This article considers Gaussian flows which are fed into a GPS (Generalized Processor Sharing) scheduler. The system is analyzed using a most probable path approach. This method gives quite good approximations for performance measures, like queue length distributions in the full range of queue levels. The approximations are based on the distinction whether it is more probable that an aggregated queue consists of traffic from one class only or whether it is a combination of several classes. The approximate queue length distribution for a specific flow is then calculated either using the Empty Buffer Approximation or the authors' Rough Full Link Approximation, respectively.
|Title of host publication||21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002|
|Subtitle of host publication||New York, USA, 23-27 June 2002|
|Publisher||IEEE Institute of Electrical and Electronic Engineers|
|Publication status||Published - 2002|
|MoE publication type||A4 Article in a conference publication|
|Series||Proceedings - IEEE INFOCOM|
Mannersalo, P., & Norros, I. (2002). GPS schedulers and gaussian traffic. In 21st Annual Joint Conference of the IEEE Computer and Communications Societies, IEEE INFOCOM 2002: New York, USA, 23-27 June 2002 (pp. 1660-1667). IEEE Institute of Electrical and Electronic Engineers. Proceedings - IEEE INFOCOM, Vol.. 21 https://doi.org/10.1109/INFCOM.2002.1019419