Information

Submission Deadline: June 20, 2026
Notification Date: TBA

Session Chair

Daniele Tarchi, University of Florence, Italy
Francesco Linsalata, Politecnico di Milano, Italy
Marco Martalò, University of Cagliari, Italy

Goals of the Session

The primary objective of this session is to explore the fundamental shift from centralized simulation models to distributed, real-time Digital Twins (DTs) that operate across the entire computing continuum. As Digital Twins evolve to represent increasingly complex, large-scale systems—such as smart cities, global supply chains, and autonomous fleets—the underlying network architecture must evolve from a passive transport layer to an active, "intelligence-aware" infrastructure.
We aim to bridge the gap between telecommunications and distributed simulation by examining how the network acts as both an enabler and an object of Digital Twin technology. This includes investigating how SAGIN and Distributed AI provide the necessary reach and intelligence for global-scale twins, as well as how Digital Twins for Networking (DT4NW) can be utilized to model, predict, and optimize the behavior of the continuum itself. By bringing together these perspectives, the session will highlight cutting-edge strategies for managing the lifecycle, connectivity, and intelligence of DTs in pervasive and real-time environments.
Furthermore, the session will explore the role of Digital Twins in advanced signal processing, where high-fidelity modeling of physical-layer phenomena, spectrum dynamics, and electromagnetic propagation enables predictive optimization and adaptive control of communication systems. High-resolution Digital Twins integrating physical signal propagation, sensing data streams, and distributed learning will be examined as key enablers for ultra-reliable and mission-critical applications.

Topics of interest include, but are not limited to:

• Architectures and frameworks for the Edge-to-Cloud-Continuum in large-scale DT deployments.
• Digital Twins for Networking (DT4NW): Modeling and optimizing network performance, reliability, and security.
• SAGIN (Space-Air-Ground Integrated Networks) for global and remote Digital Twin connectivity
• Distributed AI and Federated Learning for intelligent DT modeling and predictive analytics.
• Real-time state synchronization and ultra-low latency protocols for high-fidelity DTs.
• Intelligence at the edge for real-time data processing and autonomous decision-making in DTs.
• Dynamic resource orchestration and task offloading across the computing continuum for DT workloads.
• Network Slicing and QoS/QoE provisioning for mission-critical Digital Twin applications.
• Security, privacy-preserving techniques, and trust management in distributed DT ecosystems.
• Interoperability standards and communication protocols for multi-domain Digital Twins.
• Digital-Twin-as-a-Service (DTaaS) and cloud-native simulation architectures.
• Predictive "What-if" analysis and real-time optimization of cyber-physical systems via DTs.
• AI-native network management and self-healing continua driven by Digital Twin insights.
• AI-native network and physical layers design through Digital Twin feedback loops.
• Network astraction within Digital Twin ecosystems.
• Integrated sensing, communication, and computation (ISCC) modeling via DTs.
• Proof-Of-Concept and DT prototyping for innovative vertical applications.