Digital Network Twins (DNTs) are virtual representations of physical networks and offer promising solutions for managing complex network environments, especially when combined with machine learning. This talk discusses how DNTs address pressing challenges in advanced networks such as 6G, covering federated learning for privacy-preserving distributed model training, reinforcement learning for autonomous real-time decision-making, and practical applications including edge caching and secure vehicle networks.
Topics Covered
- Network digital twin architecture and synchronization
- Federated learning for decentralized model training in DNTs
- Reinforcement learning for closed-loop network control
- Security: defending against poisoning attacks in distributed twin systems
- Applications: edge caching optimization, secure vehicular networks