Conference proceeding
Trend based bandwidth provisioning - An online approach for Traffic Engineered tunnels
2008 NEXT GENERATION INTERNET NETWORKS AND 4TH EURONGI CONFERENCE ON NEXT GENERATION INTERNET NETWORKS, PROCEEDINGS
01 Jan 2008
Abstract
In this paper, a novel dynamic bandwidth provisioning scheme for Traffic Engineered tunnels is proposed. The mechanism uses information from the traffic trend to make resizing decisions and is designed to lower signaling and computational overhead while meeting QoS constraints. The traffic trend is observed using a Slope Estimator and a Memory Moderator unit. The Slope Estimator periodically analyzes traffic for growth and spikes whereas the Memory Moderator keeps track of traffic history and uses it to influence the update in reservation. Key metrics are identified and detailed analysis is then undertaken to gauge the performance of this approach. Accurate simulations on realistic traffic profiles and topologies show effective resizing and reduction in signaling overhead. A comparison with similar state-of-the-art mechanisms is also discussed.
Metrics
9 Record Views
5 citations in Scopus
Details
- Title
- Trend based bandwidth provisioning - An online approach for Traffic Engineered tunnels
- Creators
- Sukrit Dasgupta - Drexel UniversityJaudelice C. de Oliveira - Drexel UniversityJ. -P. Vasseur - Cisco Syst, Boxboro, MA USAIEEE
- Publication Details
- 2008 NEXT GENERATION INTERNET NETWORKS AND 4TH EURONGI CONFERENCE ON NEXT GENERATION INTERNET NETWORKS, PROCEEDINGS
- Conference
- 2008 NEXT GENERATION INTERNET NETWORKS AND 4TH EURONGI CONFERENCE ON NEXT GENERATION INTERNET NETWORKS
- Publisher
- IEEE
- Number of pages
- 2
- Grant note
- Cisco Systems 0435247 / National Science Foundation; National Science Foundation (NSF)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000259363500008
- Scopus ID
- 2-s2.0-51149111396
- Other Identifier
- 991019168885804721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Industry collaboration
- Domestic collaboration
- Web of Science research areas
- Computer Science, Interdisciplinary Applications
- Engineering, Electrical & Electronic
- Telecommunications