A Deep Learning Method Based on Bidirectional Wavenet for Voltage Sag State Estimation Via Limited Monitors in Power System
Voltage sag state estimation based on a limited number of accessible monitors is essential to assessing the cost balance between investments in mitigation device and disruption cost saved. In this paper, a deep learning method based on Bidirectional WaveNet for voltage sag state estimation via limited monitors in power grid is proposed. The presented method can estimate voltage sag state at unmonitored buses. Specially, the proposed deep learning architecture based on the Bidirectional WaveNet is designed to explore the long-term and long-range temporal dependencies in both forward and backward directions. In this way, only by using original measured voltages through monitors, high accuracy and quick estimation of voltage sag state can be achieved without restructured or designed of the raw monitored data. Moreover, the estimation results at multiple unmonitored buses can be simultaneously obtained by adopting only one model. A favorable feature of the proposed method is that it can be realized without system parameters or models or any other prior conditions. The proposed method is validated by the IEEE 30-bus benchmark systems. Experimental results demonstrate that the accuracy of voltage sag state estimation results is over 99.83%. Furthermore, a comparison among different models, including Bidirectional GRU based model, one-way-WaveNet based model and Bidirectional WaveNet based model, is also conducted. The results illustrate that the proposed Bidirectional WaveNet based model can achieve highest accuracy and quickest convergence speed
Year of publication: |
[2022]
|
---|---|
Authors: | deng, yaping ; Wang, Lu ; Jia, Hao ; zhang, xiaohui ; Tong, Xiangqian |
Publisher: |
[S.l.] : SSRN |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Contest Functions: Theoretical Foundations and Issues in Estimation
Jia, Hao, (2012)
-
Jia, Hao, (2011)
-
Contest functions: Theoretical foundations and issues in estimation
Jia, Hao, (2013)
- More ...