Cristin-resultat-ID: 1832900
Sist endret: 16. februar 2021, 09:29
NVI-rapporteringsår: 2020
Resultat
Vitenskapelig Kapittel/Artikkel/Konferanseartikkel
2020

Clustering and Dimensionality-reduction Techniques Applied on Power Quality Measurement Data

Bidragsytere:
  • Gjert Hovland Rosenlund
  • Kristian Wang Høiem
  • Bendik Nybakk Torsæter og
  • Christian Andre Andresen

Bok

Om resultatet

Vitenskapelig Kapittel/Artikkel/Konferanseartikkel
Publiseringsår: 2020
ISBN:
  • 978-1-7281-4701-7
Open Access

Klassifisering

Fagfelt (NPI)

Fagfelt: Elkraft og elektrotekniske fag
- Fagområde: Realfag og teknologi

Beskrivelse Beskrivelse

Tittel

Clustering and Dimensionality-reduction Techniques Applied on Power Quality Measurement Data

Sammendrag

The power system is changing rapidly, and new tools for predicting unwanted events are needed to keep a high level of security of supply. Large volumes of data from the Norwegian power grid have been collected over several years, and unwanted events as interruptions, earth faults, voltage dips and rapid voltage changes have been logged. This paper demonstrates the application of clustering and dimensionality-reduction techniques for the purpose of predicting unwanted events. Several techniques have been applied to reduce the dimensionality of the datasets and to cluster events based on analytical features, to separate events containing faults from a normal situation. The paper shows that the developed predictive model has some predictive capability when using balanced datasets containing similar muber of fault events and non-fault events. One of the main findings, however, is that this predictive capability is significantly reduced when using unbalanced datasets. Thus, the development of an accurate predictive model based on normal power system conditions, i.e. an unbalanced dataset of events and non-events, is a topic for further research.

Bidragsytere

Gjert Hovland Rosenlund

  • Tilknyttet:
    Forfatter
    ved Energisystemer ved SINTEF Energi AS

Kristian Wang Høiem

  • Tilknyttet:
    Forfatter
    ved Realfag og teknologi ved Norges miljø- og biovitenskapelige universitet
Aktiv cristin-person

Bendik Nybakk Torsæter

  • Tilknyttet:
    Forfatter
    ved Energisystemer ved SINTEF Energi AS

Christian Andre Andresen

  • Tilknyttet:
    Forfatter
    ved Energisystemer ved SINTEF Energi AS
1 - 4 av 4

Resultatet er en del av Resultatet er en del av

2020 International Conference on Smart Energy Systems and Technologies - SEST.

SEST 2020, .. 2020, IEEE. Vitenskapelig antologi/Konferanseserie
1 - 1 av 1