Deadline-aware Service Function Orchestration under Demand Uncertainty
Date
2020-01-17
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In network function virtualization (NFV), a service function chain (SFC) specifies a sequence of virtual network functions (VNFs) that user traffic has to traverse to realize a network service. A service can either be delivered by VNFs co-located within a single network infrastructure or geo-distributed over multiple distant cloud infrastructures. In either scenario, as the network resources are shared among multiple SFCs, optimal allocation of network resources to ensure the required quality of service while minimizing the deployment cost is a key challenge. This problem is commonly referred to as the SFC orchestration problem, which has been studied extensively in various settings. However, most existing works assume deterministic demands and resort to costly runtime resource reprovisioning to deal with dynamic demands. In this work, we formulate the co-located and geo-distributed SFC orchestration with demand uncertainty as robust optimization problems and develop exact and approximate algorithms to solve them. To avoid continuous resource reprovisioning, our algorithms utilize uncertain demand knowledge to compute proactive service orchestration solutions that can cope with fluctuations in dynamic service demands. The uncertain demand is modeled as a constrained uncertainty set whose cardinality can be adjusted to control the algorithm proactivity against demand fluctuations. We present extensive model-driven simulation results to study the behavior of the proposed algorithms in small and large scale problem instances and demonstrate their ability to achieve any desired proactivity-cost trade-off. We also evaluate the performance of our algorithms against other state-of-the-art algorithms in the literature. Mininet experiments are further conducted to validate the modeling of different components in our system model.
Description
Keywords
Citation
Nguyen, Q. M. (2020). Deadline-aware Service Function Orchestration under Demand Uncertainty (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.