Digital Twin-Empowered Network Planning for Multi-Tier Computing

In this paper, we design a resource management scheme to support stateful applications, which will be prevalent in sixth generation (6G) networks. Different from stateless applications require context data while executing computing tasks user terminals (UTs). Using multi-tier paradigm with servers deployed at the core network, gateways, and base stations aim optimize long-term reservation by jointly minimizing usage of computing, storage, communication resources cost reconfiguring reservation. The coupling among different impact UT mobility create challenges management. To address challenges, develop digital twin (DT) empowered network planning two elements, i.e., multi-resource reconfiguration. First, DTs are designed for collecting status data, based on UTs grouped according their patterns. Second, an algorithm is proposed customize groups satisfy demands. Last, Meta-learning-based approach developed reconfigure balancing reconfiguration cost. Simulation results demonstrate that DT-empowered outperforms benchmark frameworks using less incurring lower costs.