SOSP '01 Proceedings of the eighteenth ACM symposium on Operating systems principles
On selfish routing in internet-like environments
Proceedings of the 2003 conference on Applications, technologies, architectures, and protocols for computer communications
Coping with network failures: routing strategies for optimal demand oblivious restoration
Proceedings of the joint international conference on Measurement and modeling of computer systems
Walking the tightrope: responsive yet stable traffic engineering
Proceedings of the 2005 conference on Applications, technologies, architectures, and protocols for computer communications
Optimal Routing with Multiple Traffic Matrices Tradeoff between Average andWorst Case Performance
ICNP '05 Proceedings of the 13TH IEEE International Conference on Network Protocols
COPE: traffic engineering in dynamic networks
Proceedings of the 2006 conference on Applications, technologies, architectures, and protocols for computer communications
RouterFarm: towards a dynamic, manageable network edge
Proceedings of the 2006 SIGCOMM workshop on Internet network management
Negotiation-based routing between neighboring ISPs
NSDI'05 Proceedings of the 2nd conference on Symposium on Networked Systems Design & Implementation - Volume 2
TIE breaking: tunable interdomain egress selection
IEEE/ACM Transactions on Networking (TON)
GATEway: symbiotic inter-domain traffic engineering
Proceedings of the 3rd International Conference on Performance Evaluation Methodologies and Tools
Seamless BGP migration with router grafting
NSDI'10 Proceedings of the 7th USENIX conference on Networked systems design and implementation
Hi-index | 0.00 |
Traditional traffic engineering adapts the routing of traffic within the network to maximize performance. We propose a new approach that also adaptively changes where traffic enters and leaves the network---changing the "traffic matrix", and not just the intradomain routing configuration. Our approach does not affect traffic patterns and BGP routes seen in neighboring networks, unlike conventional inter-domain traffic engineering where changes in BGP policies shift traffic and routes from one edge link to another. Instead, we capitalize on recent innovations in edge-link migration that enable seamless rehoming of an edge link to a different internal router in an ISP backbone network---completely transparent to the router in the neighboring domain. We present an optimization framework for traffic engineering with migration and develop algorithms that determine which edge links should migrate, where they should go, and how often they should move. Our experiments with Internet2 traffic and topology data show that edge-link migration allows the network to carry 18.8% more traffic (at the same level of performance) over optimizing routing alone.