Predicting response times in processor-sharing queues

Ward, Amy R.; Whitt, Ward

doi:10.1090/fic/028/01

Cited by 14 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the random variables of virtual delays we consider here deal with summations of independent random variables, the Normal approximation should work well, see Whitt [29] and Ward and Whitt [26]. This claim is supported by theoretical results based on the Law of Large Numbers and the Central Limit Theorem.…”

Section: Normal Approximation Of Virtual Delaysmentioning

confidence: 73%

Queueing models for full-flexible multi-class call centers with real-time anticipated delays

Jouini

Dallery

Akşin

2009

International Journal of Production Economics

View full text Add to dashboard Cite

In this paper, we consider two basic multi-class call center models, with and without reneging. Customer classes have different priorities. The content of different types of calls is assumed to be similar allowing their service times to be identical. We study the problem of announcing delays to customers upon their arrival. For the simplest model without reneging, we give a method to estimate virtual delays that is used within the announcement step. For the second model, we first build the call center model incorporating reneging. The model takes into account the change in customer behavior that may occur when delay information is communicated to them. In particular, it is assumed that customer reneging is replaced by balking that depends on the state of the system in this case. We develop a method based on Markov chains in order to estimate virtual delays of new arrivals for this model. Finally, some practical issues concerning delay announcement are discussed.

show abstract

Section: Normal Approximation Of Virtual Delaysmentioning

confidence: 73%

Queueing models for full-flexible multi-class call centers with real-time anticipated delays

Jouini

Dallery

Akşin

2009

International Journal of Production Economics

View full text Add to dashboard Cite

show abstract

“…Once the packet dispersion is activated, round robin scheduling of involved queues (high priority that activated it and ultra-high priority queues containing shifted packets) is performed. We are modelling round robin scheduling as M/G/1/C, which is serviced using processor sharing (PS) discipline [11]. Probability mass function of M/M/1/C and M/G/1/C/PS is the same.…”

Section: Performance Analysismentioning

confidence: 99%

A Novel Scheme for Dynamic Triggering Of Packet Dispersion

Ninkovic

Bojovic

Gajin

2014

ElAEE

View full text Add to dashboard Cite

Packet burst losses are proven to be detrimental to multimedia applications. Most of the burst losses in the Internet are the result of tail drop discipline, which drops packets when queues in routers are filled to their maximum capacity. A potential way of addressing the burst losses is to use packet dispersion over multiple and disjoint paths to destination. However, packet dispersion requires packet reordering and addressing the problems concerning packet latency and jitter. We are proposing a model that dynamically triggers packet dispersion depending on the high priority queue occupancy containing high priority traffic, whereas the need for packet dispersion and the number of dispersion paths is inferred from traffic load in other queues. Proposed mechanism reduces tail drops in queues containing high priority traffic by performing packet shifting to high priority queues that belong to other output interfaces designated for packet dispersion. It delivers significant benefits regarding packet loss and packet loss distance, which are considered imperative parameters for describing the quality of multimedia and real-time traffic.

show abstract

“…They demand response time that is predictable [20,23], which makes it important to calculate moments at least, and ideally response time distributions, which is not straightforward. In the past three decades, work has addressed response time in various ways using PS queues [19,21,22,24,36,46]. In the present work, we introduce a novel momentgenerating algorithm to calculate response times analytically.…”

Section: Introductionmentioning

confidence: 99%

Moment-Generating Algorithm for Response Time in Processor Sharing Queueing Systems

Chis

Harrison

2015

Computer Performance Engineering

View full text Add to dashboard Cite

Abstract. Response times are arguably the most representative and important metric for measuring the performance of modern computer systems. Further, service level agreements (SLAs), ranging from data centres to smartphone users, demand quick and, equally important, predictable response times. Hence, it is necessary to calculate moments, at least, and ideally response time distributions, which is not straightforward. A new moment-generating algorithm for calculating response times analytically is obtained, based on M/M/1 processor sharing (PS) queueing models. This algorithm is compared against existing work on response times in M/M/1-PS queues and extended to M/M/1 discriminatory PS queues. Two real-world case studies are evaluated.

show abstract

Predicting response times in processor-sharing queues

Cited by 14 publications

References 23 publications

Queueing models for full-flexible multi-class call centers with real-time anticipated delays

Queueing models for full-flexible multi-class call centers with real-time anticipated delays

A Novel Scheme for Dynamic Triggering Of Packet Dispersion

Moment-Generating Algorithm for Response Time in Processor Sharing Queueing Systems

Contact Info

Product

Resources

About