A Hybrid Secure Resource Allocation and Trajectory Optimization Approach for Mobile Edge Computing Using Federated Learning Based on WEB 3.0

Abstract

The use of unmanned aerial vehicles (UAVs) in internet-of-things (IoT) has grown, but security for UAV communications still a challenge due to the distributed nature of line-of-sight communication networks. This paper analyses the security issues for UAV-assisted MEC systems, in which UAVs are used to support base stations (BSs) in computing offloaded workloads while also operate as jammers to inhibit malicious eavesdroppers. In this paper, a minimum secure computing capacity maximization issues is addressed by jointly optimizing communication link, computation resources, and UAVs trajectories. These issues are of a non-trivial nature and present a significant challenge to be resolved due to the presence of highly coupled variables. In order to effectively overcome these issues, we introduced the concept of WEB 3.0. Firstly, we introduced blockchain method to enhance security to the UAV assisted MEC system and then to train the data locally and to solve various wireless schemes problems, respectively we proposed a FL method. To contribute to the literature, we developed an effective resource allocation strategy that maximizes computational offloading using WEB 3.0, a Blockchain-based FRL method. Finally, numerical findings indicate that the suggested techniques improve the security computation capacity efficiency of the systems when compared to the standards.