Online anomaly symptom detection and process's resource usage control

Midori Sugaya, Kimio Kuramitsu

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

1 Citation (Scopus)

Abstract

In this paper we propose an online lightweight anomaly symptom detection and process's resource usage control mechanism. Our system collects fine-grain resource information that can reflect the subtle changes of the application's behavior. Then it creates models with a learning-based algorithm without manual configurations. If an anomaly symptom is detected, the automatic procedure will start. The system will control the suspected application's resource use by limiting the upper bound resource of the process. The method will make the application yield its CPU to the administrative inspection. In this paper, we described whole architecture of the system and evaluate it with the non deterministic and deterministic failure. Our experimental results indicate that our prototype system is able to detect non deterministic failure with high precision in anomaly training and control it's resource use with an overhead of about 1%.

Original languageEnglish
Title of host publicationProceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011
Pages364-371
Number of pages8
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011 - Tokyo and Hiroshima
Duration: 2011 Mar 232011 Mar 27

Other

Other2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011
CityTokyo and Hiroshima
Period11/3/2311/3/27

Fingerprint

Program processors
Inspection
Control systems

Keywords

  • Anomaly symptom detection
  • Operating system
  • Resource control

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Sugaya, M., & Kuramitsu, K. (2011). Online anomaly symptom detection and process's resource usage control. In Proceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011 (pp. 364-371). [5741383] https://doi.org/10.1109/ISADS.2011.106

Online anomaly symptom detection and process's resource usage control. / Sugaya, Midori; Kuramitsu, Kimio.

Proceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011. 2011. p. 364-371 5741383.

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

Sugaya, M & Kuramitsu, K 2011, Online anomaly symptom detection and process's resource usage control. in Proceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011., 5741383, pp. 364-371, 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011, Tokyo and Hiroshima, 11/3/23. https://doi.org/10.1109/ISADS.2011.106
Sugaya M, Kuramitsu K. Online anomaly symptom detection and process's resource usage control. In Proceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011. 2011. p. 364-371. 5741383 https://doi.org/10.1109/ISADS.2011.106
Sugaya, Midori ; Kuramitsu, Kimio. / Online anomaly symptom detection and process's resource usage control. Proceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011. 2011. pp. 364-371
@inproceedings{18a4945d83d8464694491e402f3b0def,
title = "Online anomaly symptom detection and process's resource usage control",
abstract = "In this paper we propose an online lightweight anomaly symptom detection and process's resource usage control mechanism. Our system collects fine-grain resource information that can reflect the subtle changes of the application's behavior. Then it creates models with a learning-based algorithm without manual configurations. If an anomaly symptom is detected, the automatic procedure will start. The system will control the suspected application's resource use by limiting the upper bound resource of the process. The method will make the application yield its CPU to the administrative inspection. In this paper, we described whole architecture of the system and evaluate it with the non deterministic and deterministic failure. Our experimental results indicate that our prototype system is able to detect non deterministic failure with high precision in anomaly training and control it's resource use with an overhead of about 1{\%}.",
keywords = "Anomaly symptom detection, Operating system, Resource control",
author = "Midori Sugaya and Kimio Kuramitsu",
year = "2011",
doi = "10.1109/ISADS.2011.106",
language = "English",
isbn = "9780769543499",
pages = "364--371",
booktitle = "Proceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011",

}

TY - GEN

T1 - Online anomaly symptom detection and process's resource usage control

AU - Sugaya, Midori

AU - Kuramitsu, Kimio

PY - 2011

Y1 - 2011

N2 - In this paper we propose an online lightweight anomaly symptom detection and process's resource usage control mechanism. Our system collects fine-grain resource information that can reflect the subtle changes of the application's behavior. Then it creates models with a learning-based algorithm without manual configurations. If an anomaly symptom is detected, the automatic procedure will start. The system will control the suspected application's resource use by limiting the upper bound resource of the process. The method will make the application yield its CPU to the administrative inspection. In this paper, we described whole architecture of the system and evaluate it with the non deterministic and deterministic failure. Our experimental results indicate that our prototype system is able to detect non deterministic failure with high precision in anomaly training and control it's resource use with an overhead of about 1%.

AB - In this paper we propose an online lightweight anomaly symptom detection and process's resource usage control mechanism. Our system collects fine-grain resource information that can reflect the subtle changes of the application's behavior. Then it creates models with a learning-based algorithm without manual configurations. If an anomaly symptom is detected, the automatic procedure will start. The system will control the suspected application's resource use by limiting the upper bound resource of the process. The method will make the application yield its CPU to the administrative inspection. In this paper, we described whole architecture of the system and evaluate it with the non deterministic and deterministic failure. Our experimental results indicate that our prototype system is able to detect non deterministic failure with high precision in anomaly training and control it's resource use with an overhead of about 1%.

KW - Anomaly symptom detection

KW - Operating system

KW - Resource control

UR - http://www.scopus.com/inward/record.url?scp=79955722953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955722953&partnerID=8YFLogxK

U2 - 10.1109/ISADS.2011.106

DO - 10.1109/ISADS.2011.106

M3 - Conference contribution

SN - 9780769543499

SP - 364

EP - 371

BT - Proceedings - 2011 10th International Symposium on Autonomous Decentralized Systems, ISADS 2011

ER -