Federated Learning-Based Resource Allocation for Cloud-Edge Computing.

Abstract

Cloud-edge computing is a promising paradigm that can address the challenges of latency, bandwidth, and privacy in cloud computing. However, the edge nodes have limited resources, so it is important to allocate resources efficiently. This paper proposes a federated learning-based resource allocation framework for cloud-edge computing. The proposed framework consists of three main components: a federated learning algorithm, a resource allocation algorithm, and a secure communication protocol. The federated learning algorithm is responsible for training a machine learning model without sharing the data with a central server. The resource allocation algorithm is responsible for allocating resources to the edge nodes efficiently. The secure communication protocol is used to protect the privacy of the data during the federated learning process. The proposed framework is evaluated using simulations. The results show that the proposed framework can achieve better performance than traditional resource allocation algorithms.