基于长短期记忆网络的电网同调机群快速辨识

doi:10.11985/2022.02.023

摘要/Abstract

摘要：

基于长短期记忆网络(Long short-term memory,LSTM)提出了一种电网同调机群的快速辨识方法。首先针对两机振荡模型,挖掘相量平面内电压相量轨迹的分类特性,为机组的同调性辨识提供了依据;其次,基于短时响应数据,利用LSTM分别对机端电压实、虚部时序轨迹进行预测,并依据复合而成的相量轨迹判断机组的分群情况;最后,利用扩展等面积法则(Extended equal area criterion,EEAC)对上述分群情况进行验证,进而给出同调机群的最终辨识结果。IEEE-39节点系统算例验证了方法的有效性,具有较好的工程应用价值。

关键词: 同调机群辨识, 电压相量轨迹, 长短期记忆网络(LSTM), 扩展等面积法则(EEAC)

Abstract:

Based on the long short-term memory network(LSTM), a fast prediction method of coherent generators is proposed. Firstly, the classification characteristics of bus voltage phase trajectories are extracted to provide a new way for the identification of generator coherency. Secondly, based on the short-term response data, the real and imaginary parts of the generator terminal voltage phase are predicted respectively by using LSTM, and the coherent generators are identified based on the fitted voltage phase trajectories. Finally, the extended equal area criterion(EEAC) is used to further verify the coherency of the identified generator groups. The proposed method is validated used in the IEEE-39 bus system, and the simulation results show that the method has the advantages of higher engineering practice value.

Key words: Coherent generator identification, voltage phase trajectory, long short-term memory network(LSTM), extended equal area criteria(EEAC)

中图分类号:

TM561

毛煜, 尚海昆, 于卓琦. 基于长短期记忆网络的电网同调机群快速辨识[J]. 电气工程学报, 2022, 17(2): 201-207.

MAO Yu, SHANG Haikun, YU Zhuoqi. A Fast Prediction Method of Coherent Generators Based on Long Short-term Memory Network[J]. Journal of Electrical Engineering, 2022, 17(2): 201-207.

图/表 14

图1

图2

图3

图4

图5

图6

图7

表1

图8

表2

图9

图10

图11

图12

参考文献 18

[1]	李明节, 陈国平, 董存, 等. 新能源电力系统电力电量平衡问题研究[J]. 电网技术, 2019, 43(11):3979-3986.
	LI Mingjie, CHEN Guoping, DONG Cun, et al. Research on power balance of high proportion renewable energy system[J]. Power System Technology, 2019, 43(11):3979-3986.
[2]	马世英, 朱存浩, 郑超, 等. 扩展相轨迹特征解析及暂态稳定判别方法研究[J]. 中国电机工程学报, 2020, 40(20):6516-6527.
	MA Shiying, ZHU Cunhao, ZHENG Chao, et al. Analysis of extended phase trajectory characteristics and transient stability identification[J]. Proceedings of the CSEE, 2020, 40(20):6516-6527.
[3]	安军, 穆钢, 徐炜彬. 基于主成分分析法的电力系统同调机群识别[J]. 电网技术, 2009, 33(3):25-28.
	AN Jun, MU Gang, XU Weibin. Recognition of power system coherent generators based on principal component analysis[J]. Power System Technology, 2009, 33(3):25-28.
[4]	王旭东, 林济铿, 李胜文, 等. 电力孤岛划分研究综述[J]. 电力系统自动化, 2013, 37(22):125-135.
	WANG Xudong, LIN Jikeng, LI Shengwen, et al. Review of research on island partitioning in power grid[J]. Automation of Electric Power Systems, 2013, 37(22):125-135.
[5]	戴晨松, 薛峰, 薛禹胜. 受扰轨迹的分群研究[J]. 电力系统自动化, 2000, 24(1):13-16.
	DAI Chensong, XUE Feng, XUE Yusheng. Classification of disturbed trajectories[J]. Automation of Electric Power Systems, 2000, 24(1):13-16.
[6]	李莉, 刘玉田. 基于同调分群和自适应判据的失步解列策略[J]. 山东大学学报, 2007, 37(6):49-53.
	LI Li, LIU Yutian. Out-of-step splitting scheme based on coherency identification and self-adaptive power system separation criteria[J]. Journal of Shandong University, 2007, 37(6):49-53.
[7]	倪敬敏, 沈沉, 谭伟, 等. 一种基于非平衡点处线性化的同调识别方法[J]. 电力系统自动化, 2010, 34(20):7-12.
	NI Jingmin, SHEN Chen, TAN Wei, et al. A coherence identifying based on linearization at Non-equilibrium point[J]. Automation of Electric Power Systems, 2010, 34(20):7-12.
[8]	夏成军, 周良松, 彭波, 等. 基于Epsilon分解的发电机同调识别新方法[J]. 电力系统自动化, 2000(24):30-33,37.
	XIA Chengjun, ZHOU Liangsong, PENG Bo, et al. A new method for coherency recognition of generator using Epsilon decomposition[J]. Automation of Electric Power Systems, 2000(24):30-33,37.
[9]	宋洪磊, 吴俊勇, 冀鲁豫. 基于慢同调理论和希尔伯特-黄变换的发电机在线同调识别[J]. 电力自动化设备, 2013, 37(8):70-76.
	SONG Honglei, WU Junyong, JI Luyu. Online identification of coherent generators based on slow coherency theory and Hilbert-Huang transform[J]. Electric Power Automation Equipment, 2013, 37(8):70-76.
[10]	文俊, 刘天琪, 李兴源, 等. 在线识别同调机群的优化支持向量机算法[J]. 中国电机工程学报, 2008, 28(25):80-85.
	WEN Jun, LIU Tianqi, LI Xingyuan, et al. On-line identification of coherent generator using optimized LS-SVM[J]. Proceedings of the CSEE, 2008, 28(25):80-85.
[11]	黄夏楠. 基于能量传输函数的电力系统暂态稳定评估及控制策略研究[D]. 北京: 中国电力科学研究院, 2018.
	HUANG Xianan. Study on power system transient stability assessment and control strategy based on energy transfer function[D]. Beijing: China Electric Power Research Institute, 2018.
[12]	冯康恒, 张艳霞, 刘志雄, 等. 基于广域信息的同调机群在线识别方法[J]. 电网技术, 2014, 38(8):2082-2086.
	FENG Kangheng, ZHANG Yanxia, LIU Zhixiong, et al. A wide area information based online recognition of coherent generators in power system[J]. Power System Technology, 2014, 38(8):2082-2086.
[13]	史坤鹏, 穆钢, 李婷, 等. 基于经验模式分解的聚类树方法及其在同调机组分群中的应用[J]. 电网技术, 2007, 31(22):21-25.
	SHI Kunpeng, MU Gang, LI Ting, et al. Empirical mode decomposition based clustering-tree method and its application in coherency identification of generating sets[J]. Power System Technology, 2007, 31(22):21-25.
[14]	李宗翰, 张东霞, 刘道伟, 等. 基于电压矢量矢端轨线的电网主动解列断面快速定位方法[J]. 中国电机工程学报, 2020, 40(3):701-713.
	LI Zonghan, ZHANG Dongxia, LIU Daowei, et al. Rapid location method of controlled splitting sections for power grid based on the voltage vector portraits[J]. Proceedings of the CSEE, 2020, 40(3):701-713.
[15]	俞嘉晨, 李宗翰, 刘道伟, 等. 基于短时电压相量轨迹的同调机群快速预估方法[J]. 中国电机工程学报, 2021, 41(8):2705-2716.
	YU Jiachen, LI Zonghan, LIU Daowei, et al. A fast prediction method for coherent generators based on short-time voltage phase trajectories[J]. Proceedings of the CSEE, 2021, 41(8):2705-2716.
[16]	陶晓峰, 吕朋朋, 缪平, 等. 基于深度神经网络的工单采集模型研究[J]. 自动化与仪器仪表, 2020(2):39-42,46.
	TAO Xiaofeng, LÜ Pengpeng, MIAO Ping, et al. Intelligent work order collection system based on deep neural network[J]. Automation and Instrumentation, 2020(2):39-42,46.
[17]	薛禹胜. 运动稳定性量化理论——非自治非线性多刚体系统的稳定性分析[M]. 南京: 江苏科技出版社, 1999.
	XU Yusheng. Quantitative study of general motion stability and an example of power system stability[M]. Nanjing: Jiangsu Science and Technology Press, 1999.
[18]	张保会, 杨松浩, 王怀远. 电力系统暂态稳定性闭环控制(二)——多机电力系统暂态不稳定判别方法[J]. 电力自动化设备, 2014(34):1-6.
	ZHAO Baohui, YANG Songhao, WANG Huaiyuan. Closed-loop control of power system transient stability(2):Transient instability detection method of multi-machine power system[J]. Electric Power Automation Equipment, 2014(34):1-6.

暂态稳定裕度	同调辨识结果
η≥1	S和A具有强同调性
η<1	S和A分为两群

神经元参数	描述
激活函数	sigmoid
权值初始化	正态
损失函数	方均根误差函数
优化算法	RMSProp
Batchsize	15