Engset multi-rate state-dependent loss models with QoS guarantee

Abstract

SUMMARYWe consider a single link loss system of quasi-random input, described by the Engset multirate loss model (EnMLM). Blocked calls may once reattempt to be connected to the system requiring less bandwidth; then the system is described by the single retry model for finite sources (f-SRM). The EnMLM and the f-SRM are extended with the single threshold finite source model (f-STM), where calls may attempt to be connected to the system with less bandwidth requirements, according to the link occupancy, before blocking occurs. We focus on CBP equalization in the EnMLM, f-SRM and f-STM, under the bandwidth reservation (BR) policy. For this analysis, we apply two approximate methods, the Roberts' method and the method of reverse transition rates (RTR), which lead to a recursive CBP calculation. We evaluate the accuracy of the above models under the BR policy by comparing the analytical with simulation CBP results, based on the relative approximation errors (RAE). The results are highly satisfactory because they show that the proposed models (formulas) lead to small RAE.

Steady state analysis of the M/G/1//N queue with orbit of blocked customers

“…To the best of our knowledge, most of the studies on finite queues with losses consider Engset models and are mainly concerned with formulas for the blocking probability in the multi-server queues with exponential service times (Dahmouni et al 2005;Moscholios and Logothetis 2006;Overby 2005;Zukerman et al 2004). In these models it is assumed that the customers are ready to produce new calls immediately after the failures.…”

The extended connection‐dependent threshold model for call‐level performance analysis of multi‐rate loss systems under the bandwidth reservation policy

“…The accuracy of the new model is verified by simulation. Extensions of the CDTM for quasi-random traffic and the BR policy appear in [9,10]. Finally, we generalize the proposed model by incorporating service classes with either random or quasi-random arrivals.…”

“…Extensions of the CDTM for quasi-random traffic and the BR policy appear in [9,10]. In the retry models [6], a blocked call is allowed to retry one or more times, requesting for less bandwidth each time in order to be accepted for service.…”

“…The connection-dependent threshold model (CDTM) [8] generalizes the retry and threshold models by individualizing thresholds among service classes. Extensions of the CDTM for quasi-random traffic and the BR policy appear in [9,10]. Although we talk about elastic traffic in [6][7][8][9][10], in-service calls cannot alter their bandwidth.Another extension of the EMLM, which allows the modification of the bandwidth allocated to in-service calls, is presented in [11].…”

“…Extensions of the CDTM for quasi-random traffic and the BR policy appear in [9,10]. Although we talk about elastic traffic in [6][7][8][9][10], in-service calls cannot alter their bandwidth.…”