An engineering approach to dynamic prediction of network performance from application logs

Zalal Uddin Mohammad Abusina, Salahuddln Muhammad Salim Zabir, Ahmed Ashir, Debasish Chakraborty, Takuo Suganuma, Norio Shiratori

    Research output: Contribution to journalArticle

    13 Citations (Scopus)

    Abstract

    Network measurement traces contain information regarding network behavior over the period of observation. Research carried out from different contexts shows predictions of network behavior can be made depending on network past history. Existing works on network performance prediction use a complicated stochastic modeling approach that extrapolates past data to yield a rough estimate of long-term future network performance. However, prediction of network performance in the immediate future is still an unresolved problem. In this paper, we address network performance prediction as an engineering problem. The main contribution of this paper is to predict network performance dynamically for the immediate future. Our proposal also considers the practical implication of prediction. Therefore, instead of following the conventional approach to predict one single value, we predict a range within which network performance may lie. This range is bounded by our two newly proposed indices, namely, Optimistic Network Performance Index (ONPI) and Robust Network Performance Index (RNPI). Experiments carried out using one-year-long traffic traces between several pairs of real-life networks validate the usefulness of our model.

    Original languageEnglish
    Pages (from-to)151-162
    Number of pages12
    JournalInternational Journal of Network Management
    Volume15
    Issue number3
    DOIs
    Publication statusPublished - 2005 May

    Fingerprint

    Network performance

    ASJC Scopus subject areas

    • Software

    Cite this

    Abusina, Z. U. M., Zabir, S. M. S., Ashir, A., Chakraborty, D., Suganuma, T., & Shiratori, N. (2005). An engineering approach to dynamic prediction of network performance from application logs. International Journal of Network Management, 15(3), 151-162. https://doi.org/10.1002/nem.554

    An engineering approach to dynamic prediction of network performance from application logs. / Abusina, Zalal Uddin Mohammad; Zabir, Salahuddln Muhammad Salim; Ashir, Ahmed; Chakraborty, Debasish; Suganuma, Takuo; Shiratori, Norio.

    In: International Journal of Network Management, Vol. 15, No. 3, 05.2005, p. 151-162.

    Research output: Contribution to journalArticle

    Abusina, ZUM, Zabir, SMS, Ashir, A, Chakraborty, D, Suganuma, T & Shiratori, N 2005, 'An engineering approach to dynamic prediction of network performance from application logs', International Journal of Network Management, vol. 15, no. 3, pp. 151-162. https://doi.org/10.1002/nem.554
    Abusina, Zalal Uddin Mohammad ; Zabir, Salahuddln Muhammad Salim ; Ashir, Ahmed ; Chakraborty, Debasish ; Suganuma, Takuo ; Shiratori, Norio. / An engineering approach to dynamic prediction of network performance from application logs. In: International Journal of Network Management. 2005 ; Vol. 15, No. 3. pp. 151-162.
    @article{a842e03bff7b453da3a05f011031ce63,
    title = "An engineering approach to dynamic prediction of network performance from application logs",
    abstract = "Network measurement traces contain information regarding network behavior over the period of observation. Research carried out from different contexts shows predictions of network behavior can be made depending on network past history. Existing works on network performance prediction use a complicated stochastic modeling approach that extrapolates past data to yield a rough estimate of long-term future network performance. However, prediction of network performance in the immediate future is still an unresolved problem. In this paper, we address network performance prediction as an engineering problem. The main contribution of this paper is to predict network performance dynamically for the immediate future. Our proposal also considers the practical implication of prediction. Therefore, instead of following the conventional approach to predict one single value, we predict a range within which network performance may lie. This range is bounded by our two newly proposed indices, namely, Optimistic Network Performance Index (ONPI) and Robust Network Performance Index (RNPI). Experiments carried out using one-year-long traffic traces between several pairs of real-life networks validate the usefulness of our model.",
    author = "Abusina, {Zalal Uddin Mohammad} and Zabir, {Salahuddln Muhammad Salim} and Ahmed Ashir and Debasish Chakraborty and Takuo Suganuma and Norio Shiratori",
    year = "2005",
    month = "5",
    doi = "10.1002/nem.554",
    language = "English",
    volume = "15",
    pages = "151--162",
    journal = "International Journal of Network Management",
    issn = "1055-7148",
    publisher = "John Wiley and Sons Ltd",
    number = "3",

    }

    TY - JOUR

    T1 - An engineering approach to dynamic prediction of network performance from application logs

    AU - Abusina, Zalal Uddin Mohammad

    AU - Zabir, Salahuddln Muhammad Salim

    AU - Ashir, Ahmed

    AU - Chakraborty, Debasish

    AU - Suganuma, Takuo

    AU - Shiratori, Norio

    PY - 2005/5

    Y1 - 2005/5

    N2 - Network measurement traces contain information regarding network behavior over the period of observation. Research carried out from different contexts shows predictions of network behavior can be made depending on network past history. Existing works on network performance prediction use a complicated stochastic modeling approach that extrapolates past data to yield a rough estimate of long-term future network performance. However, prediction of network performance in the immediate future is still an unresolved problem. In this paper, we address network performance prediction as an engineering problem. The main contribution of this paper is to predict network performance dynamically for the immediate future. Our proposal also considers the practical implication of prediction. Therefore, instead of following the conventional approach to predict one single value, we predict a range within which network performance may lie. This range is bounded by our two newly proposed indices, namely, Optimistic Network Performance Index (ONPI) and Robust Network Performance Index (RNPI). Experiments carried out using one-year-long traffic traces between several pairs of real-life networks validate the usefulness of our model.

    AB - Network measurement traces contain information regarding network behavior over the period of observation. Research carried out from different contexts shows predictions of network behavior can be made depending on network past history. Existing works on network performance prediction use a complicated stochastic modeling approach that extrapolates past data to yield a rough estimate of long-term future network performance. However, prediction of network performance in the immediate future is still an unresolved problem. In this paper, we address network performance prediction as an engineering problem. The main contribution of this paper is to predict network performance dynamically for the immediate future. Our proposal also considers the practical implication of prediction. Therefore, instead of following the conventional approach to predict one single value, we predict a range within which network performance may lie. This range is bounded by our two newly proposed indices, namely, Optimistic Network Performance Index (ONPI) and Robust Network Performance Index (RNPI). Experiments carried out using one-year-long traffic traces between several pairs of real-life networks validate the usefulness of our model.

    UR - http://www.scopus.com/inward/record.url?scp=18844373635&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=18844373635&partnerID=8YFLogxK

    U2 - 10.1002/nem.554

    DO - 10.1002/nem.554

    M3 - Article

    AN - SCOPUS:18844373635

    VL - 15

    SP - 151

    EP - 162

    JO - International Journal of Network Management

    JF - International Journal of Network Management

    SN - 1055-7148

    IS - 3

    ER -