Predicting Power Quality Disturbance Events from Weather Conditions Using Gaussian Mixture Model and Decision Tree

Ali Asheibi, Ashraf Khalil, Zakariya Rajab

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

The effects of weather conditions on generation of power quality disturbances due to climate change has increased. Therefore, it has become essential to capture any power quality (PQ) disturbance events to investigate any causalities of weather conditions. In this paper, Gaussian Mixture Models (GMM) of clustering techniques is used to detect anomalies in PQ disturbances events and discover any association with weather data. To train the GMM, the Expectation and Maximization algorithm (EM) is employed. The C5.0 algorithm of classification techniques is then applied to the discovered classes to gain close insight into the obtained clusters and to predict the occurrences of unusual clusters in PQ future measurement data.
Original languageEnglish
Title of host publication2023 10th International Conference on Electrical and Electronics Engineering (ICEEE)
Number of pages6
PublisherIEEE
Publication date2023
Pages469-474
ISBN (Electronic)979-8-3503-0429-9
DOIs
Publication statusPublished - 2023
Event2023 10th International Conference on Electrical and Electronics Engineering - Istanbul, Turkey
Duration: 8 May 202310 May 2023

Conference

Conference2023 10th International Conference on Electrical and Electronics Engineering
Country/TerritoryTurkey
CityIstanbul
Period08/05/202310/05/2023

Keywords

  • Power quality (PQ)
  • Clustering
  • Gaussian mixture models (GMM)
  • Expectation and maximization algorithm (EM) decision tree (C5.0)

Fingerprint

Dive into the research topics of 'Predicting Power Quality Disturbance Events from Weather Conditions Using Gaussian Mixture Model and Decision Tree'. Together they form a unique fingerprint.

Cite this