Online Evaluation Method for Low Frequency Oscillation Stability in a Power System Based on Improved XGboost

Wenping Hu, Jifeng Liang, Yitao Jin, Fuzhang Wu, Xiaowei Wang and Ersong Chen
Additional contact information
Wenping Hu: State Grid Hebei Electric Power Co., Ltd., Technology Research Institute, Shijiazhuang 050021, China
Jifeng Liang: State Grid Hebei Electric Power Co., Ltd., Technology Research Institute, Shijiazhuang 050021, China
Yitao Jin: School of Electrical Engineering, Wuhan University, Wuhan 430072, China
Fuzhang Wu: School of Electrical Engineering, Wuhan University, Wuhan 430072, China
Xiaowei Wang: State Grid Hebei Electric Power Co., Ltd., Technology Research Institute, Shijiazhuang 050021, China
Ersong Chen: State Grid Hebei Electric Power Co., Ltd., Technology Research Institute, Shijiazhuang 050021, China

Energies, 2018, vol. 11, issue 11, 1-18

Abstract: Low frequency oscillation in an interconnected power system is becoming an increasingly serious problem. It is of great practical significance to make online evaluation of actual power grid’s stability. To evaluate the stability of the power system quickly and accurately, a low frequency oscillation stability evaluation method based on an improved XGboost algorithm and power system random response data is proposed in this paper. Firstly, the original input feature set describing the dynamic characteristics of the power system is established by analyzing the substance of low frequency oscillation. Taking the random response data of power system including the disturbance end time feature and the dynamic feature of power system as the input sample set, the wavelet threshold is applied to improve its effectiveness. Secondly, using the eigenvalue analysis method, different damping ratios are selected as threshold values to judge the stability of the system low-frequency oscillation. Then, the supervised training with improved XGboost algorithm is performed on the characteristics of stability. On this basis, the training model is obtained and applied to online low frequency oscillation stability evaluation of a power system. Finally, the simulation results of the eight-machine 36-node test system and Hebei southern power grid show that the proposed low frequency oscillation online evaluation method has the features of high evaluation accuracy, fast evaluation speed, low error rate of unstable sample evaluation, and strong anti-noise ability.

Keywords: random response data; low frequency oscillation stability; online evaluation; improved XGboost algorithm (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2018
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/1996-1073/11/11/3238/pdf (application/pdf)
https://www.mdpi.com/1996-1073/11/11/3238/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:11:y:2018:i:11:p:3238-:d:184563

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().