Power System Transient Stability Rules Extraction Based on Multi-Attribute Decision Tree

被引：0
|
作者：
Shi F. [1 ]
Zhang L. [1 ]
Hu X. [2 ]
Yu Z. [3 ]
Zhang H. [1 ]
机构：
[1] The Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education, Shandong University, Ji'nan
[2] State Grid Jiangxi Electric Power Co. Ltd, Nanchang Power Supply Branch, Nanchang
[3] China Electric Power Research Institute, Beijing
来源：
Diangong Jishu Xuebao/Transactions of China Electrotechnical Society | 2019年 / 34卷 / 11期
关键词：
Association rules; Decision tree; Linear discriminant analysis; Mutual information; Transient stability margin;
D O I：
10.19595/j.cnki.1000-6753.tces.180648
中图分类号：
学科分类号：
摘要：
With the development of the renewable energy generation and the AC-DC hybrid interconnected power grid, the operation and dispatching mode of the power grid is more complex and changeable. The traditional dispatch and control method based on online computer-assisted decision support and artificial experience is no longer suitable for the up-to-date power grid. In this paper, a multi-attribute decision tree is proposed based on transient stability margin index. The mutual information is used to primarily analyze the electrical variables. Then linear discriminant analysis is applied to get the best the projection of the selected attributes, from which the combination feature of attributes can be get. The decision tree is constructed after the discretization of the transient stability margins under some specified faults, then the general rules for evaluating the stability of the system are achieved. The operation mode adjustment strategies for improving the system stability are obtained through the backward analysis of the decision tree. Finally, the IEEE-39 node test system is used to verify the correctness and effectiveness of the proposed method. © 2019, Electrical Technology Press Co. Ltd. All right reserved.
引用
收藏
页码：2364 / 2374
页数：10
相关论文
共 27 条
  • [1] Yu Z., Huang Y., Lu G., Et al., A time series associative classification method for the operation rule extracting of transient stability, Proceedings of the CSEE, 35, 3, pp. 519-526, (2015)
  • [2] Chen H., Wang C., Jiang T., Et al., Transient stability assessment in bulk power grid using projection energy function and support vector machine with pinball loss, Transactions of China Electrotechnical Society, 32, 11, pp. 67-76, (2017)
  • [3] Zhao J., Deng H., Wu X., Et al., Review on power system transient stability control technologies based on PMU/WAMS, Power System Protection and Control, 44, 5, pp. 1-9, (2016)
  • [4] Shen X., Shu H., Cao M., Et al., Risk assessment and research of dynamic stability for large-scale interconnected grids and its application, Transactions of China Electrotechnical Society, 31, pp. 230-238, (2016)
  • [5] Liu S., Yang H., An X., Fast simulation algorithm for power system transient stability based on a new predictor-corrector strategy, Power System Protection and Control, 45, 14, pp. 32-37, (2017)
  • [6] Li Y., Li G., Gu X., Et al., Transient stability assessment of power systems based on ensemble OS-ELM, Transactions of China Electrotechnical Society, 30, 14, pp. 412-418, (2015)
  • [7] Tian F., Zhou X., Yu Z., Power system transient stability assessment based on comprehensive SVM classification model and key sample set, Power System Protection and Control, 45, 22, pp. 1-8, (2017)
  • [8] Huang Y., Yu Z., Xie C., Et al., Study on the application of electric power big data technology in power system simulation, Proceedings of the CSEE, 35, 1, pp. 13-22, (2015)
  • [9] Xue Y., Lai Y., Integration of macro energy thinking and big data thinking part one big data and power big data, Automation of Electric Power Systems, 40, 1, pp. 1-8, (2016)
  • [10] Xue Y., Lai Y., Integration of macro energy thinking and big data thinking part two applications and explorations, Automation of Electric Power Systems, 40, 8, pp. 1-13, (2016)
123