Elastic Net Based Online Assessment of Power System Transient Stability Margin

被引：0
|
作者：
Mi D. [1 ]
Wang T. [1 ]
Xiang Y. [1 ]
Du W. [1 ]
机构：
[1] State Key Laboratory of Alternate Electric Power Systems With New Energy Resources, North China Electric Power University, Changping District, Beijing
来源：
Dianwang Jishu/Power System Technology | 2020年 / 44卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Elastic Net; Feature selection; Online assessment; Transient stability margin;
D O I：
10.13335/j.1000-3673.pst.2019.0687
中图分类号：
TM614 [风能发电];
学科分类号：
0807 ;
摘要：
With expansion of power system and continuous proliferation of renewable energy generation, the transient stability characteristics of power system become more complicated, and online transient stability margin assessment faces severe challenges. This paper proposes a new method based on Elastic Net for online evaluation of power system transient stability margin. Instead of calculated features, the measurement data before fault were employed as inputs. The system steady-state bus voltage amplitude and phase angle are taken as sample features. Then the Elastic Net algorithm is used to complete the feature selection and construct a mapping relationship between measurement data and critical clear time. The original features are further mapped to a high dimensional space to improve accuracy of the prediction model. Finally, fast prediction of the transient stability margin based on the steady state operating information of the system is achieved. Case study on New England 39-bus system connected to wind farm and IEEE 118-bus system shows that the proposed approach can effectively select features and has high prediction accuracy through a small amount of data training. © 2020, Power System Technology Press. All right reserved.
引用
收藏
页码：19 / 26
页数：7
相关论文
共 20 条
  • [1] Zhu S., Liu K., Qin L., Et al., Analysis of transient stability of power electronics dominated power system: an overview, Proceedings of the CSEE, 37, 14, (2017)
  • [2] Jiang Q., Liu T., Zeng X., Et al., Affecting mechanism of large-scale wind power and DC integrated effect on transient stability of transmitting system, Power System Technology, 42, 7, pp. 2038-2046, (2018)
  • [3] Liang Z., Ge R., Dong Y., Et al., Analysis of large-scale blackout occurred on July 30 and July 31, 2012 in India and Its lessons to China's power grid dispatch and operation, Power System Technology, 37, 7, pp. 1841-1848, (2013)
  • [4] Xue Y., Lai Y., The fusion of big energy thinking and big data thinking(1)big data and power big data, Automation of Electric Power System, 40, 1, pp. 1-8, (2016)
  • [5] Al-Masri A.N., Kadir M.Z.A.A., Hizam H., Et al., A novel implementation for generator rotor angle stability prediction using an adaptive artificial neural network application for dynamic security assessment, IEEE Transactions on Power Systems, 28, 3, pp. 2516-2525, (2013)
  • [6] Yao D., Jia H., Zhao S., Power system transient stability assessment and margin prediction based on combined neural network, Automation of Electric Power System, 37, 20, pp. 41-46, (2013)
  • [7] Yang Y., Liu Y., Liu J., Et al., Transient stability prevention control based on neural network prediction and calibration, Power System Technology, 42, 12, pp. 4076-4084, (2018)
  • [8] An J., Ai S., Liu D., Et al., A method for power system transient stability assessment based on short-time disturbed trajectory, Power System Technology, 43, 5, pp. 1690-1697, (2019)
  • [9] Amraee T., Ranjbar S., Transient instability prediction using decision tree technique, IEEE Transactions on Power Systems, 28, 3, pp. 3028-3037, (2013)
  • [10] Shi F., Zhang L., Hu X., Et al., Power system transient stability rules extraction based on multi-attribute decision tree, Transactions of China Electrotechnical Society, pp. 1-12
12