答辩公告
我的位置在: 首页 > 答辩公告 > 正文
THABO EMONG答辩公告
浏览次数:日期:2018-05-30编辑:研究生教务办1

答辩公告

论文题目

Multi-source   Routing in Software-Defined Networks

答辩人

THABO   SEMONG

指导教师

谢鲲

答辩委员会

主席

罗娟

学科专业

计算机科学与技术

学院

信息科学与工程学院

答辩地点

信科院基地317

答辩时间

201861

下午230


学位论文简介

1.    We firstly studied a novel delay-bounded multi-source multicast Software-Defined Network problem, in which among the set of potential sources, we select a source to build the multicast-tree, under the constraint that the transmission delay for every destination is bounded. We modeled the problem as a MILP and prove its NP-Hardness. To solve the problem, a delay bounded multi-source (DBMS) scheme was proposed, which includes a DBMS algorithm to build a minimum delay cost DBMS-Forest. The DBMS algorithm ensures that every destination node connect to one and only one source node. All potential source nodes are directly connected to the virtual source node that then act as a super source.


2.    We then proposed an efficient load balancing and multicasting scheme for uncertain-source Software-Defined Network, using current link cost monitoring. We considered load balance, bandwidth utilization, tree building and the process of uncertain-source selection. We named this scheme RTLMUS (Real-Time Link Monitoring Uncertain-Source). We then ensured that each destination node connect to just one potential source node. In the presented SDN controller architecture, all multicast routing calculations work off a single view of the network state maintained by the controller The controller learns the network state through a combination of LLDP polling (for topology discovery), and OpenFlow statistic polling (for traffic state discovery). This unified network view may still contain stale network state due to network delays, but routing calculations will always be performed using a consistent view of the network state, and no convergence delays are incurred by traffic state or topology changes.


3.    Lastly, we have presented Multi-Source Multicast Energy-Aware Routing (MSM-EAR) for Software-Defined Network. Prior works on classical energy-aware routing focused more on single-source multicast and assumed that the table of OpenFlow switch can hold an infinite number of rules. In practice, this assumption does not hold since the flow table is implemented with Ternary Content Addressable Memory (TCAM) which is expensive and power-hungry. To address this problem, we have proposed an optimization method to minimize energy consumption for a backbone network while at the same time respecting the capacity on network links and rule space constraints on routers. We also formulated the problem using Integer Linear Program (ILP) and introduced efficient greedy heuristic algorithm.



主要学术成果


[1] Semong, Thabo, Kun Xie, Xuhui Zhou, Hemant Kumar Singh, and Zhetao Li. "Delay Bounded Multi-source Multicast in Software-Defined Networking." Electronics 7, no. 1 (2018): 10. (SCIE Journal)

DOI: https://doi.org/10.3390/electronics7010010

[2] Semong, Thabo, and Kun Xie. "Efficient Load Balancing and Multicasting for Uncertain-Source SDN: Real-Time Link-Cost Monitoring." In Computer Science On-line Conference, pp. 178-187. Springer, Cham, 2018. (EI Conference)

DOI: https://doi.org/10.1007/978-3-319-91186-1_19

Semong, Thabo and Kun Xie. "Multi-Source Multicast with Energy-aware Routing for Software-Defined Networking."  (Under review)