Measurement-Based Admission Control with Aggregate Traffic Envelopes
The goal of admission control is to support the quality-of-service demands of real-time applications via resource reservation. In this paper, we introduce a new approach to Measurement-Based Admission Control (MBAC) based on adaptive and measurement-based maximal rate envelopes of the aggregate traffic flow. We show that such traffic envelopes provide a robust and accurate characterization of the aggregate traffic, capturing its temporal correlation as well as the available statistical multiplexing gain. In estimating applications’ future performance, we introduce the notion of a schedulability confidence level which describes the uncertainty of the measurement—based “prediction” and reflects estimation errors and temporal variations in the measured envelope. We then apply principles from extreme value theory and devise techniques to estimate the packet loss probability for a buffered multiplexer. Our results are quite general and apply to heterogeneous and bursty traffic flows belonging to a broad class of underlying traffic distributions including Gaussian, log-normal, and Gamma.
KeywordsAutocorrelation Dition Kelly Rote
Unable to display preview. Download preview PDF.
- 1.E. Castillo.Extreme Value Theory in Engineering. Academic Press, 1988.Google Scholar
- 2.D. Clark, S. Shenker, L. Zhang. Supporting real-time applications in an integrated services packet network: Architecture and mechanism. In Proceedings of ACM SIGCOMM’92, pages 14–26, Baltimore, Maryland, August 1992.Google Scholar
- 6.S. Floyd. Comments on measurement—based admissions control for controlled-load services, July 1996. Lawrence Berkeley Laboratory Technical Report.Google Scholar
- 8.M. Garret, W. Willinger. Analysis, modeling and generation of self-similar VBR video traffic. In Proceedings of ACM SIGCOMM’94, pages 269–280, London, UK, August 1994.Google Scholar
- 13.A. Lazar, G. Pacifici. Control of resources in broadband networks with quality of service guarantees. IEEE Communications, pages 66–73, October 1991.Google Scholar
- 15.J. Qiu. Measurement-Based Admission Control in Integrated Services Networks. M.S. Thesis, Rice University, May 1998.Google Scholar
- 16.O. Rose. Statistical properties of MPEG video traffic and their impact on traffic modeling in ATM systems. In Proceedings of IEEE Conference on Local Computer Networks, pages 397–406, Minneapolis, MN, October 1995.Google Scholar
- 17.D. Tse, M. Grossglauser. Measurement-based call admission control: Analysis and simulation. In Proceedings of IEEE INFOCOM ’97, Kobe, Japan, April 1997.Google Scholar