Journal of Modern Power Systems and Clean Energy

ISSN 2196-5625 CN 32-1884/TK

Data-driven Transient Stability Assessment Based on Kernel Regression and Distance Metric Learning
Author:
Affiliation:

1.Department of Electrical Engineering, Tsinghua University, Beijing 100084, China;2.State Grid Jibei Electric Power Company, Beijing 100053, China;3.State Grid Corporation of China, Beijing 100031, China

Fund Project:

This work was supported by National Key R&D Program of China (No. 2018YFB0904500) and State Grid Corporation of China.

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
    Abstract:

    Transient stability assessment (TSA) is of great importance in power systems. For a given contingency, one of the most widely-used transient stability indices is the critical clearing time (CCT), which is a function of the pre-fault power flow. TSA can be regarded as the fitting of this function with the pre-fault power flow as the input and the CCT as the output. In this paper, a data-driven TSA model is proposed to estimate the CCT. The model is based on Mahalanobis-kernel regression, which employs the Mahalanobis distance in the kernel regression method to formulate a better regressor. A distance metric learning approach is developed to determine the problem-specific distance for TSA, which describes the dissimilarity between two power flow scenarios. The proposed model is more accurate compared to other data-driven methods, and its accuracy can be further improved by supplementing more training samples. Moreover, the model provides the probability density function of the CCT, and different estimations of CCT at different conservativeness levels. Test results verify the validity and the merits of the method.

    表 2 Table 2
    图1 An illustration of Mahalanobis distance.Fig.1
    图2 Flowchart of proposed method.Fig.2
    图3 Single-line diagram of SMIB system.Fig.3
    图4 CCT with original and transformed features. (a) Original features. (b) Transformed features.Fig.4
    图5 Single-line diagram of IEEE 10M39B system.Fig.5
    图6 Frequency density of Em with different methods.Fig.6
    图11 Accuracy versus training time.Fig.11
    表 1 Table 1
    Reference
    Related
    Cited by
Get Citation
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:August 23,2019
  • Revised:
  • Adopted:
  • Online: January 22,2021
  • Published: