Browsing by Author "Liu, Gen-Hen"

Now showing 1 - 7 of 7

A Scalable Source Multipath Routing Architecture for Datacenter Networks
(2015)
Jia, Wen-Kang
;
Liu, Gen-Hen
;
Chen, Yaw-Chung
;
資訊工程學系
;
Department of Computer Science
The continuous growth in traffic volumes on modern Data Center Networks (DCNs) can be classified into either delay-or throughput-sensitive applications. In order to providing quality delivery to such applications, it is important that multipath routing and/or forwarding can be supported in the DCNs. However, some inherent problems of multipath forwarding have not been totally solved by existing solutions. Aiming to balance all these requirements for the multipath DCNs, we propose a novel solution-Code-Oriented eXplicit MultiPath (COXMP) scheme which evenly distributes traffic along multiple paths, resulting in better network throughput, delay, jitter, and resilience. The simulation results show that COXMP outperforms existing solutions and achieves a reasonable tradeoff between scalability and overhead.
(DENDIST)-E-2-FM: Flow Migration in Routing of OpenFlow-based Cloud Networks
(2013-01-01)
Lin, Wei-Chu
;
Liu, Gen-Hen
;
Kuo, Kuan-Tsen
;
Wen, Charles H. -P.
;
電機資訊學士班
A prior layer-2 routing algorithm-(DENDIST)-E-2 demonstrates advantages in throughput improvement, reroute period and failure recovery. Moreover, with the invention of software-defined networking (SDN), a revolutionary networking concept, dynamic routing protocols can embrace more flexible policy on per-flow basis. However, due to runtime complexity of dynamic routing, many issues on the practicality emerge and await to be resolved. Therefore, in this paper, we first apply (DENDIST)-E-2 to a SDN architecture and compare performances between dynamic-routing and flow-control mechanisms in a OpenFlow-based cloud network. Then, the flow-migration (FM) scheme, showing a better flow-control management, can be combined with (DENDIST)-E-2, and evolved into (DENDIST)-E-2-FM. At last, experimental results demonstrate that (DENDIST)-E-2-FM enables better feasibility in real-world applications, throughput improvement, sensitivity to reroute period and reduction in failure recovery time.
(DENDIST)-E-2: Dynamic and Disjoint ENDIST-based Layer-2 Routing Algorithm for Cloud Datacenters
(2012)
Liu, Gen-Hen
;
Wen, Charles H. -P
;
Wang, Li-Chun
;
電機資訊學士班
;
Undergraduate Honors Program of Electrical Engineering and Computer Science
This paper presents an improved layer-2 routing algorithm, called dynamic and disjoint edge node divided spanning tree ((DENDIST)-E-2), to overcome the issues of the single path route and unbalanced link utilization in cloud datacenters. (DENDIST)-E-2 consists of two key schemes: (1) disjoint ENDIST routing and (2) reroute by dynamic reweights. The former scheme can provide multi-path routes, thereby reducing traffic congestion. The latter scheme can balance the traffic load and improve the link utilization. Our experimental results show that the proposed scheme can enhance system throughput by 25% subject to the constraint of very short failure recovery time compared to the existing ENDIST scheme.
NAT-Aware Peer Grouping and Chunk Scheduling for Mesh-Pull P2P Live Streaming Systems
(2015)
Jia, Wen-Kang
;
Liu, Gen-Hen
;
Chen, Yaw-Chung
;
資訊工程學系
;
Department of Computer Science
Live streaming (a.k.a. Internet Protocol Television (IPTV)) services have been popularly deployed on the Internet. Traditionally, IPTV service provider adopted client-server architecture. However, when the client population grows up to a certain amount, it usually faces the scalability and cost-effective problems. Fortunately, the development of Peer to Peer (P2P) content sharing application has proved that the P2P paradigm is an efficient solution to deliver many kinds of content over the Internet. P2P IPTV services may face the problem that there are more and more Network Address Translator (NAT) users, and peers behind NAT (NATed peer) cannot directly deliver its streaming data to other NATed peers. This situation easily leads to the so-called free rider problem. In this paper, we propose a grouping and scheduling scheme to increase the share rate of NATed peers. By restricting transmission connectivity of those peers with public IP address and properly arrange data chunks delivery, we could allow NATed peer to contribute more data on the overlay network. Simulation results show that proposed scheme can improve the performance in terms of the share rate and video playback quality compared to original NAT traversal mechanism. Besides, the deployment complexity of both P2P IPTV operators and peers, are expected reduction.
Performance Evaluation of IEEE 802.1Qbu: Experimental and Simulation Results
(2013-01-01)
Jia, Wen-Kang
;
Liu, Gen-Hen
;
Chen, Yaw-Chung
;
資訊工程學系
;
Department of Computer Science
In this paper, we apply IEEE 802.1Qbu Preemptive Priority Frame Forwarding mechanism to the IEEE 802.3z Gigabit Ethernet networks, and compare its performance with non-frame-preemption queuing schemes for various traffic patterns. A feasible implementation of the proposed solutions is addressed. The FPF effectively reduces the forwarding delay as well as jitter, so as to enhance response time of real-time services in GbE networks. Through simulations, we show that the FPF achieves superior and precise QoS control compared to existing non-preemptive-based priority scheduling schemes.
Scalable Explicit Multicasting on Internet: A Topological-Aware Approach
(2015-01-01)
Jia, Wen-Kang
;
Liu, Gen-Hen
;
Chen, Yaw-Chung
;
資訊工程學系
;
Department of Computer Science
eXplicit multicasting (Xcast) is a protocol to send data to multiple receivers in an efficient way. Compared with traditional stateful multicast, Xcast is based on a stateless approach that scales better in number of groups. Unfortunately, original Xcast brings up new challenges such as scalability of group size and efficiency issue. Therefore, Multiple Xcast (MXcast) and Generalized Xcast (GXcast) were proposed to retard the limitation of the group size by reconstructing the multicast group into multiple subgroups, and transferring multiple Xcast packets to different subgroups respectively. In this paper, we propose various subgrouping schemes and evaluate their performance based on hybrid simulation experiments. The results show that it can save up to 36.7% bandwidth consumption from Xcast to our proposed OGXcast in VoIP. The results reflect that the proposed scheme can improve the scalability of group size, achieve minimal packet delivery latency, reduce network bandwidth consumption, and reduce the loading of the source while compared with unicast and original Xcast, MXcast, and GXcast.
Topology-Aware Optimal Subgrouping and Subscheduling for Generalized Explicit Multicasting on Internet
(2017-12-01)
Jia, Wen-Kang
;
Liu, Gen-Hen
;
Chen, Yaw-Chung
;
資訊工程學系
;
Department of Computer Science
eXplicit multicasting (Xcast) is a protocol to send data to multiple receivers in an efficient way. Compared with traditional stateful multicast, Xcast is based on a stateless approach that scales better in number of groups. Unfortunately, the original Xcast brings up new challenges such as the scalability of group size and efficiency issue. Therefore, Multiple Xcast (MXcast) and Generalized Xcast (GXcast) were proposed to retard the limitation of the group size by reconstructing the multicast group into multiple subgroups and transferring multiple Xcast packets to different subgroups, respectively. In this paper, we propose various subgrouping schemes and evaluate their performance based on hybrid simulation experiments. The results show that it can save up to 36.7% bandwidth consumption from Xcast to our proposed Optimal GXcast in Voice over Internet Protocol (VoIP). The results reflect that the proposed scheme can improve the scalability of group size, achieve minimal packet delivery latency, reduce both network bandwidth consumption and source loading compared with the unicast and original Xcast, MXcast, and GXcast.