Energy-efficient URLLC service provisioning in softwarization-based networks

Software defined networking (SDN) and network function virtualization (NFV) as new technologies have shown great potential in improving the flexibility of resource management for network service provisioning. As traffic dynamics may cause violation of rigid service requirements, especially for ultra-reliability and low-latency communication (URLLC) service, it is essential yet challenging to dynamically allocate an appropriate amount of resources (including computation, transmission, and energy) to network functions (NFs) in softwarization-based networks. Meanwhile, with the explosion of high resource-demanding applications, the energy efficiency of communication networks deserves significant attention. In this paper, we investigate the dynamic network function resource allocation (NFRA) problem with aim to minimize long-term energy consumption while guaranteeing the requirements of URLLC services in softwarization-based networks. To cater for efficient on-line NFRA decisions, we design a distributed dynamic NF resource allocation (DDRA) algorithm based on dynamic value iteration (DVI). The convergence of the DDRA algorithm is proved. We conduct simulation experiments based on real-world data traces for performance evaluation. The numerical results demonstrate that the proposed DDRA algorithm achieves around 25% and 20% energy consumption reduction when compared with two benchmark algorithms, respectively.