Experiences with adaptive QOS mapping scheme

Tatsuo Nakajima, Hiroshi Fujita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In multimedia computing, guaranteeing Quality of Service(QOS) is one of the most important topics. If QOS values specified by users are not ensured, the users may not put up with the degraded quality of media streams. However, operating systems cannot understand QOS values specified by users directly, then the QOS values should be mapped to the CPU capacity that is required for guaranteeing the QOS values. There are two approaches for realizing the mapping. In the first approach called static mapping, the mapping is calculated before applications are started. In the second approach called dynamic mapping, the mapping is calculated at run-time. The system monitors the actual CPU utilization of continuous media applications, and adjusts their reserved CPU resources at run-time. The advantage of the approach is that it does not require to estimate the CPU utilization that each application requires. In this paper, we propose an adaptive QOS mapping scheme using a feedback control. Also, we show that high level QOS values can be adjusted according to the reserved CPU capacity by using our algorithm.

Original languageEnglish
Title of host publicationProceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages261-268
Number of pages8
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 3rd International Workshop on Real-Time Computing Systems and Applications - Seoul, South Korea
Duration: 1996 Oct 301996 Nov 1

Other

OtherProceedings of the 1996 3rd International Workshop on Real-Time Computing Systems and Applications
CitySeoul, South Korea
Period96/10/3096/11/1

Fingerprint

Quality of service
Program processors
Feedback control

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Nakajima, T., & Fujita, H. (1996). Experiences with adaptive QOS mapping scheme. In Anon (Ed.), Proceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA (pp. 261-268). Piscataway, NJ, United States: IEEE.

Experiences with adaptive QOS mapping scheme. / Nakajima, Tatsuo; Fujita, Hiroshi.

Proceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA. ed. / Anon. Piscataway, NJ, United States : IEEE, 1996. p. 261-268.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakajima, T & Fujita, H 1996, Experiences with adaptive QOS mapping scheme. in Anon (ed.), Proceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA. IEEE, Piscataway, NJ, United States, pp. 261-268, Proceedings of the 1996 3rd International Workshop on Real-Time Computing Systems and Applications, Seoul, South Korea, 96/10/30.
Nakajima T, Fujita H. Experiences with adaptive QOS mapping scheme. In Anon, editor, Proceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA. Piscataway, NJ, United States: IEEE. 1996. p. 261-268
Nakajima, Tatsuo ; Fujita, Hiroshi. / Experiences with adaptive QOS mapping scheme. Proceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA. editor / Anon. Piscataway, NJ, United States : IEEE, 1996. pp. 261-268
@inproceedings{841bb260c2d5409b81a9a5f4b52ce241,
title = "Experiences with adaptive QOS mapping scheme",
abstract = "In multimedia computing, guaranteeing Quality of Service(QOS) is one of the most important topics. If QOS values specified by users are not ensured, the users may not put up with the degraded quality of media streams. However, operating systems cannot understand QOS values specified by users directly, then the QOS values should be mapped to the CPU capacity that is required for guaranteeing the QOS values. There are two approaches for realizing the mapping. In the first approach called static mapping, the mapping is calculated before applications are started. In the second approach called dynamic mapping, the mapping is calculated at run-time. The system monitors the actual CPU utilization of continuous media applications, and adjusts their reserved CPU resources at run-time. The advantage of the approach is that it does not require to estimate the CPU utilization that each application requires. In this paper, we propose an adaptive QOS mapping scheme using a feedback control. Also, we show that high level QOS values can be adjusted according to the reserved CPU capacity by using our algorithm.",
author = "Tatsuo Nakajima and Hiroshi Fujita",
year = "1996",
language = "English",
pages = "261--268",
editor = "Anon",
booktitle = "Proceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA",
publisher = "IEEE",

}

TY - GEN

T1 - Experiences with adaptive QOS mapping scheme

AU - Nakajima, Tatsuo

AU - Fujita, Hiroshi

PY - 1996

Y1 - 1996

N2 - In multimedia computing, guaranteeing Quality of Service(QOS) is one of the most important topics. If QOS values specified by users are not ensured, the users may not put up with the degraded quality of media streams. However, operating systems cannot understand QOS values specified by users directly, then the QOS values should be mapped to the CPU capacity that is required for guaranteeing the QOS values. There are two approaches for realizing the mapping. In the first approach called static mapping, the mapping is calculated before applications are started. In the second approach called dynamic mapping, the mapping is calculated at run-time. The system monitors the actual CPU utilization of continuous media applications, and adjusts their reserved CPU resources at run-time. The advantage of the approach is that it does not require to estimate the CPU utilization that each application requires. In this paper, we propose an adaptive QOS mapping scheme using a feedback control. Also, we show that high level QOS values can be adjusted according to the reserved CPU capacity by using our algorithm.

AB - In multimedia computing, guaranteeing Quality of Service(QOS) is one of the most important topics. If QOS values specified by users are not ensured, the users may not put up with the degraded quality of media streams. However, operating systems cannot understand QOS values specified by users directly, then the QOS values should be mapped to the CPU capacity that is required for guaranteeing the QOS values. There are two approaches for realizing the mapping. In the first approach called static mapping, the mapping is calculated before applications are started. In the second approach called dynamic mapping, the mapping is calculated at run-time. The system monitors the actual CPU utilization of continuous media applications, and adjusts their reserved CPU resources at run-time. The advantage of the approach is that it does not require to estimate the CPU utilization that each application requires. In this paper, we propose an adaptive QOS mapping scheme using a feedback control. Also, we show that high level QOS values can be adjusted according to the reserved CPU capacity by using our algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0030417552&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030417552&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030417552

SP - 261

EP - 268

BT - Proceedings of the International Workshop on Real-Time Computing Systems and Applications/RTCSA

A2 - Anon, null

PB - IEEE

CY - Piscataway, NJ, United States

ER -