Title :
Bandwidth allocation bounds for α-stable self-similar Internet traffic models
Author :
Karasaridis, Anestis ; Hatzinakos, Dimitrios
Author_Institution :
Dept. of Electr. & Comput. Eng., Toronto Univ., Ont., Canada
Abstract :
In this paper we investigate the implications of traffic with long-tails and long-range dependence (LRD) on bandwidth allocation for ATM networks with quality of service (QoS) performance guarantees. Analytic formulas for the overflow probability bounds of a constant service rate infinite buffer are used to provide bounds of the service rate for α-stable self-similar sources, for which the general theory of effective bandwidths does not apply. Our analytical results are verified with extended simulation studies with real and model generated traffic. The conditions under which the bounds become tight are identified
Keywords :
Internet; asynchronous transfer mode; bandwidth allocation; buffer storage; fractals; probability; quality of service; telecommunication traffic; α-stable self-similar Internet traffic models; α-stable self-similar sources; ATM networks; QoS performance guarantees; bandwidth allocation bounds; constant service rate infinite buffer; long-range dependence; overflow probability bounds; quality of service; service rate; Analytical models; Bandwidth; Broadband communication; Channel allocation; Internet; Probability density function; Tail; Telecommunication traffic; Traffic control; Upper bound;
Conference_Titel :
Higher-Order Statistics, 1999. Proceedings of the IEEE Signal Processing Workshop on
Conference_Location :
Caesarea
Print_ISBN :
0-7695-0140-0
DOI :
10.1109/HOST.1999.778728
