Optimal Feature and Decision Tree Based Classification of Power Quality Disturbances in Distributed Generation Systems

• Type: Article in International Conference Proceedings Book
• Date: 2014

Authors

Ray, PK (Author) Other; Mohanty, SR (Author) Other; Kishor, N (Author) Other; Catalao, J (Author) Other

Conference proceedings International

Title: 2014 IEEE PES GENERAL MEETING - CONFERENCE & EXPOSITION

IEEE PES General Meeting

National Harbor, MD, JUL 27-31, 2014

Indexing

ISI Web of Knowledge - 0 Citations

Other information

Authenticus ID: P-00N-5A0

DOI: 10.1109/pesgm.2014.6939076

Abstract (EN): Penetration of distributed generation (DG) systems in conventional power systems leads to power quality (PQ) disturbances. This paper provides an improved PQ disturbances classification, which are associated with load changes and environmental factors. Various forms of PQ disturbances, including sag, swell, notch and harmonics, are taken into account. Several features are obtained through HS-transform, out of which optimal features are selected using a genetic algorithm (GA). These optimal features are used for PQ disturbances classification by employing support vector machines (SVM) and decision tree (DT) classifiers. The study is supported on three different case studies, considering experimental set-up prototypes for wind energy and photovoltaic (PV) systems, as well as the modified Nordic 32-bus test system. The robustness and precision of DT and SWM is performed with noise and harmonics in the disturbance signals, thus providing comprehensive results.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 1