Energy-Aware Service Function Placement for Service Function Chaining in Data Centers

摘要

Nowadays, data centers deploy a large number of servers and network devices to provide various service functions (e.g. firewalls, deep packet inspection, content caches, WAN optimizers, etc.) and sufficient network connection. Most traffic in data centers is subject to treatment by multiple service functions (SFs) which form an ordered service function chain (SFC). In this paper, we study the energy-aware service function placement problem for SFC in data centers. By considering the computing, bandwidth resources constrains and the power models both in servers and switches, a new service function placement algorithm Merge-RD is proposed to save the energy consumption in data centers. The simulation results indicate that the Merge-RD can effectively reduce the energy consumption and average transmission delay in data center compared with some existing service function placement algorithms while guaranteeing the packet delivery ratio at a high level.