다양한 송전선로 고장데이터 생성을 위한 기반 데이터 증강기법 = GAN-Based Data Augmentation Technique for Various Transmission Line Fault Data

다국어 초록 (Multilingual Abstract)

Transmission line fault data plays an important role in power system reliability analysis and fault prediction. However, real fault data is not enough because transmission line faults do not frequently happen. To obtain various fault data, we propose a generative adversarial network (GAN)-based data augmentation technique. The proposed technique consists of three steps. i) it generates fault data using the wasserstein GAN with gradient penalty (WGAN-GP) model. ii) the generated data is filtered through an isolation forest (IF) algorithm, and iii) the filtered data is evaluated for its quality through KL-divergence. We visually showed that the proposed technique's data generation performance in terms of data diversity. It is also confirmed that the generated data is closer to the real fault data than the simulated data.

참고문헌 (Reference)

1 L. Van der Maaten, "Visualizing data using t-SNE" 9 (9): 2579-2605, 2008

2 A. Abdullah, "Ultrafast transmission line fault detection using a DWT-based ANN" 54 (54): 1182-1193, 2017

3 H. Liang, "Transmission line fault-cause identification method for large-scale new energy grid connection scenarios" 5 (5): 362-374, 2022

4 A. Mukherjee, "Transmission line fault classification under high noise in signal : a direct PCA-threshold-based approach" 103 : 197-211, 2021

5 K. M. Song, "Transmission Line Fault Cause Modeling and Waveform Analysis" 2023

6 L. Yang, "Simulation on HVDC Actual Fault and Analysis of Simulation Reliability" 789-793, 2021

7 R. Kuffel, "RTDS-A Fully Digital Power System Simulator Operation in Real Time" 2 : 19-24, 1995

8 A. Torfi, "On the evaluation of generative adversarial networks by discriminative models" IEEE 991-998, 2021

9 김태근 ; 임세헌 ; 송경민 ; 윤성국, "LSTM-based Fault Classification Model in Transmission Lines for Real Fault Data" 73 (73): 585-592, 2024

10 F. T. Liu, "Isolation forest" 413-422, 2008

11 I. Gulrajani, "Improved training of wasserstein gans" 30 : 2017

12 W. L. Liu, "High impedance fault diagnosis method based on conditional Wasserstein generative adversarial network" 1-6, 2021

13 I. Goodfellow, "Generative adversarial nets" 27 : 2014

14 M. Heusel, "Gans trained by a two time-scale update rule converge to a local nash equilibrium" 30 : 2017

15 K. Y. Lee, "GAN-based Generative Algorithm for Various Transmission Line Fault Data" 2024

16 X. Gao, "Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty" 396 : 487-494, 2020

17 A. Yadav, "An overview of transmission line protection by artificial neural network: fault detection, fault classification, fault location, and fault direction discrimination" 2014 (2014): 230382-, 2014

18 S. Barratt, "A note on the inception score"

19 A. Mukherjee, "A differential signal-based fault classification scheme using PCA for long transmission lines" 102 : 403-414, 2021

20 M. F. Guo, "A data-enhanced high impedance fault detection method under imbalanced sample scenarios in distribution networks" 59 (59): 4720-4733, 2023

21 Y. Xing, "A Physics-Informed Data-Driven Fault Location Method for Transmission Lines Using Single-Ended Measurements with Field Data Validation"

22 M. Pazoki, "A New Fault Classifier in Transmission Lines Using Intrinsic Time Decomposition" 14 (14): 619-628, 2018