Energy-Efficient Federated Learning and Migration in Digital Twin Edge Networks

2025-03-20

AI Summary

To address the high energy consumption and low model accuracy of federated learning (FL) in sixth-generation (6G) digital twin-enabled edge networks (DITEN), this paper jointly optimizes multi-dimensional energy consumption—encompassing digital twin association, historical data allocation, and long-term maintenance (i.e., FL training, data synchronization, and twin migration). We first formulate the impact of twin association and data allocation on FL model accuracy, proposing an analytically tractable data utility function and conducting rigorous convergence analysis. Building upon this, we establish a utility–energy co-optimization framework and design an optimization-driven learning algorithm. Experimental results demonstrate that the proposed approach significantly outperforms multiple baseline schemes in both model accuracy and energy efficiency. This work provides a verifiable, holistic optimization paradigm for green and intelligent 6G networks.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The digital twin edge network (DITEN) is a significant paradigm in the sixth-generation wireless system (6G) that aims to organize well-developed infrastructures to meet the requirements of evolving application scenarios. However, the impact of the interaction between the long-term DITEN maintenance and detailed digital twin tasks, which often entail privacy considerations, is commonly overlooked in current research. This paper addresses this issue by introducing a problem of digital twin association and historical data allocation for a federated learning (FL) task within DITEN. To achieve this goal, we start by introducing a closed-form function to predict the training accuracy of the FL task, referring to it as the data utility. Subsequently, we carry out comprehensive convergence analyses on the proposed FL methodology. Our objective is to jointly optimize the data utility of the digital twin-empowered FL task and the energy costs incurred by the long-term DITEN maintenance, encompassing FL model training, data synchronization, and twin migration. To tackle the aforementioned challenge, we present an optimization-driven learning algorithm that effectively identifies optimized solutions for the formulated problem. Numerical results demonstrate that our proposed algorithm outperforms various baseline approaches.

Problem

• Optimize energy-efficient federated learning in digital twin edge networks.
• Address privacy and data allocation in digital twin tasks.
• Jointly improve data utility and reduce long-term maintenance energy costs.

Innovation

• Closed-form function predicts FL training accuracy.
• Optimization-driven algorithm for energy-efficient FL.
• Joint optimization of data utility and energy costs.