Resource optimization of optical aggregation network for efficient software-defined datacenters

Abstract

Software-defined datacenters (SDDCs) have recently received much attention for rapid delivery of cloud-based applications. In this paper, we consider the design of an optical aggregation network for cost-efficient software-defined datacenters (SDDCs). Here, an optical aggregation network connects a server accommodating virtual network functions (VNFs) with access gateway nodes (AGNs) via a time-division-multiplexing (TDM)-based point-to-multipoint (P2MP) wavelength path to aggregate traffic from geographically distributed end users to cloud datacenters. Each VNF must be placed on an adequate server in consideration of the efficiency of wavelength paths to reduce network cost for cloud access. However, existing VNF placement algorithms determine VNF placement without considering the efficiency of wavelength paths, which deteriorates network performance and increases network cost. To solve this problem, VNFs must be placed so that a P2MP wavelength path can be efficiently shared by multiple AGNs to reduce network cost. For this purpose, we propose a VNF placement algorithm, called the decomposition-based VNF placement algorithm (DVA), in a TDM-wavelength-division-multiplexing (WDM)-based optical aggregation network for cost-efficient SDDCs. DVA can find approximate solutions of sufficient quality within practical computation time.