Maximum Frequency Deviation Prediction Method Considering Frequency Deviation Distribution and Penalty Cost

被引：0

作者：

Huang M. ^{[1
]}

Wen Y. ^{[1
]}

Gou J. ^{[2
]}

Jiang H. ^{[3
]}

Xu W. ^{[2
]}

Li T. ^{[2
]}

机构：

[1] College of Electrical and Information Engineering, Hunan University, Changsha

[2] Economic Research Institute of State Grid Sichuan Electric Power Company, Chengdu

[3] Global Energy Interconnection Group Co., Ltd., Beijing

来源：

Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2021年 / 45卷 / 23期

基金：

中国国家自然科学基金;

关键词：

Cascaded light gradient boosting machine (CasLightGBM); Frequency deviation; Multi-source information fusion; Penalty cost;

D O I：

10.7500/AEPS20210305006

中图分类号：

学科分类号：

摘要：

Current data-driven maximum frequency deviation prediction methods for power systems ignore the effect of uneven sample distribution on the maximum frequency deviation, and its prediction accuracy can be further improved. To this end, this paper proposes a maximum frequency deviation prediction method considering the frequency deviation distribution and penalty cost. To avoid the dimensional explosion problem, the multi-source information fusion method is used to extract key input feature subsets from power system operation information. Then, a cascaded light gradient boosting machine (CasLightGBM) is constructed, and a punishment sensitivity mechanism is embedded into its loss function, which helps CasLightGBM automatically correct the sample loss value in training according to the probability distribution of frequency deviation samples and the penalty cost of conservative prediction. Simulation results based on the IEEE 118-bus test system show that the proposed method has excellent prediction accuracy and anti-noise performance. © 2021 Automation of Electric Power Systems Press.

引用

页码：51 / 59

页数：8

共 23 条

[1] GOLPIRA H, SEIFI H, MESSINA A R, Et al., Maximum penetration level of micro-grids in large-scale power systems: frequency stability viewpoint, IEEE Transactions on Power Systems, 31, 6, pp. 5163-5171, (2016)
[2] ZHANG Zhiqiang, YUAN Rongxiang, XU Youping, Et al., Optimization of over-frequency generator-tripping scheme in Sichuan power grid adaptable to multi-UHVDC transmission project, Automation of Electric Power Systems, 40, 2, pp. 141-146, (2016)
[3] CHANG Yekui, LI Weidong, BA Yu, Et al., A new method for frequency control performance assessment on operation security, Transactions of China Electrotechnical Society, 34, 6, pp. 1218-1229, (2019)
[4] WEN Yunfeng, YANG Weifeng, WANG Ronghua, Et al., Review and prospect of toward 100% renewable energy power systems, Proceedings of the CSEE, 40, 6, pp. 1843-1856, (2020)
[5] LI Weidong, JIN Cuicui, WEN Kerui, Et al., Active frequency response control under high-power loss, Automation of Electric Power Systems, 42, 8, pp. 22-30, (2018)
[6] LIU Ketian, ZHANG Jun, LI Jun, Et al., Power deficit calculation and under frequency load shedding strategy based on the frequency deviation area, Transactions of China Electrotechnical Society, 36, 5, pp. 1040-1051, (2021)
[7] LI M, MCCALLEY J D., Influence of renewable integration on frequency dynamics, 2012 IEEE Power and Energy Society General Meeting, (2012)
[8] SHI Q X, LI F X, CUI H T., Analytical method to aggregate multi-machine SFR model with applications in power system dynamic studies, IEEE Transactions on Power Systems, 33, 6, pp. 6355-6367, (2018)
[9] WEN Yunfeng, YANG Weifeng, LIN Xiaohuang, Review and prospect of frequency stability analysis and control of low-inertia power systems, Electric Power Automation Equipment, 40, 9, pp. 211-222, (2020)
[10] LIU Shengyuan, LIN Zhenzhi, LI Jincheng, Et al., Review and prospect of situation awareness technologies of power system, Automation of Electric Power Systems, 44, 3, pp. 229-239, (2020)

← 1 2 3 →