Models and algorithms for centralized control planes to optimize control traffic overhead

被引:13
作者
Bhamare, Deval [1 ]
Krishnamoorthy, Mohan [1 ,3 ]
Gumaste, Ashwin [2 ]
机构
[1] Indian Inst Technol, IITB Monash Res Acad, Mumbai 400076, Maharashtra, India
[2] Indian Inst Technol, Dept Comp Sci & Engn, Mumbai 400076, Maharashtra, India
[3] Monash Univ, Dept Mech & Aerosp Engn, Clayton, Vic 3800, Australia
关键词
Carrier Ethernet; Centralized control plane; Network Management System; Controller placement; Omnipresent Ethernet; SOFTWARE-DEFINED NETWORKING;
D O I
10.1016/j.comcom.2015.06.022
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Carrier Ethernet has rapidly advanced to become an important technology in metro transport. However, the overlapping of control plane and data plane in contemporary Carrier Ethernet (CE) networks leads to complex and unmanageable networks. CE networks that use packet technologies ought to be more manageable, scalable and robust. Recently proposed network architecture, Omnipresent Ethernet (OE) recommends that the control and management plane in CE networks be decoupled from the forwarding and routing plane to overcome the problem mentioned earlier. In view of this, we investigate the possibility of a centralized control plane from OE perspective. A centralized control plane is a networking paradigm that abstracts and centralizes the control information of the network from the underlying distributed data-forwarding infrastructure. In this paper, we have focused on engineering and architectural issues related to the design of a centralized control plane for the networks built on OE Networking paradigm. Furthermore, the problem of control traffic overhead in managed networks is analyzed using an appropriate simulation model. A scheme to divide the network into smaller sub-networks is proposed so that the total control traffic is always below some threshold. An Integer Linear Program (ILP) for the controllers' placement in the partitioned network is presented. The ILP attempts to minimize the total control traffic, the total controllers' implementation cost and the overall response time in the network. Since the ILP solves the problem optimally for networks with a limited number of nodes, a heuristic approach is developed and presented for larger and real-time service-provider networks. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码:68 / 78
页数:11
相关论文
共 31 条
[1]  
[Anonymous], Q1211 ITUT
[2]  
[Anonymous], 2008, ITUTY1731
[3]  
[Anonymous], ACM SIGCOMM
[4]  
Berger L., 2003, 3471 RFC, V3471
[5]  
Bhamare D., 2015, IEEE INT C CLOUD ENG
[6]  
Bhamare D., 2011, P IEEE INT C COMM IC, P1
[7]  
Blendin Jeremias, 2014, 2014 Third European Workshop on Software Defined Networks (EWSDN), P109, DOI 10.1109/EWSDN.2014.14
[8]  
Chiu A. L., 2003, Optical Networks Magazine, V4, P26
[9]  
Curtis A.R., 2011, P ACM SIGCOMM 2011 C
[10]   Solution algorithms for the capacitated single allocation hub location problem [J].
Ernst, AT ;
Krishnamoorthy, M .
ANNALS OF OPERATIONS RESEARCH, 1999, 86 (0) :141-159