Abstract | ||
---|---|---|
Accurate and rapid transient stability assessment (TSA) is able to reduce the risk of severe blackout and cascading failure effectively. Data-driven based TSA has been continuously concerned due to the wide deployment of phasor measurement unit (PMU) in recent year. In this paper, a temporal feature selection for time-adaptive transient stability assessment scheme is proposed, which is one efficient filter feature ranking algorithm to extract the crucial temporal features subset by calculating the feature importance. Consequently, the accuracy and speed of TSA can be balanced. The simulation implemented on New England 39-bus power system demonstrates the effectiveness of proposed method to decrease the model complexity and speed up the training process. In addition, explanation of the reason why the response time can be reduced with proposed temporal feature selection for TSA is also presented from the data visualization view. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ISGTEurope.2019.8905487 | 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe) |
Keywords | Field | DocType |
transient stability assessment,temporal feature selection,phasor measurement unit,crucial temporal features subset,data visualization | Feature selection,Pattern recognition,Computer science,Transient stability assessment,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
2165-4816 | 978-1-5386-8219-7 | 0 |
PageRank | References | Authors |
0.34 | 5 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bendong Tan | 1 | 0 | 1.01 |
Jun Yang | 2 | 8 | 2.27 |
Ting Zhou | 3 | 0 | 0.34 |
Yi Xiao | 4 | 0 | 0.34 |
Qiangming Zhou | 5 | 0 | 0.34 |