Smart Distributed Generation Systems Using Artificial Neural Network-Based Event Classification

Document Type

Article

Publication Date

3-13-2018

Publication Title

IEEE Power and Energy Technology Systems Journal

DOI

10.1109/JPETS.2018.2805894

ISSN

2332-7707

Abstract

Distributed Generation (DG) sources have become an integral part of today’s decentralized power systems. However, current DG systems are mostly passive and do not provide intelligent information to help detect power quality issues. In this paper, a novel and intelligent event classification scheme is proposed to provide DG systems with real-time decision making capabilities. The proposed technique has the ability to provide information to help maintain the quality and reliability of DG systems under various disturbances or operating conditions. This event classification technique was developed using artificial neural networks (ANN) with a pre-defined set of local input parameters. The algorithm is implemented using four parallel ANNs that were designed to operate under a majority vote fusion algorithm representing the final classification output. A total of 310 event cases were generated to test the performance of the proposed technique. Simulation results showed that events were accurately classified within 10 cycles of their occurrences while achieving a 96.21% average classification accuracy.

Link to Full Text

Share

COinS