Efficiently Embedding Service Function Chains with Dynamic Virtual Network Function Placement in Geo-Distributed Cloud System

• Published in: IEEE transactions on parallel and distributed systems Vol. 30; no. 10; pp. 2179 - 2192
• Main Authors: Pei, Jianing, Hong, Peilin, Xue, Kaiping, Li, Defang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Bandwidth; Chains; Cloud computing; Costs; dynamic VNF placement; Embedded systems; Embedding; Heuristic algorithms; Integer programming; Internet service providers; Linear programming; Load modeling; Middleboxes; Optimization; Performance evaluation; Placement; Service function chain; Software-defined networking; Switches; virtual network function; Virtual networks
• ISSN: 1045-9219; 1558-2183
• DOI: 10.1109/TPDS.2018.2880992

Network Function Virtualization (NFV) and Software-Defined Networks (SDN) enable Internet Service Providers (ISPs) to place Virtual Network Functions (VNFs) to achieve the performance and security benefit without incurring high Operating Expenses (OPEX) and Capital Expenses (CAPEX). In NFV environment, Service Function Chains (SFCs) always need to steer the traffic through a series of VNF instances in predefined orders. Moreover, the required number and placement of VNF instances should be optimized to adapt to dynamic network load. Therefore, it is considerable for ISPs to conduct an optimal SFC embedding strategy to improve the network performance and revenue. In the paper, we study the SFC Embedding Problem (SFC-EP) with dynamic VNF placement in geo-distributed cloud system. We formulate this problem as a Binary Integer Programming (BIP) model aiming to embed SFC requests with the minimum embedding cost. Furthermore, the novel SFC eMbedding APproach (SFC-MAP) and VNF Dynamic Release Algorithm (VNF-DRA) have been proposed to efficiently embed SFC requests and optimize the number of placed VNF instances. Performance evaluation results show that the proposed algorithms can provide higher performance in terms of SFC request acceptance rate, network throughput, and mean VNF utilization rate and efficiently reduce the total VNF running time compared with the algorithms in existing literatures.