Abstract
By separating network functionalities from the dedicated hardware and implementing them in the form of Virtual Network Function (VNF), Network Function Virtualization (NFV) provides a new service paradigm called Service Function Chain (SFC). It is unrealistic to replace the running VNFs due to the stateful information accumulated, which makes the current VNF re-deployment or replacement approaches no longer effective enough. Such a situation is even worse when VNFs are shared. Instead of replacing VNFs, this paper proposes a VNF migration approach to maintain the network balance and performance by migrating VNFs from poor-state nodes to good-state nodes. In particular, two situations are considered, which are node-aware and link-aware VNF migrations respectively. Via migrating the VNFs that are related to the nodes or links causing Quality of Service (QoS) issues, the network and service performance can be optimized. In addition, the migration impact is also minimized by perceiving the global network states. The experimental results indicate that the service performance is improved and the load balance is achieved after the VNF migration.
Highlights
The traditional network is fulfilled by various kinds of middleboxes which are closely coupled with the dedicated hardware
NETWORK AND SERVICE DESCRIPTION In order to minimize the overall impact caused by Virtual Network Function (VNF) migration, we presents a redesigned model for service and network according to the unique VNF characteristics
1) NODE-AWARE VNF MIGRATION Aiming at the physical node overload situation, we propose a Node Aware VNF Migration Mechanism (NAVMM)
Summary
The traditional network is fulfilled by various kinds of middleboxes which are closely coupled with the dedicated hardware. Assuming that one VNF is already deployed on a physical node which gradually becomes over-loaded during this VNF’s lifecycle, if we still use the VNF deployment strategy to solve this situation, we will need to first remove it and initiate the same kind of VNF on the other physical nodes Such operation could average out the computational burden on nodes, it ignores the important stateful information accumulated at the beginning of the VNF deployment, which naturally leads to serious issues when the new VNF is running. When the number of network service request increases, the actual required resource of VNFs may exceed those offered by physical nodes In this condition, more packets would be backlogged in VNFs, which leads to many issues such as longer processing delay, link congestion, VNF crash, etc.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
