Title: Towards user-friendly and high-performance analytics with big data historian
Authors: Possolt, Martin
Jirkovský, Václav
Obitko, Marek
Citation: STEINBERGER, Josef ed.; ZÍMA, Martin ed.; FIALA, Dalibor ed.; DOSTAL, Martin ed.; NYKL, Michal ed. Data a znalosti 2017: sborník konference, Plzeň, Hotel Angelo 5. - 6. října 2017. 1. vyd. Plzeň: Západočeská univerzita v Plzni, 2017, s. 27-30. ISBN 978-80-261-0720-0.
Issue Date: 2017
Publisher: Západočeská univerzita v Plzni
Document type: konferenční příspěvek
conferenceObject
URI: https://www.zcu.cz/export/sites/zcu/pracoviste/vyd/online/DataAZnalosti2017.pdf
http://hdl.handle.net/11025/26330
ISBN: 978-80-261-0720-0
Keywords: vícevrstvý perceptron;velká data;ontologie;vodní elektrárna
Keywords in different language: multilayer perceptron;big data;ontology;hydroelectric power station
Abstract in different language: We are witnessing the trend of increasing data production in various domains including industrial automation. This trend requires means for data capturing, storing, and analyzing. Furthermore, a versatile data model is needed to enable easy knowledge representation as well as change management. In this paper, we utilize Semantic Big Data Historian, which can cope with previously mentioned requirements, for a demonstration of promising analytic approach combining Big Data methods and a user-friendly modular platform. The ap-proach is demonstrated on data from a hydroelectric power station. The station has been dealing with the interesting problem of prediction when to momentari-ly stop their turbine to increase generated power after the restart. In this contri-bution, we discuss several approaches how to process and analyze data from power station sensors for achieving the best results.
Rights: © Západočeská univerzita v Plzni
Appears in Collections:Data a znalosti 2017
Data a znalosti 2017

Files in This Item:
File Description SizeFormat 
Possolt.pdfPlný text423,17 kBAdobe PDFView/Open


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/26330

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.