Journal on Communications ›› 2016, Vol. 37 ›› Issue (4): 128-138.doi: 10.11959/j.issn.1000-436x.2016080

• academic paper • Previous Articles     Next Articles

Traffic matrix-based load balancing routing in flow-based smart identifier network

ARu JI1,Shuai GAO1,Hong-bin LUO1,Hong-ke ZHANG1,Ming WAN2   

  1. 1 National Engineering Laboratory for Next Generatio nternet Interconnection Devices, School of Electronic and Information Engineering,Beijing Jiaotong University,Beijing 100044,China
    2 Laboratory of Networked Control System,Shenyang Institute of Automation Chinese Academy of Sciences,Shenyang 110016,China
  • Online:2016-04-25 Published:2016-04-26
  • Supported by:
    The National Basic Research Program of China (973 Program);The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National High Technology Research and Develop-ment Program of China (863 Program)

Abstract:

Smart identifier network (SINET)has an advantage of being aware of the accurate traffic matrix. Traffic ma-trix was use as the constraint, model on load balancing routing problem, and transform the primal problem into dual problem by using Lagrange function. Therefore,the optimization goal of the dual problem can be easily achieved. In or-der to achieve the dual problem optimization goal,a traffic matrix based load balancing routing algorithm (TM-LB)was proposed. By performing the TM-LB,the control plane can plan paths for subsequent traffic according to network fluctu-ation. OMNET++ was used to run the experiment simulation based on NSFnet topology. The results show that TM-LB can better reduce congestion and realize load balancing, compared with traditional routing mechanism. Finally, a proof-of-concept was built implementation and carry out experiments for testing the overhead of TM-LB algorithm.

Key words: smart identifier network, traffic matrix, routing optimization, Lagrange duality,, load balance

No Suggested Reading articles found!