AI Empowered Modeling, Closed-Loop Optimization, and Field Trials of RAN Digital Twin
- 30 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (1) , 154-164
Abstract
As mobile networks evolve, we are witnessing a significant shift from traditional communication services to advanced network applications. This transformation calls for efficient and reliable Radio Access Network (RAN) operations. RAN Digital Twin (DT) is such an enabling technology. This paper delves into the AI-empowered RAN DT technology, analyzing the services that RAN DTs can provide to enhance the performance and operational efficiency of both current 5G networks and upcoming 6G networks. A comprehensive framework is proposed, which includes four subsystems: feature application, data repository, model repository, and RAN DT management. By integrating several key enabling technologies such as data management, AI-empowered RAN modeling techniques, multi-objective RAN performance optimization methods and RAN DT performance management which refers to the optimization of the RAN DT’s own model performance, the proposed RAN Digital Twin system can predict network conditions and fine-tune network configuration in a way that enhances network reliability and user satisfaction. To validate these improvements, practical tests are carried out within real mobile networks, focusing on the joint optimization of network energy efficiency and user data rates. The results demonstrate significant improvements in both network energy consumption and user data rates through RAN DT optimization. These findings underscore the potential of RAN Digital Twins in revolutionizing network operations and achieving high-level network automation.Keywords
This publication has 9 references indexed in Scilit:
- Wireless Network Digital Twin for 6G: Generative AI as a Key EnablerIEEE Wireless Communications, 2024
- Multiverse at the Edge: Interacting Real World and Digital Twins for Wireless BeamformingIEEE/ACM Transactions on Networking, 2024
- An Efficient Data-Driven Traffic Prediction Framework for Network Digital TwinIEEE Network, 2023
- Digital Twin-Based Cloud-Native Vehicular Networks Architecture for Intelligent DrivingIEEE Network, 2023
- Digital Twin for Intelligent Network: Data Lifecycle, Digital Replication, and AI-Based OptimizationsIEEE Communications Magazine, 2023
- Digital-Twin-Enabled 6G: Vision, Architectural Trends, and Future DirectionsIEEE Communications Magazine, 2022
- Data Driven Smart Load Balancing in Wireless Networks2020
- MOPSO: a proposal for multiple objective particle swarm optimization2002
- Multiobjective Evolutionary Algorithms: Analyzing the State-of-the-ArtEvolutionary Computation, 2000