The maximum concurrent flow problem
Journal of the ACM (JACM)
Wide area traffic: the failure of Poisson modeling
IEEE/ACM Transactions on Networking (TON)
Internet Web servers: workload characterization and performance implications
IEEE/ACM Transactions on Networking (TON)
Scheduling data transfers in a network and the set scheduling problem
STOC '99 Proceedings of the thirty-first annual ACM symposium on Theory of computing
Multicommodity max-flow min-cut theorems and their use in designing approximation algorithms
Journal of the ACM (JACM)
The impact of a heavy-tailed service-time distribution upon the M/GI/s waiting-time distribution
Queueing Systems: Theory and Applications
Routing Strategies for Fast Networks
IEEE Transactions on Computers
Traffic Dispersion Strategies for Multimedia Streaming
FTDCS '01 Proceedings of the 8th IEEE Workshop on Future Trends of Distributed Computing Systems
An online throughput-competitive algorithm for multicast routing and admission control
Journal of Algorithms
Source routing and scheduling in packet networks
Journal of the ACM (JACM)
Lambda scheduling algorithm for file transfers on high-speed optical circuits
CCGRID '04 Proceedings of the 2004 IEEE International Symposium on Cluster Computing and the Grid
Networks with Advance Reservations: Applications, Architecture, and Performance
Journal of Network and Systems Management
A dynamically adaptive hybrid algorithm for scheduling lightpaths in lambda-grids
CCGRID '05 Proceedings of the Fifth IEEE International Symposium on Cluster Computing and the Grid - Volume 01
Distributed algorithms for multicommodity flow problems via approximate steepest descent framework
SODA '07 Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms
Improving the bulk data transfer experience
International Journal of Internet Protocol Technology
Path switching and grading algorithms for advance channel reservation architectures
IEEE/ACM Transactions on Networking (TON)
Commentary: back to the future
IEEE Communications Magazine
QofIS'02/ICQT'02 Proceedings of the 3rd international conference on quality of future internet services and internet charging and QoS technologies 2nd international conference on From QoS provisioning to QoS charging
Ultrascience net: network testbed for large-scale science applications
IEEE Communications Magazine
On the capacity of optical networks: A framework for comparing different transport architectures
IEEE Journal on Selected Areas in Communications - Part Supplement
Competitive routing of virtual circuits in ATM networks
IEEE Journal on Selected Areas in Communications
A literature survey on traffic dispersion
IEEE Network: The Magazine of Global Internetworking
Hi-index | 0.00 |
In response to the high throughput needs of grid and cloud computing applications, several production networks have recently started to support advance reservation of dedicated circuits. An important open problem within this context is to devise advance reservation algorithms that can provide provable throughput performance guarantees independently of the specific network topology and arrival pattern of reservation requests. In this paper, we first show that the throughput performance of greedy approaches, which return the earliest possible completion time for each incoming request, can be arbitrarily worse than optimal. Next, we introduce two new online, polynomial-time algorithms for advance reservation, called BatchAll and BatchLim. Both algorithms are shown to be throughput-optimal through the derivation of delay bounds for 1 + ε bandwidth augmented networks. The BatchLim algorithm has the advantage of returning the completion time of a connection immediately as a request is placed, but at the expense of looser delay performance than Batch All. We then propose a simple approach that limits path dispersion, i.e., the number of parallel paths used by the algorithms, while provably bounding the maximum reduction factor in the transmission throughput. We prove that the number of paths needed to approximate any flow is quite small and never exceeds the total number of edges in the network. Through simulation for various topologies and traffic parameters, we show that the proposed algorithms achieve reasonable delay performance, even at request arrival rates close to capacity bounds, and that three to five parallel paths are sufficient to achieve near-optimal performance.