Towards application of text mining for enhanced power network data analytics - Part II: Offline analysis of textual data

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

    171 Downloads (Pure)

    Abstract

    Text mining is a subdivision of data mining technologies used to extract useful information from unstructured textual data. In recent years, power distribution networks have become more complex due to the versatile consumer demand and integration of distributed energy resources. This has led to the need for enhanced data processing and analysis, i.e., data analytics, in distribution system studies. This paper for the first time explores the feasibility of application of text mining methods as a part of power system data analytics. The focus is on identifying and describing the steps that need to be taken for the knowledge extraction from large offline textual document collections and on demonstrating the effectiveness of the whole process if undertaken by a power system engineer, i.e., a non-specialist in the area of text mining.

    Original languageEnglish
    Title of host publicationIET Conference Publications
    PublisherInstitution of Engineering and Technology
    Volume2016
    EditionCP711
    Publication statusPublished - 2016
    EventMediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion, MedPower 2016 - Belgrade, Serbia
    Duration: 6 Nov 20169 Nov 2016

    Conference

    ConferenceMediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion, MedPower 2016
    Country/TerritorySerbia
    CityBelgrade
    Period6/11/169/11/16

    Keywords

    • Data analytics
    • Power distribution network
    • Text categorisation
    • Text mining
    • Text summarisation

    Fingerprint

    Dive into the research topics of 'Towards application of text mining for enhanced power network data analytics - Part II: Offline analysis of textual data'. Together they form a unique fingerprint.

    Cite this