNetworking, new and emerging networking technologies and use cases are taking\nshape. One such technology is the Internet of Vehicles (IoV), which describes\nan interconnected system of vehicles and infrastructure. Coupled with recent\ndevelopments in artificial intelligence and machine learning, the IoV is\ntransformed into an Intelligent Transportation System (ITS). There are,\nhowever, several operational considerations that hinder the adoption of ITS\nsystems, including scalability, high availability, and data privacy. To address\nthese challenges, Federated Learning, a collaborative and distributed\nintelligence technique, is suggested. Through an ITS case study, the ability of\na federated model deployed on roadside infrastructure throughout the network to\nrecover from faults by leveraging group intelligence while reducing recovery\ntime and restoring acceptable system performance is highlighted. With a\nmultitude of use cases and benefits, Federated Learning is a key enabler for\nITS and is poised to achieve widespread implementation in 5G and beyond\nnetworks and applications.\n