Learning environment model at runtime for self-adaptive systems

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

    4 Citations (Scopus)

    Abstract

    Self-adaptive systems alter their behavior in response to environmental changes to continually satisfy their requirements. Self-adaptive systems employ an environment model, which should be updated during runtime to maintain consistency with the real environment. Although some techniques have been proposed to learn environment model based on execution traces at the design time, these techniques are time consuming and consequently inappropriate for runtime learning. Herein, a technique using a stochastic gradient descent and the difference in the data acquired during the run-time is proposed as an efficient learning environment model. The computational time and accuracy of our technique are verified through a case study.

    Original languageEnglish
    Title of host publication32nd Annual ACM Symposium on Applied Computing, SAC 2017
    PublisherAssociation for Computing Machinery
    Pages1198-1204
    Number of pages7
    VolumePart F128005
    ISBN (Electronic)9781450344869
    DOIs
    Publication statusPublished - 2017 Apr 3
    Event32nd Annual ACM Symposium on Applied Computing, SAC 2017 - Marrakesh, Morocco
    Duration: 2017 Apr 42017 Apr 6

    Other

    Other32nd Annual ACM Symposium on Applied Computing, SAC 2017
    CountryMorocco
    CityMarrakesh
    Period17/4/417/4/6

    Fingerprint

    Adaptive systems

    Keywords

    • Gradient descent
    • Learning
    • Self-adaptive

    ASJC Scopus subject areas

    • Software

    Cite this

    Tanabe, M., Tei, K., Fukazawa, Y., & Honiden, S. (2017). Learning environment model at runtime for self-adaptive systems. In 32nd Annual ACM Symposium on Applied Computing, SAC 2017 (Vol. Part F128005, pp. 1198-1204). Association for Computing Machinery. https://doi.org/10.1145/3019612.3019776

    Learning environment model at runtime for self-adaptive systems. / Tanabe, Moeka; Tei, Kenji; Fukazawa, Yoshiaki; Honiden, Shinichi.

    32nd Annual ACM Symposium on Applied Computing, SAC 2017. Vol. Part F128005 Association for Computing Machinery, 2017. p. 1198-1204.

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

    Tanabe, M, Tei, K, Fukazawa, Y & Honiden, S 2017, Learning environment model at runtime for self-adaptive systems. in 32nd Annual ACM Symposium on Applied Computing, SAC 2017. vol. Part F128005, Association for Computing Machinery, pp. 1198-1204, 32nd Annual ACM Symposium on Applied Computing, SAC 2017, Marrakesh, Morocco, 17/4/4. https://doi.org/10.1145/3019612.3019776
    Tanabe M, Tei K, Fukazawa Y, Honiden S. Learning environment model at runtime for self-adaptive systems. In 32nd Annual ACM Symposium on Applied Computing, SAC 2017. Vol. Part F128005. Association for Computing Machinery. 2017. p. 1198-1204 https://doi.org/10.1145/3019612.3019776
    Tanabe, Moeka ; Tei, Kenji ; Fukazawa, Yoshiaki ; Honiden, Shinichi. / Learning environment model at runtime for self-adaptive systems. 32nd Annual ACM Symposium on Applied Computing, SAC 2017. Vol. Part F128005 Association for Computing Machinery, 2017. pp. 1198-1204
    @inproceedings{e54e30a63922446f876814e294fbca36,
    title = "Learning environment model at runtime for self-adaptive systems",
    abstract = "Self-adaptive systems alter their behavior in response to environmental changes to continually satisfy their requirements. Self-adaptive systems employ an environment model, which should be updated during runtime to maintain consistency with the real environment. Although some techniques have been proposed to learn environment model based on execution traces at the design time, these techniques are time consuming and consequently inappropriate for runtime learning. Herein, a technique using a stochastic gradient descent and the difference in the data acquired during the run-time is proposed as an efficient learning environment model. The computational time and accuracy of our technique are verified through a case study.",
    keywords = "Gradient descent, Learning, Self-adaptive",
    author = "Moeka Tanabe and Kenji Tei and Yoshiaki Fukazawa and Shinichi Honiden",
    year = "2017",
    month = "4",
    day = "3",
    doi = "10.1145/3019612.3019776",
    language = "English",
    volume = "Part F128005",
    pages = "1198--1204",
    booktitle = "32nd Annual ACM Symposium on Applied Computing, SAC 2017",
    publisher = "Association for Computing Machinery",

    }

    TY - GEN

    T1 - Learning environment model at runtime for self-adaptive systems

    AU - Tanabe, Moeka

    AU - Tei, Kenji

    AU - Fukazawa, Yoshiaki

    AU - Honiden, Shinichi

    PY - 2017/4/3

    Y1 - 2017/4/3

    N2 - Self-adaptive systems alter their behavior in response to environmental changes to continually satisfy their requirements. Self-adaptive systems employ an environment model, which should be updated during runtime to maintain consistency with the real environment. Although some techniques have been proposed to learn environment model based on execution traces at the design time, these techniques are time consuming and consequently inappropriate for runtime learning. Herein, a technique using a stochastic gradient descent and the difference in the data acquired during the run-time is proposed as an efficient learning environment model. The computational time and accuracy of our technique are verified through a case study.

    AB - Self-adaptive systems alter their behavior in response to environmental changes to continually satisfy their requirements. Self-adaptive systems employ an environment model, which should be updated during runtime to maintain consistency with the real environment. Although some techniques have been proposed to learn environment model based on execution traces at the design time, these techniques are time consuming and consequently inappropriate for runtime learning. Herein, a technique using a stochastic gradient descent and the difference in the data acquired during the run-time is proposed as an efficient learning environment model. The computational time and accuracy of our technique are verified through a case study.

    KW - Gradient descent

    KW - Learning

    KW - Self-adaptive

    UR - http://www.scopus.com/inward/record.url?scp=85020904092&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85020904092&partnerID=8YFLogxK

    U2 - 10.1145/3019612.3019776

    DO - 10.1145/3019612.3019776

    M3 - Conference contribution

    AN - SCOPUS:85020904092

    VL - Part F128005

    SP - 1198

    EP - 1204

    BT - 32nd Annual ACM Symposium on Applied Computing, SAC 2017

    PB - Association for Computing Machinery

    ER -