Robustness Aware SFC Placement in NFV-Enabled Multi-Domain Networks Under Resource Demand Uncertainty

The increasing service demands in 5G networks have led to the emergence of Network Function Virtualization (NFV) technology. Through the virtualization technique, NFV enables on-demand and flexible service provisioning and deployment by implementing networks functions in forms of software instances, called Virtual Network Functions (VNFs). With the rapid development and implementation of 5G, the Service Function Chain (SFC) placement problem in multi-domain network scenarios is gaining significant attentions due to the sudden and dynamic patterns of resource demands from a diversity of service requests. Most existing proposals attempt to optimize the SFC placement in multi-domain networks, under the assumption that resource demand required each service request is given in prior and keeps unchanged during the SFC execution period. However, it is impractical in real network scenarios due to the evolving dynamic changes of service requests. The uncertainty of service demands has an important effect on service reliability, service quality and network performance. To this end, in this paper, we study the problem of robust SFC placement in multi-domain networks under the assumption that resource demands of SFC requests are uncertain. We first formulated the problem of robust SFC placement in multi-domain networks as an integer programming model with the aim to minimize the SFC placement cost while considering the Quality of Service (QoS) guarantee. Then, we develop a three-stage heuristic placement algorithm to solve the problem. The extensive simulation results demonstrate that our proposed heuristic algorithm is efficient and can save more placement cost than comparison mechanisms.