Incipient Fault Prediction in Power Quality Monitoring

dc.contributor.affiliationSINTEF AS
dc.contributor.affiliationSINTEF AS
dc.contributor.affiliationSINTEF Energy Research AS
dc.contributor.affiliationSINTEF Energy Research AS
dc.contributor.authorHoffmann, Volker
dc.contributor.authorMichałowska, Katarzyna
dc.contributor.authorAndresen, Christian
dc.contributor.authorTorsæter, Bendik Nybakk
dc.contributor.countryNorway
dc.contributor.countryNorway
dc.contributor.countryNorway
dc.contributor.countryNorway
dc.contributor.detailedauthorHoffmann, Volker, SINTEF AS, Norway
dc.contributor.detailedauthorMichałowska, Katarzyna, SINTEF AS, Norway
dc.contributor.detailedauthorAndresen, Christian, SINTEF Energy Research AS, Norway
dc.contributor.detailedauthorTorsæter, Bendik Nybakk, SINTEF Energy Research AS, Norway
dc.date.accessioned2019-07-24T12:41:29Z
dc.date.available2019-07-24T12:41:29Z
dc.date.conferencedate3-6 June 2019
dc.date.issued2019-06-03
dc.description.abstractEuropean and global power grids are moving towards a Smart Grid architecture. Supporting this, advanced measurement equipment such as PQAs and PMUs are being deployed. These generate vast amounts of data upon which machine learning models capable of forecasting incipient faults can be built. We use live measurements from nine PQA nodes in the Norwegian grid to predict incipient interruptions, voltage dips, and earth faults. After training ensembles of gradient boosted decision trees on spectral decompositions of cycle-by-cycle voltage measurements, we evaluate their predictive performance. We find that interruptions are easiest to predict (95 % true positive, 20 % false positives). Earth faults and voltage dips are more challenging. Our models outperform naïve classifiers. We have explored forecast horizons of up to 40 seconds, but we have indications that forecast horizons of at least a few minutes are feasible.
dc.description.conferencelocationMadrid, Spain
dc.description.conferencenameCIRED 2019
dc.description.openaccessYes
dc.description.peerreviewedYes
dc.description.sessionPower quality and electromagnetic compatibility
dc.description.sessionidSession 2
dc.identifier.isbn978-2-9602415-0-1
dc.identifier.issn2032-9644
dc.identifier.urihttps://cired-repository.org/handle/20.500.12455/444
dc.identifier.urihttp://dx.doi.org/10.34890/673
dc.language.isoen
dc.publisherAIM
dc.relation.ispartProc. of the 25th International Conference on Electricity Distribution (CIRED 2019)
dc.relation.ispartofseriesCIRED Conference Proceedings
dc.titleIncipient Fault Prediction in Power Quality Monitoring
dc.title.number1535
dc.typeConference Proceedings
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
CIRED 2019 - 1535.pdf
Size:
311.42 KB
Format:
Adobe Portable Document Format