A case study on the use of data mining for detecting and classifying abnormal power system modal behaviors. Issue Volume 31:Issues 2(2019) (3rd April 2019)

• Record Type: Journal Article
• Authors: Yin, Tianzhixi; Wulff, Shaun S.; Pierre, John W.; Robinson, Timothy J.
• Is Part Of: Quality engineering. Volume 31:Issues 2(2019)
• Page Start: 314
• Page End: 333
• Publication Date: 2019-04-03
• Subjects: feature extraction -- knowledge discovery -- machine learning -- phasor measurement units -- smart grid -- wide-area measurement systems; Quality control -- Periodicals; Production management -- Quality control -- Periodicals; 658.5
• DOI: 10.1080/08982112.2018.1530356
• Languages: English
• ISSNs: 0898-2112

Abstract

Abstract: This article presents a case study involving data mining (DM) and the knowledge discovery (KD) process for the Western US power grid. With the installation of phasor measurement units (PMUs) in the US power systems, there is potential to improve wide-area situational awareness using data analytics. The KD process is challenging due to the complex nature of the power grid, data propriety issues, the file size of the time-series data, and questions of how to extract meaningful features. This case study demonstrates how the KD process can be implemented in light of these challenges to detect the anomalies of interest.