MEET: Advancing Mobility-Enhanced Edge Intelligence for Efficient and Sustainable 6G Networks

A machine learning technique known as federated learning, or collaborative learning, allows edge devices to cooperatively integrate to a global model while retaining local copies of their data. The integration of edge AI, IoT, and communication technologies can be greatly improved via federated learning. Because of the abundance of devices, apps, and services available in the modern digital era, users have higher expectations and demands for quality of service (QoS) from network service providers. As a result, extensive deployment of base stations (BSs) overall edge servers (ESs) is required, which raises the cost of deployment and operation—particularly energy expenditures. In order to add flexibility to the creation of the traffic along with mobility management algorithms, the current work makes use of fuzzy logic. Enhancing the quality of service (QoS) of current mobility management solutions and making optimum use of available network resources are the main goals of the research project. In this study, we examine a novel architecture for the efficient and environmentally friendly 6G systems dubbed Mobility-Enhanced Edge inTelligence (MEET), that takes advantage of the detection, communication, computation, and automatic features of intelligent linked vehicles.