Joint Edge Server Selection and Data Set Management for Federated-Learning-Enabled Mobile Traffic Prediction

To realize intelligent network management for future 6G-mobile edge computing (MEC) systems, mobile traffic prediction is crucial. Most of the previous machine learning-driven prediction approaches adopt traditional centralized training paradigm wherein mobile traffic data should be transferred to a central server. To exploit the distributed and parallel processing nature of MEC servers for training mobile traffic prediction models in a fast and secure manner, we propose a novel federated learning (FL) framework wherein locally trained prediction models over MEC servers are aggregated into a global model with joint optimization of MEC server selection and data set management for FL participation. From mathematical investigations of the influence of MEC server participation and data set utilization on the global model accuracy and training costs, including both training latency and energy consumption in the FL process, we first formulate an optimization problem for balancing the accuracy-cost tradeoff by considering a linear accuracy estimation model. Here, the optimization problem is designed using mixed-integer nonlinear programming, which is generally known as NP-hard. We then leverage a number of relaxation techniques to develop near-optimal yet the plausible algorithm based on linear programming. Furthermore, for practical concern, the proposed problem is extended by considering a concave accuracy estimation model; a genetic-based heuristic approach to the extension is proposed for determining the suboptimal solution. The numerical and simulation results suggest that our proposed framework can be effective for building mobile traffic prediction models in a more cost-efficient manner while maintaining competitive prediction accuracy.

I. Introduction

With the renaissance and democratization of artificial intelligence (AI) and machine learning (ML), AI-driven control for wireless communication networks has been attracting significant attention from industry and academia toward the sixth generation (6G) and mobile edge computing (MEC) technologies, considering ML as a key enabler for introducing more advanced intelligence into the network management domain (e.g., traffic prediction, application classification, intrusion/anomaly detection, resource scheduling/allocation, routing, etc.) [1]. Following this trend, the 3rd Generation Partnership Project (3GPP) has been actively working on AI-driven control by introducing new types of control plane (CP) services in its technical specifications; a network data analytics function (NWDAF) that provides both training and inference [2], [3]. Specifically, in 6G-MEC systems, because of the heterogeneous service requirements for various devices (e.g., smartphones, sensors, vehicles, drones, factory machines, etc.), a variety of AI-driven mobile traffic prediction schemes have been proposed for proactive, automated, and cost-efficient network resource management [4].