Post-fault prediction of transient instabilities using stacked sparse autoencoder

•A fast and robust method is proposed for transient stability assessment.•Stacked sparse autoencoder is used as a stability classification algorithm.•The measurements from the fault-on time period are adopted as inputs.•The method is tested on WSCC test system and on the Turkish power system.•The ro...

Full description

Saved in:
Bibliographic Details
Published in:Electric power systems research Vol. 164; pp. 243 - 252
Main Authors: Mahdi, Mohammed, Genc, V.M. Istemihan
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.11.2018
Elsevier Science Ltd
Subjects:
Deep learning
Electricity distribution
Fault diagnosis
Measuring instruments
Monitoring systems
Multilayer perceptrons
Phasor measurement units
Power reliability
Prediction
Predictions
Situational awareness
Sparse autoencoder
Stability
Transient stability
Wide area measurements
Deep learning
Phasor measurement units
Sparse autoencoder
Transient stability
Wide area measurements
Prediction
ISSN:0378-7796, 1873-2046
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A fast and robust method is proposed for transient stability assessment.•Stacked sparse autoencoder is used as a stability classification algorithm.•The measurements from the fault-on time period are adopted as inputs.•The method is tested on WSCC test system and on the Turkish power system.•The robustness of the method is tested against different uncertainties. Post-fault prediction of transient stability of power systems has a great impact on the performance of wide area monitoring, protection and control systems. Situational awareness capabilities of a power system are improved by fast detection of instabilities after severe fault occurrences. This allows sufficient time to take necessary corrective control actions. In this paper, a novel method based on stacked sparse autoencoder is proposed to predict the post-fault transient stability status of the power system directly after clearing the fault. A dataset is generated off-line to train a stacked sparse autoencoder, and then the trained stacked sparse autoencoder is used in an online application of predicting any transient instability. The stacked sparse autoencoder is fed by the inputs, which are specific points extracted from the fault-on voltage magnitude measurements collected from the phasor measurement units. The effectiveness of the proposed method is demonstrated and compared with the conventional approaches that adopt multilayer perceptrons or post-fault measurements as it is applied to the 127-bus WSCC test system and to the Turkish power system.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0378-7796
1873-2046
DOI:10.1016/j.epsr.2018.08.009