Data sources in proactive network management

Marat Zhanikeev, John McKeown, Yoshiaki Tanaka

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

    Abstract

    As networks are extremely heterogeneous, and application layer requires higher level o f flexibility in network performance and resource allocation, proactive management is becoming an important research target. Main purpose of proactive management is to detect network performance anomaly before its occurrence and undertake steps to rectify the conditions that lead to the anomaly. Since detection of anomalies is the key point of proactive management, continuous data about network performance are required. Conventionally, to obtain performance data one would use SNMP protocol to poll MIB agents at networking devices at regular intervals, and then process the data offline. For large management domains offline processing either takes long time when thorough, or is not reliable when processing is made selective. To solve the above problem with online processing, we propose to use performance data obtained by end-to-end probing. In our study, we use neural network to predict anomalies. Comparison of predictions made solely based on SNMP polls with those that use end-to-end probing prove the validity of our proposal. End-to-end performance data offers clearer patterns, and best error rate of predictions around 4-6%, which is one forth of predictions based on SNMP polls. In our study we use special probes with packets of two different sizes in order to obtain multiple performance data from a single probe.

    Original languageEnglish
    Title of host publicationAPNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings
    PublisherKICS/KNOM
    Pages410-421
    Number of pages12
    Publication statusPublished - 2005
    Event8th Asia-Pacific Network Operations and Management Symposium, APNOMS 2005 - Okinawa
    Duration: 2005 Sep 272005 Sep 30

    Other

    Other8th Asia-Pacific Network Operations and Management Symposium, APNOMS 2005
    CityOkinawa
    Period05/9/2705/9/30

    Fingerprint

    Network management
    Network performance
    Processing
    Resource allocation
    Neural networks
    Network protocols
    Data sources
    Anomaly
    Prediction
    Polls

    ASJC Scopus subject areas

    • Computer Networks and Communications
    • Management Science and Operations Research

    Cite this

    Zhanikeev, M., McKeown, J., & Tanaka, Y. (2005). Data sources in proactive network management. In APNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings (pp. 410-421). KICS/KNOM.

    Data sources in proactive network management. / Zhanikeev, Marat; McKeown, John; Tanaka, Yoshiaki.

    APNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings. KICS/KNOM, 2005. p. 410-421.

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

    Zhanikeev, M, McKeown, J & Tanaka, Y 2005, Data sources in proactive network management. in APNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings. KICS/KNOM, pp. 410-421, 8th Asia-Pacific Network Operations and Management Symposium, APNOMS 2005, Okinawa, 05/9/27.
    Zhanikeev M, McKeown J, Tanaka Y. Data sources in proactive network management. In APNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings. KICS/KNOM. 2005. p. 410-421
    Zhanikeev, Marat ; McKeown, John ; Tanaka, Yoshiaki. / Data sources in proactive network management. APNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings. KICS/KNOM, 2005. pp. 410-421
    @inproceedings{ff93a7b02271412ca865cb737ceb6c25,
    title = "Data sources in proactive network management",
    abstract = "As networks are extremely heterogeneous, and application layer requires higher level o f flexibility in network performance and resource allocation, proactive management is becoming an important research target. Main purpose of proactive management is to detect network performance anomaly before its occurrence and undertake steps to rectify the conditions that lead to the anomaly. Since detection of anomalies is the key point of proactive management, continuous data about network performance are required. Conventionally, to obtain performance data one would use SNMP protocol to poll MIB agents at networking devices at regular intervals, and then process the data offline. For large management domains offline processing either takes long time when thorough, or is not reliable when processing is made selective. To solve the above problem with online processing, we propose to use performance data obtained by end-to-end probing. In our study, we use neural network to predict anomalies. Comparison of predictions made solely based on SNMP polls with those that use end-to-end probing prove the validity of our proposal. End-to-end performance data offers clearer patterns, and best error rate of predictions around 4-6{\%}, which is one forth of predictions based on SNMP polls. In our study we use special probes with packets of two different sizes in order to obtain multiple performance data from a single probe.",
    author = "Marat Zhanikeev and John McKeown and Yoshiaki Tanaka",
    year = "2005",
    language = "English",
    pages = "410--421",
    booktitle = "APNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings",
    publisher = "KICS/KNOM",

    }

    TY - GEN

    T1 - Data sources in proactive network management

    AU - Zhanikeev, Marat

    AU - McKeown, John

    AU - Tanaka, Yoshiaki

    PY - 2005

    Y1 - 2005

    N2 - As networks are extremely heterogeneous, and application layer requires higher level o f flexibility in network performance and resource allocation, proactive management is becoming an important research target. Main purpose of proactive management is to detect network performance anomaly before its occurrence and undertake steps to rectify the conditions that lead to the anomaly. Since detection of anomalies is the key point of proactive management, continuous data about network performance are required. Conventionally, to obtain performance data one would use SNMP protocol to poll MIB agents at networking devices at regular intervals, and then process the data offline. For large management domains offline processing either takes long time when thorough, or is not reliable when processing is made selective. To solve the above problem with online processing, we propose to use performance data obtained by end-to-end probing. In our study, we use neural network to predict anomalies. Comparison of predictions made solely based on SNMP polls with those that use end-to-end probing prove the validity of our proposal. End-to-end performance data offers clearer patterns, and best error rate of predictions around 4-6%, which is one forth of predictions based on SNMP polls. In our study we use special probes with packets of two different sizes in order to obtain multiple performance data from a single probe.

    AB - As networks are extremely heterogeneous, and application layer requires higher level o f flexibility in network performance and resource allocation, proactive management is becoming an important research target. Main purpose of proactive management is to detect network performance anomaly before its occurrence and undertake steps to rectify the conditions that lead to the anomaly. Since detection of anomalies is the key point of proactive management, continuous data about network performance are required. Conventionally, to obtain performance data one would use SNMP protocol to poll MIB agents at networking devices at regular intervals, and then process the data offline. For large management domains offline processing either takes long time when thorough, or is not reliable when processing is made selective. To solve the above problem with online processing, we propose to use performance data obtained by end-to-end probing. In our study, we use neural network to predict anomalies. Comparison of predictions made solely based on SNMP polls with those that use end-to-end probing prove the validity of our proposal. End-to-end performance data offers clearer patterns, and best error rate of predictions around 4-6%, which is one forth of predictions based on SNMP polls. In our study we use special probes with packets of two different sizes in order to obtain multiple performance data from a single probe.

    UR - http://www.scopus.com/inward/record.url?scp=84899030034&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84899030034&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:84899030034

    SP - 410

    EP - 421

    BT - APNOMS 2005 - 8th Asia-Pacific Network Operations and Management Symposium :Toward Managed Ubiquitous Information Society, Proceedings

    PB - KICS/KNOM

    ER -