Browsing by Author "Li, Kuan-Wei"

Now showing 1 - 2 of 2

NACHOS: Network-Aware CHains Orchestration Selection for NFV in SDN Datacenter
(2015)
Huang, Po-Han
;
Li, Kuan-Wei
;
Wen, Charles H. -P.
;
電機學院
;
College of Electrical and Computer Engineering
Network function virtualization (NFV) provides the flexibility for service providers to scale up their service systems and also enhances the possibility to satisfy user demand with limited resources by enabling network functions on commodity servers, as well as by allowing multiple identical network functions existing in the service networks. On the other hand, to accommodate various user demands, multiple service chains need to be applied in this network. However, due to the flow mingling problem in network service chaining, the system throughput can hardly be evaluated, and determining multiple service chains becomes a challenge. In this work, we identify two types of flow-mingling problems: intra-chains link contention and inter-chains link contention, and propose an algorithm named NACHOS to facilitate selection of multiple service chains. As a result, NACHOS can result in the optimality with maximum available bandwidth in a datacenter network, and can select service chains in polynomial time.
Reducing Network Cost of Minimal-Migration Based VM Management in Cloud Datacenters
(2016)
Li, Kuan-Wei
;
Huang, Po-Han
;
Wen, Charles H-P.
;
電機工程學系
;
Department of Electrical and Computer Engineering
Nowadays, Cloud Service Providers (CSPs) provide flexible architectures and reliable internet accessories in cloud datacenters, where different types of applications are hosted. In order to achieve higher resource utilization and better quality of service, virtualization is widely used and implemented with virtual machines (VMs). However, most studies focus on VM management for utilization and energy, not yet considering the cost for emerging internet applications. Therefore, to further reduce network cost, we propose utilization-and-network-driven (UND) and only-network-driven (OND) strategies on top of the common minimal-migration (MM) based VM management as UND-MM and OND-MM. According to simulation results, both UND-MM and OND-MM strategies effectively reduce network cost by averagely 7% and 37%, respectively, of the original MM while retaining comparable resource utilization in CPU and memory for normally-loaded and overloaded datacenters. Moreover, the OND-MM, which is simpler, outperforms the UND-MM, and thus becomes more preferable for VM management in cloud datacenters.