Home Problem Statement
Traffic engineering plays a critical role in determining the performance and reliability of a network. Among the major challenges to traffic engineering are the following three:
- How to cope with dynamic and unpredictable changes in traffic demand?
- How to efficiently implement the traffic engineered routing in current network architecture?
- How to provide integrated traffic engineering to best-effort traffic and traffic with QoS guarantee, particularly VPN traffic?
COPE: optimize for common cases and bound worst-case performance
COPE is a class of traffic engineering algorithms that optimize for the expected scenarios while providing a worst-case guarantee for unexpected scenarios. Using extensive evaluations based on real topologies and traffic traces, we show that COPE can achieve efficient resource utilization and avoid network congestion in a wide variety of scenarios.
An extension to COPE
Zheng et al. utilize support from Multiprotocol label switching (MPLS). We propose an efficient algorithm to achieve MPLS-based, optimal and robust traffic engineering. We also propose a novel and efficient algorithm to select effective MPLS paths. Furthermore, we extend our framework to conduct integrated VPN provisioning and traffic engineering. Using real network topologies and traffic traces, we demonstrate the effectiveness of our algorithms.
Paper Toys
- COPE: Traffic Engineering in Dynamic Networks.
Hao Wang, Haiyong Xie, Lili Qiu, Yang Richard Yang, Yin Zhang, and Albert Greenberg.
In Proceedings of ACM SIGCOMM, Pisa, Italy, September 2006. (PDF)
Related Toys (NOT by me!)
- Traffic Engineering in MPLS and VPN Networks.
Zheng Ma, Hao Wang, Yang Richard Yang, Arvind Krishnamurthy, and Avi Silberschatz.
Yale Computer Science Technical Report YALEU/DCS/TR-1366, August 2006.