Resource Optimization in Distributed Real-Time Multimedia Applications

R. Yang, R.D. van der Mei, D. Roubos, F.J. Seinstra, H.E. Bal

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

The research area of multimedia content analysis (MMCA) considers all aspects of the automated extraction of knowledge from multimedia archives and data streams. To adhere to strict time constraints, large-scalemultimedia applications typically are being executed on distributed systems consisting of large collections of compute clusters. In a distributed scenario, it is first essential to determine the optimal number of compute nodes used by each cluster, properly balancing the complex tradeoff between computation and communication. This issue is referred as the "resource utilization" (RU) problem. Next, it is important to tune the transmission of newly generated data sent to each cluster, so as to obtain the highest service utilization, while minimizing the need for buffering. This latter issue is referred as the problem of "just-in-time" (JIT) communication. In this paper, we first present a simple and easy-to-implement method for the RU problem, which is based on the classical binary search method. Second, we address the JIT problem by introducing a smart adaptive control method that properly reacts to the continuously changing circumstances in distributed systems. Extensive experimental validation of the two approaches on a real distributed system shows that our optimization approaches are indeed highly effective. © The Author(s) 2011.
Original languageEnglish
Pages (from-to)941-971
JournalMultimedia Tools and Applications
Volume59
Issue number3
DOIs
Publication statusPublished - 2012

Fingerprint

Communication

Cite this

@article{96f0ea8f2d124b3ab1b648b5b413fed3,
title = "Resource Optimization in Distributed Real-Time Multimedia Applications",
abstract = "The research area of multimedia content analysis (MMCA) considers all aspects of the automated extraction of knowledge from multimedia archives and data streams. To adhere to strict time constraints, large-scalemultimedia applications typically are being executed on distributed systems consisting of large collections of compute clusters. In a distributed scenario, it is first essential to determine the optimal number of compute nodes used by each cluster, properly balancing the complex tradeoff between computation and communication. This issue is referred as the {"}resource utilization{"} (RU) problem. Next, it is important to tune the transmission of newly generated data sent to each cluster, so as to obtain the highest service utilization, while minimizing the need for buffering. This latter issue is referred as the problem of {"}just-in-time{"} (JIT) communication. In this paper, we first present a simple and easy-to-implement method for the RU problem, which is based on the classical binary search method. Second, we address the JIT problem by introducing a smart adaptive control method that properly reacts to the continuously changing circumstances in distributed systems. Extensive experimental validation of the two approaches on a real distributed system shows that our optimization approaches are indeed highly effective. {\circledC} The Author(s) 2011.",
author = "R. Yang and {van der Mei}, R.D. and D. Roubos and F.J. Seinstra and H.E. Bal",
year = "2012",
doi = "10.1007/s11042-011-0782-5",
language = "English",
volume = "59",
pages = "941--971",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "3",

}

Resource Optimization in Distributed Real-Time Multimedia Applications. / Yang, R.; van der Mei, R.D.; Roubos, D.; Seinstra, F.J.; Bal, H.E.

In: Multimedia Tools and Applications, Vol. 59, No. 3, 2012, p. 941-971.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Resource Optimization in Distributed Real-Time Multimedia Applications

AU - Yang, R.

AU - van der Mei, R.D.

AU - Roubos, D.

AU - Seinstra, F.J.

AU - Bal, H.E.

PY - 2012

Y1 - 2012

N2 - The research area of multimedia content analysis (MMCA) considers all aspects of the automated extraction of knowledge from multimedia archives and data streams. To adhere to strict time constraints, large-scalemultimedia applications typically are being executed on distributed systems consisting of large collections of compute clusters. In a distributed scenario, it is first essential to determine the optimal number of compute nodes used by each cluster, properly balancing the complex tradeoff between computation and communication. This issue is referred as the "resource utilization" (RU) problem. Next, it is important to tune the transmission of newly generated data sent to each cluster, so as to obtain the highest service utilization, while minimizing the need for buffering. This latter issue is referred as the problem of "just-in-time" (JIT) communication. In this paper, we first present a simple and easy-to-implement method for the RU problem, which is based on the classical binary search method. Second, we address the JIT problem by introducing a smart adaptive control method that properly reacts to the continuously changing circumstances in distributed systems. Extensive experimental validation of the two approaches on a real distributed system shows that our optimization approaches are indeed highly effective. © The Author(s) 2011.

AB - The research area of multimedia content analysis (MMCA) considers all aspects of the automated extraction of knowledge from multimedia archives and data streams. To adhere to strict time constraints, large-scalemultimedia applications typically are being executed on distributed systems consisting of large collections of compute clusters. In a distributed scenario, it is first essential to determine the optimal number of compute nodes used by each cluster, properly balancing the complex tradeoff between computation and communication. This issue is referred as the "resource utilization" (RU) problem. Next, it is important to tune the transmission of newly generated data sent to each cluster, so as to obtain the highest service utilization, while minimizing the need for buffering. This latter issue is referred as the problem of "just-in-time" (JIT) communication. In this paper, we first present a simple and easy-to-implement method for the RU problem, which is based on the classical binary search method. Second, we address the JIT problem by introducing a smart adaptive control method that properly reacts to the continuously changing circumstances in distributed systems. Extensive experimental validation of the two approaches on a real distributed system shows that our optimization approaches are indeed highly effective. © The Author(s) 2011.

U2 - 10.1007/s11042-011-0782-5

DO - 10.1007/s11042-011-0782-5

M3 - Article

VL - 59

SP - 941

EP - 971

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 3

ER -