Transient stability assessment method of electric power systems based on stacked variational auto-encoder

被引：0
|
作者：
Wang H. [1 ]
Chen Q. [1 ]
机构：
[1] College of Electrical Engineering and Automation, Fuzhou University, Fuzhou
来源：
Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2019年 / 39卷 / 12期
关键词：
Cha-racteristic quantities; Deep learning; Electric power systems; Noise immunity; Stability; Stacked variational auto-encoder; Transient analysis;
D O I：
10.16081/j.epae.201911032
中图分类号：
学科分类号：
摘要：
From the two aspects of model construction and characteristic quantities extraction, a transient stability discriminant model with better noise immunity is proposed. A stacked variational auto-encoder is adopted to construct the assessment model. Besides, a L2 regularization method is introduced in the trai-ning process, which enhances the generalization ability of the stability discriminant model. Meanwhile, the characteristic quantities extraction time of the proposed method is different from the traditional method. By setting the threshold of the maximum power angle difference of all generators, when the system develops to the threshold, the characteristic quantities extraction is carried out. The simulative results based on IEEE 39-bus system show that the miscalculation of the stability assessment model is greatly reduced with the proposed characteristic quantities extraction method. Meanwhile the reasonable threshold will not affect the start of real-time control methods, and the noise immunity ability of the model can be also strengthened. © 2019, Electric Power Automation Equipment Press. All right reserved.
引用
收藏
页码：134 / 139
页数：5
相关论文
共 17 条
  • [1] Tian F., Zhou X., Yu Z., Optimization method of transient stability preventive control based on sensitivity analysis and time domain simulation, Electric Power Automation Equipment, 38, 7, pp. 155-161, (2018)
  • [2] Yang S., Wang H., Su F., Et al., Analysis and comparison of transient instability detection methods based on convexity and concavity of phase trajectory, Electric Power Automation Equipment, 37, 9, pp. 193-198, (2017)
  • [3] Feng L., Cai Z., Wang Y., Et al., Impact of DFIG LVRT characteristics on transient stability of power system, Electric Power Automation Equipment, 38, 3, pp. 16-23, (2018)
  • [4] Su F., Yang S., Wang H., Et al., Study on fast termination algorithm of time-domain simulation for power system transient stability, Proceedings of the CSEE, 37, 15, pp. 4372-4378, (2017)
  • [5] Tang Y., Response-based wide area control for power system security and stability, Proceedings of the CSEE, 34, 29, pp. 5041-5050, (2014)
  • [6] Bhui P., Senroy N., Real-time prediction and control of transient stability using transient energy function, IEEE Transactions on Power Systems, 32, 2, pp. 923-934, (2017)
  • [7] Muyeen S.M., Hasanien H.M., Al-Durra A., Transient stability enhancement of wind farms connected to a multi-machine power system by using an adaptive ANN-controlled SMES, Energy Conversion & Management, 78, 1, pp. 412-420, (2014)
  • [8] Rahmatian M., Chen Y.C., Palizban A., Et al., Transient stability assessment via decision trees and multivariate adap-tive regression splines, Electric Power Systems Research, 142, pp. 320-328, (2017)
  • [9] Houben I., Wehenkel L., Pavella M., Coupling of K-NN with decision trees for power system transient stability assessment, International Conference on Control Applications, pp. 825-832, (1995)
  • [10] Zhou Y., Wu J., Ji L., Et al., Transient stability preventive con-trol of power systems using chaotic particle swarm optimi-zation combined with two-stage support vector machine, Electric Power Systems Research, 155, pp. 111-120, (2018)
12