Grid Network Dimensioning by Modeling the Deadline Constrained Bulk Data Transfers

Munir, Kashif; Primet, Pascale Vicat-Blanc; Welzl, Michael

doi:10.1109/hpcc.2009.52

Cited by 7 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dimensioning determines required resources for given traffic load and is investigated in [17][18][19]. The previous dimensioning methods first obtain performance approximations, then make use of them in routing to optimize required resources.…”

Section: Related Workmentioning

confidence: 99%

“…Uses a transient solution of the Markov chain. [18] Investigates dimensioning of the link capacity for elastic traffic with a deadline. Uses M/M/1/N-RPS to model capacity sharing among multiple malleable requests, which can transfer with a variable rate.…”

Section: Resourcesmentioning

confidence: 99%

“…However, only wavelength provisioning without deadline and elastic bandwidth provisioning have been investigated. The processor-sharing queuing discipline is used to analyze link capacity [18] and TDM is equivalent with processor sharing. Our work investigates joint provisioning of node storage and lightpaths for large data transfer requests with respective deadlines.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Dimensioning of the Store-and-Transfer WDM Network With Limited Node Storage Under the Sliding Scheduled Traffic Model

Feng

Sun

Zhang

2017

J. Opt. Commun. Netw.

View full text Add to dashboard Cite

The so-called store-and-transfer WDM network (STWN) can store data in source storage and provision lightpaths at an optimal time when wavelengths are clear of conflicts. Consequently, blocking of requests can be reduced and resource utilization of the network can be improved. In this work, we investigate dimensioning of STWN and propose a two-step method to jointly determine the number of wavelengths and storage size required to satisfy the demand, which is given as a load matrix with a deadline, blocking rate, and wavelength utilization. The method models the STWN as a TDM network and first obtains the required storage size by maximizing the number of fixed time slots in each period, then calculates the required number of wavelengths with the number of time slots. Numerical results show the following: high load between far apart source and destination nodes has significant impact on the required wavelengths and storage. For instance, in a 24-node topology, 20% more wavelengths and storage may be required to satisfy a biased load matrix than a randomly generated one. When calculating the required number of wavelengths, our method outperforms traditional routing and wavelength assignment (RWA), because the TDM-based model supports fractional load. In the 24-node topology, 18% more wavelengths may be required by RWA than by our method. By installing a moderate amount of storage, wavelength utilization can be effectively improved. With number of wavelengths and storage size equaling 29 and 274, in the 24-node topology, utilization can reach 0.9. We also find wavelength is equivalent with storage regarding capacity of a STWN. For instance, with number of wavelengths and storage size equaling 114 and 131, in the 24-node topology, the blocking rate is the same as with number of wavelengths and storage size equaling 29 and 270.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Resourcesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Dimensioning of the Store-and-Transfer WDM Network With Limited Node Storage Under the Sliding Scheduled Traffic Model

Feng

Sun

Zhang

2017

J. Opt. Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…The early version of this work presented in 11 modeled the deadline‐constrained Grid bulk data transfers using an M/M/ 1/ N − RPS queue, considering only the average value of the minimum rate requirements of different requests. The queueing model M / M ( nc )/1/ k ( s )− RPS presented in Section 4.2 describes the system's characteristics better than the earlier model, as in this model requests are divided into different classes on the basis of their different minimum rate requirements.…”

Section: Introductionmentioning

confidence: 99%

Planning data transfers in grids: a multi‐service queueing approach

Munir

Cigno

Vicat-Blanc

et al. 2011

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

SUMMARYGrid applications move large amounts of data between distributed resources, and the efficiency of a Grid depends on their timely delivery within given bounds (deadlines). In most cases, the data volume and deadline are known in advance, allowing for both network planning and connection admission control (CAC). We formally define the problem and, based on this formalization, describe the operation of a feasible procedure for network reservations of deadline-constrained bulk data transfer requests. The procedure guarantees a minimum bandwidth to meet the deadlines and allows for opportunistic utilization of residual network capacity. We propose a novel analytical model based on the solution of an M/M(nc)/1/k(s)-R P S queue. The analytical model is validated against ns-2 simulations taking into account network level details (IP and TCP protocols), showing remarkably good coherence even under heavy loads. The model is orders of magnitude faster than simulation, which enables its application to plan the capacity of Grid networks, and to enforce CAC under the hypothesis of a dominating bottleneck on the transfer route.

show abstract

Combining explicit admission control and congestion control for predictable data transfers in grids

Munir

Welzl

Pasin

et al. 2012

Future Generation Computer Systems

View full text Add to dashboard Cite

Grid Network Dimensioning by Modeling the Deadline Constrained Bulk Data Transfers

Cited by 7 publications

References 32 publications

Dimensioning of the Store-and-Transfer WDM Network With Limited Node Storage Under the Sliding Scheduled Traffic Model

Dimensioning of the Store-and-Transfer WDM Network With Limited Node Storage Under the Sliding Scheduled Traffic Model

Planning data transfers in grids: a multi‐service queueing approach

Combining explicit admission control and congestion control for predictable data transfers in grids

Contact Info

Product

Resources

About