Discriminatory processor sharing queues with stationary ergodic service times and the performance of TCP in overload |
| |
| Authors: | Eitan Altman Tania Jiménez Daniel Kofman |
| |
| Affiliation: | 1. INRIA, B.P. 93, 2004 Route des Lucioles, 06902 Sophia-Antipolis Cedex, France;2. LIA, Avignon University, France;3. Network Department, TELECOM ParisTech, 46 rue Barrault, 75634 Paris Cedex, France;1. Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN, USA;2. College of Social Science, 203 Berkey Hall, Michigan State University, East Lansing, MI 48823, USA;3. Department of Telecommunications, Michigan State University, East Lansing, MI 48823, USA;4. International Livestock Research Institute, Nairobi, Kenya;5. Ministry of Livestock and Fisheries Development, P.O. 34188, Nairobi, Kenya;6. Ministry of Water Resources Management and Development, P.O. Box 49720, Nairobi, Kenya;7. GEF Project on Management of Indigenous Vegetation, P.O. Box 350, 00618 Ruaraka, Nairobi, Kenya;8. Physical Planning Department, Ministry of Lands and Settlement, Ardhi House RG13, Box 4025, Nairobi, Kenya;9. Planning Department, Ministry of Agriculture, Kilimo House, Cathedral Road, P.O. Box 30028, Nairobi, Kenya;10. Head of KWS EIA Programme, P.O. Box 40241, Nairobi, Kenya;11. Ministry of Regional Development, P.O. Box 10280-00100 GPO, Nairobi, Kenya;12. National Programme Manager, NEMA, Ministry of Environment, Natural Resources and Wildlife, P.O. Box 47146, Nairobi, Kenya;1. INESC Porto, Portugal Escola Superior de Tecnologia e Gestão de Felgueiras, Politécnico do Porto, Portugal;2. INESC Porto, Faculdade de Engenharia, Universidade do Porto, Portugal;1. Lebanese American University (LAU), Electrical and Computer Engineering, Byblos, Lebanon;2. University of Paris, 13 – L2TI Lab, 99, Avenue Jean-Baptiste Clement, 93430 Villetaneuse, France;3. North Carolina State University, Raleigh, NC 27695-7534, United States;1. TNO Information and Communication Technology, Department of Planning, Performance and Quality of Service, Delft, The Netherlands;2. Delft University of Technology, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft, The Netherlands;3. Center for Mathematics and Computer Science, Department of Probability and Stochastic Networks, Science Park 123, 1098XG Amsterdam, The Netherlands;4. VU University, Faculty of Exact Sciences, Department of Mathematics, Amsterdam, The Netherlands;1. Oklahoma State University, Stillwater, OK 74078, United States;2. IBM Watson Research Center, Yorktown Heights, NY 10598, United States;1. LAMOS, University of Bejaia;2. Econometrics, Vrije Universiteit Amsterdam |
| |
| Abstract: | In a recent paper, Bonald and Roberts (2001) [6] studied non-persistent TCP connections in transient overload conditions, under the assumption that all connections have the same round-trip times. In this paper our goal is to develop theoretical tools that will enable us to relax this assumption and obtain explicit expressions for the rate of growth of the number of connections at the system, the rate at which TCP connections leave the system, as well as the time needed for the completion of a connection. To that end, we model the system as a discriminatory processor sharing (DPS) system which we analyze under very mild assumptions on the probability distributions related to different classes of arrivals: we only assume that the arrival rates of connections exist, and that the amount of information transmitted during a connection of a given type forms a stationary ergodic sequence. We then proceed to obtain explicit expressions for the growth rate of the number of connections at the DPS system for several specific probability distributions. We check through simulations the applicability of our queueing results for modeling TCP connections sharing a bottleneck. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
