Adaptive Federated Learning for Efficient Network Traffic Management in Edge Computing

With the increasing prevalence of edge computing environment, there is a need to establish effective network traffic management that are able to manage vast data while also protecting the privacy of users. The proposed method enhances efficiency of bandwidth, reduce the network latency and manages computational demands without managing data privacy. This is achieved by utilizing the design of edge devices. The adaptable nature of the method enables it to react in real time to different traffic situations. It optimizes the distribution of resources and improves the overall performance of the network. Additionally, it can reduce the possibility of centralized data exposure, providing robust privacy preservation through the allowance of local model training on edge devices. Finally, this method is superior. The employment of federated learning to network traffic management provide efficiency to optimize the traffic in edge computing which is both scalable and safe. This makes it suitable for a wide variety of applications that are utilized in next generation networks