基于深度极限学习机的暂态稳定预防控制方法

doi:10.16088/j.issn.1001-6600.2024071802

广西师范大学学报（自然科学版） ›› 2025, Vol. 43 ›› Issue (5): 64-74.doi: 10.16088/j.issn.1001-6600.2024071802

基于深度极限学习机的暂态稳定预防控制方法

刘颂凯^1,2, 曾羽聪^1,2, 张磊^1,2*, 李彦彰³, 王秋杰^1,2, 刘龙成^1,2, 陈萍^1,2, 赵文博^1,2

1.三峡大学电气与新能源学院,湖北宜昌 443002;
2.新能源微电网湖北省协同创新中心,湖北宜昌 443002;
3.国网湖北省电力有限公司武汉市供电公司,湖北武汉 430010

收稿日期:2024-07-18 修回日期:2024-11-04 出版日期:2025-09-05 发布日期:2025-08-05
通讯作者: 张磊(1986—),男,湖北鹤峰人,三峡大学副教授,博士。E-mail:leizhang0323@163.com
基金资助:
国家自然科学基金(52307109);湖北省自然科学基金(2022CFB825)

Transient Stability Preventive Control Method Based on Deep Extreme Learning Machine

LIU Songkai^1,2, ZENG Yucong^1,2, ZHANG Lei^1,2*, LI Yanzhang³, WANG Qiujie^1,2, LIU Longcheng^1,2, CHEN Ping^1,2, ZHAO Wenbo^1,2

1. College of Electrical Engineering and New Energy, China Three Gorges University, Yichang Hubei 443002, China;
2. Hubei Provincial Collaborative Innovation Center for New Energy Microgrid, Yichang Hubei 443002, China;
3. Wuhan Power Supply Company of State Grid Hubei Electric Power Co., Ltd, Wuhan Hubei 430010, China

Received:2024-07-18 Revised:2024-11-04 Online:2025-09-05 Published:2025-08-05

摘要/Abstract

摘要： 在电力系统暂态稳定预防控制中时域仿真计算复杂,同时系统存在样本不平衡问题,影响机器学习模型的性能。针对上述问题,本文提出一种基于深度极限学习机(deep extreme learning machine,DELM)的暂态稳定预防控制方法。首先采用过采样技术处理样本不平衡;然后利用DELM发现平衡数据集的潜在信息,建立电力系统运行特征和暂态稳定指标之间的映射模型,在预防控制中引入基于DELM的暂态稳定预测模型来代替暂态稳定约束最优潮流(transient stability constrained optimal power flow,TSCOPF)模型中含微分代数方程的暂态稳定约束,减少计算复杂度,并采用萤火虫算法对模型进行求解,获取最终策略;最后在IEEE 39节点系统进行仿真验证。结果表明,在预防故障发生时,本文所提的预防控制方法能够以2 042美元的优化调整成本实现系统暂态稳定性的提高,将暂态失稳的情况调节为稳定,且采用的萤火虫算法求解的计算时间可以控制在20 s以内,表明本文提出的基于DELM暂态稳定预防控制方法能够有效提升系统的暂态稳定性,且在具有较快的计算速度的同时具有良好的经济性。

关键词: 暂态稳定, 预防控制, 最优潮流, 样本不平衡, 深度极限学习机, 萤火虫算法

Abstract: In the transient stability prevention and control of power system, the time domain simulation calculation is complex, and there is a problem of sample class imbalance in the system, which affects the performance of machine learning model. To solve these problems, a transient stability prevention and control method based on deep extreme learning machine (DELM) is proposed. Firstly, the oversampling technique is used to deal with the unbalance of sample class. Then, DELM is used to discover the potential information of the balanced data set, and a mapping model between the operating parameters of the power system and the transient stability index is established. The transient stability prediction model based on DELM is introduced in preventive control to replace the transient stability constraint optimal power flow (TSCOPF) model containing differential algebraic equations with transient stability constraints, the computational complexity is reduced, and the model is solved by firefly algorithm to obtain the final strategy. Finally, the IEEE 39-node system is simulated and verified. The results show that the proposed preventive control method can improve the transient stability of the system at an optimal adjustment cost of \$2 042, adjust the transient instability to stability, and the calculation time of the firefly algorithm can be controlled within 20 s. This indicates that the transient stability prevention and control method based on DELM proposed in this paper can effectively improve the transient stability of the system, and has a fast calculation speed and good economy.

Key words: transient stability, preventive control, optimal power flow, sample imbalance, deep extreme learning machine, firefly algorithm

中图分类号: TM712;TP181

刘颂凯, 曾羽聪, 张磊, 李彦彰, 王秋杰, 刘龙成, 陈萍, 赵文博. 基于深度极限学习机的暂态稳定预防控制方法[J]. 广西师范大学学报（自然科学版）, 2025, 43(5): 64-74.

LIU Songkai, ZENG Yucong, ZHANG Lei, LI Yanzhang, WANG Qiujie, LIU Longcheng, CHEN Ping, ZHAO Wenbo. Transient Stability Preventive Control Method Based on Deep Extreme Learning Machine[J]. Journal of Guangxi Normal University(Natural Science Edition), 2025, 43(5): 64-74.

参考文献

[1] 谢培元, 袁文, 刘永刚, 等. 基于主动学习的电力系统暂态稳定评估方法[J]. 电测与仪表, 2021, 58(5): 86-91. DOI: 10.19753/j.issn1001-1390.2021.05.012.
[2] 鲁广明, 张璐路, 马晶, 等. 基于时序特征选择与改进MSPCA算法的电网暂态稳定态势智能评估[J]. 电测与仪表, 2023, 60(6): 125-133. DOI: 10.19753/j.issn1001-1390.2023.06.018.
[3] 焦瑞浩, 王震宇, 王克非, 等. 计及大规模风电并网的交直流电网连锁故障熵特征研究[J]. 电测与仪表, 2021, 58(7): 49-56. DOI: 10.19753/j.issn1001-1390.2021.07.007.
[4] 王杰, 彭志炜, 田宇, 等. 双馈风电机组故障穿越对系统暂态稳定的影响[J]. 电测与仪表, 2021, 58(5): 112-118. DOI: 10.19753/j.issn1001-1390.2021.05.016.
[5] ZENG H T, ZHOU Y Z, GUO Q L, et al. Distributed deep reinforcement learning-based approach for fast preventive control considering transient stability constraints[J]. CSEE Journal of Power and Energy Systems, 2023, 9(1): 197-208. DOI: 10.17775/CSEEJPES.2020.04610.
[6] 杨跃, 刘友波, 刘俊勇, 等. 基于神经网络预测校核的暂态稳定预防控制[J]. 电网技术, 2018, 42(12): 4076-4084. DOI: 10.13335/j.1000-3673.pst.2018.0421.
[7] 关慧哲, 陈颖, 黄少伟, 等. 基于生成对抗网络的暂态稳定预防控制[J]. 电力系统自动化, 2020, 44(24): 36-43.
[8] KITA H, NISHIYA K I, HASEGAWA J. On-line preventive control for power system transient stability based on the energy function method[J]. Electrical Engineering in Japan, 1991, 111(7): 30-39. DOI: 10.1002/eej.4391110704.
[9] 夏德明, 梅生伟, 沈沉, 等. 基于暂态稳定裕度指标的最优潮流求解[J]. 电力系统自动化, 2006, 30(24): 5-10. DOI: 10.3321/j.issn:1000-1026.2006.24.002.
[10] 刘明波, 阳曾. 含暂态能量裕度约束多故障最优潮流计算[J]. 中国电机工程学报, 2007, 27(34): 12-18. DOI: 10.3321/j.issn:0258-8013.2007.34.003.
[11] JIANG Q Y, HUANG Z G. An enhanced numerical discretization method for transient stability constrained optimal power flow[J]. IEEE Transactions on Power Systems, 2010, 25(4): 1790-1797. DOI: 10.1109/TPWRS.2010.2043451.
[12] 孙景强, 房大中, 锺德成. 暂态稳定约束下的最优潮流[J]. 中国电机工程学报, 2005, 25(12): 12-17. DOI: 10.3321/j.issn:0258-8013.2005.12.003.
[13] 阳育德, 韦化, 李滨. 求解暂态稳定约束最优潮流模型的递推降阶解耦算法[J]. 中国电机工程学报, 2015, 35(2): 335-343. DOI: 10.13334/j.0258-8013.pcsee.2015.02.010.
[14] 傅一苇, 陈磊, 马子明, 等. 含数据驱动型稳定约束的电力系统预防控制[J]. 中国电机工程学报, 2022, 42(15): 5417-5430. DOI: 10.13334/j.0258-8013.pcsee.213161.
[15] LIU C X, SUN K, RATHER Z H, et al. A systematic approach for dynamic security assessment and the corresponding preventive control scheme based on decision trees[C]// 2014 IEEE PES General Meeting | Conference & Exposition. Piscataway, NJ: IEEE, 2014: 1. DOI: 10.1109/PESGM.2014.6938856.
[16] TIAN F, ZHOU X X, YU Z H, et al. A preventive transient stability control method based on support vector machine[J]. Electric Power Systems Research, 2019, 170: 286-293. DOI: 10.1016/j.epsr.2019.01.030.
[17] 田芳, 周孝信, 史东宇, 等. 基于卷积神经网络的电力系统暂态稳定预防控制方法[J]. 电力系统保护与控制, 2020, 48(18): 1-8. DOI: 10.19783/j.cnki.pspc.191310.
[18] 潘晓杰, 徐友平, 解治军, 等. 堆栈式集成学习驱动的电力系统暂态稳定预防控制优化方法[J]. 发电技术, 2023, 44(6): 865-874.
[19] LIU T J, LIU Y B, LIU J Y, et al. A Bayesian learning based scheme for online dynamic security assessment and preventive control[J]. IEEE Transactions on Power Systems, 2020, 35(5): 4088-4099. DOI: 10.1109/TPWRS.2020.2983477.
[20] 苏童, 刘友波, 沈晓东, 等. 深度学习驱动的电力系统暂态稳定预防控制进化算法[J]. 中国电机工程学报, 2020, 40(12): 3813-3824. DOI: 10.13334/j.0258-8013.pcsee.191114.
[21] 卢锦玲, 张津. 考虑暂态稳定约束的电力系统最优潮流算法[J]. 电力系统保护与控制, 2017, 45(10): 24-30. DOI: 10.7667/PSPC160754.
[22] 杨健, 韦化, 覃秀君. 基于二阶正交配置法的暂态稳定约束最优潮流[J]. 中国电机工程学报, 2017, 37(1): 64-73. DOI: 10.13334/j.0258-8013.pcsee.151451.
[23] 田芳, 周孝信, 于之虹. 基于灵敏度分析和时域仿真的暂态稳定预防控制优化方法[J]. 电力自动化设备, 2018, 38(7): 155-161. DOI: 10.16081/j.issn.1006-6047.2018.07.021.
[24] 蒋仲安, 王佩, 施蕾蕾, 等. 基于低偏差序列的矿井供水管网可靠性[J]. 中南大学学报(自然科学版), 2014, 45(5):1686-1691. DOI:10.3969/j.issn.1003-6059.2011.02.007.
[25] 魏洁. 深度极限学习机的研究与应用[D]. 太原: 太原理工大学, 2016.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于深度极限学习机的暂态稳定预防控制方法

Transient Stability Preventive Control Method Based on Deep Extreme Learning Machine

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

Metrics

本文评价

推荐阅读 10

[1]	李欣, 宁静. 基于时空特征融合的电力系统暂态稳定评估[J]. 广西师范大学学报（自然科学版）, 2024, 42(6): 89-100.
[2]	许伦辉, 陈凯勋. 基于改进萤火虫算法优化BP神经网络的路网速度分布预测[J]. 广西师范大学学报（自然科学版）, 2019, 37(2): 1-8.
[3]	彭新建,翁小雄. 基于萤火虫算法优化BP神经网络的公交行程时间预测[J]. 广西师范大学学报（自然科学版）, 2017, 35(1): 28-36.