Power System Transient Stability Preventive Control Optimization Method Driven by Stacking Ensemble Learning

doi:10.12096/j.2096-4528.pgt.22165

Abstract

Abstract:

Aiming at the contradiction between the rapidity requirement of online calculation of transient stability preventive control and the computational complexity of time-domain equations, a stacking ensemable learning driven optimization method for power system transient stability preventive control was proposed. Firstly, a transient stability estimator based on a stacking ensemble deep belief network was constructed to replace the nonlinear differential algebraic equation solution process required for transient stability determination. Secondly, the trained transient stability estimator was used as a transient stability constraint discriminator, which was embedded in the iterative optimization process of the Aptenodytes Forsteri optimization algorithm. Finally, with the goal of minimizing the cost of preventive control, a stacking ensemble learning driven power system transient stability preventive control optimization algorithm was established. The algorithm realized the efficient judgment of transient stability constraints in preventive control, and improved the decision-making level of preventive control for power generation rescheduling. Based on the IEEE39 bus system, the proposed preventive control method was verified by experiments. The results show that the method has achieved good results in both evaluation accuracy and calculation efficiency.

Key words: power system, stacking ensemble learning, Aptenodytes Forsteri optimization algorithm, transient stability, preventive control

CLC Number:

TM 712

Xiaojie PAN, Youping XU, Zhijun XIE, Yukun WANG, Mujie ZHANG, Mengxuan SHI, Kun MA, Wei HU. Power System Transient Stability Preventive Control Optimization Method Driven by Stacking Ensemble Learning[J]. Power Generation Technology, 2023, 44(6): 865-874.

Figures/Tables 13

Fig. 1 Schematic diagram of stacked ensemble learning

Fig. 2 Transient stability estimator model based on stacked ensemble DBN

Fig. 3 Model structure of SEDBN-AFO

Fig. 4 Calculation flow chart of transient stability preventive control algorithm

Tab. 1 Structure parameters of stacked ensemble DBN model

模型	隐藏层数	隐藏层单元的数目(自左到右)
DBN-1	3	64， 32， 16
DBN-2	4	128， 64， 32， 16
DBN-3	5	256， 128， 64， 32， 16
DBN-4	3	64， 32， 16
DBN-5	4	128， 64， 32， 16
DBN-6	5	256， 128， 64， 32， 16
DBN-7	3	64， 32， 16
DBN-8	4	128， 64， 32， 16
DBN-9	5	256， 128， 64， 32， 16
元学习器DBN	3	64， 32， 16

Fig. 5 Performance index results of transient stability evaluator

Tab. 2 Performance comparison of different models

模型	RF	SVM	CNN	SAE	集成DBN
识别准确率/%	89.92	93.16	95.70	96.34	98.31

Fig. 6 Performance comparison of stacked ensemble DBN transient stability estimator and each sub-estimator

Fig. 7 Fitness comparison results of different models

Fig. 8 Comparison of generator output before and after system preventive control

Tab. 3 Transient stability prevention and control cost

发电机编号	预防控制前出力/MW	预防控制后出力/MW	有功出力调整/MW	单位调节成本/美元	单机调节成本/美元	总调节成本/美元
1	249.57	255.03	5.46	1.0	5.46	127.52
2	687.28	668.87	-18.41	1.0	18.41
3	648.89	664.04	15.15	1.0	15.15
4	630.92	621.99	-8.93	0.5	4.47
5	507.13	497.29	-9.84	0.5	4.92
6	648.89	650.03	1.14	0.5	0.57
7	559.04	616.75	57.71	0.5	28.85
8	539.08	558.03	18.95	1.0	18.95
9	828.58	781.11	-47.47	0.5	23.74
10	998.29	984.29	-14.00	0.5	7.00

Fig. 9 Comparison of power angle curves of generators before and after preventive control of BUS4 and BUS3

Fig. 10 Comparison of power angle curves of generators before and after preventive control of BUS28 and BUS29

References 25

1	别朝红，林超凡，李更丰，等．能源转型下弹性电力系统的发展与展望[J]．中国电机工程学报，2020，40(9)：2735-2745．
	BIE Z H， LIN C F， LI G F，et al ．Development and prospect of resilient power system in the context of energy transition[J]．Proceedings of the CSEE，2020，40(9)：2735-2745．
2	申洪，周勤勇，刘耀，等．碳中和背景下全球能源互联网构建的关键技术及展望[J]．发电技术，2021，42(1)：8-19． doi:10.12096/j.2096-4528.pgt.20113
	SHEN H， ZHOU Q Y， LIU Y，et al ．Key technologies and prospects for the construction of global energy Internet under the background of carbon neutral[J]．Power Generation Technology，2021，42(1)：8-19． doi:10.12096/j.2096-4528.pgt.20113
3	申志鹏，熊会，朱介北，等．影响特高压直流输电工程安全高效运行评估因素集的建模与分析[J]．发电技术，2021，42(1)：48-59． doi:10.12096/j.2096-4528.pgt.20121
	SHEN Z P， XIONG H， ZHU J B，et al ．Modelling and analysis on evaluation factor sets affecting the safe and high-efficiency operation of UHVDC transmission project[J]．Power Generation Technology，2021，42(1)：48-59． doi:10.12096/j.2096-4528.pgt.20121
4	刘建锋，姚晨曦，陈乐乐．基于门控时空图神经网络的电力系统暂态稳定评估[J]．电力科学与技术学报，2023，38(2)：214-223．
	LIU J F， YAO C X， CHEN L L ．Power system transient stability assessment based on gating spatial temporal graph neural network[J]．Journal of Electric Power Science and Technology，2023，38(2)：214-223．
5	刘颂凯，胡竞哲，杨超，等．基于改进CDBN的电力系统暂态稳定评估[J]．智慧电力，2023，51(6)：8-14． doi:10.3969/j.issn.1673-7598.2023.06.002
	LIU S K， HU J Z， YANG C，et al ．Transient stability assessment of power systems based on improved CDBN[J]．Smart Power，2023，51(6)：8-14． doi:10.3969/j.issn.1673-7598.2023.06.002
6	章昊，田宏强，王磊，等．基于Seq2Seq技术的电力系统暂态稳定评估方法[J]．电网与清洁能源，2021，37(4)：23-31． doi:10.3969/j.issn.1674-3814.2021.04.004
	ZHANG H， TIAN H Q， WANG L，et al ．A power system transient stability assessment method based on Seq2Seq technology[J]．Power System and Clean Energy，2021，37(4)：23-31． doi:10.3969/j.issn.1674-3814.2021.04.004
7	胡伟，郑乐，闵勇，等．基于深度学习的电力系统故障后暂态稳定评估研究[J]．电网技术，2017，41(10)：3140-3146．
	HU W， ZHENG L， MIN Y，et al ．Research on power system transient stability assessment based on deep learning of big data technique[J]．Power System Technology，2017，41(10)：3140-3146．
8	张玮灵，胡伟，闵勇，等．稳定域概念下考虑保守性的电力系统在线暂态稳定评估方法[J]．电网技术，2016，40(4)：992-998．
	ZHANG W L， HU W， MIN Y，et al ．Conservative online transient stability assessment in power system based on concept of stability region[J]．Power System Technology，2016，40(4)：992-998．
9	周子涵，卜广全，马士聪，等．基于特征分离型神经网络的电力系统暂态稳定性评估与优化方法[J]．电网技术，2021，45(9)：3658-3667．
	ZHOU Z H， BU G Q， MA S C，et al ．Assessment and optimization of power system transient stability based on feature-separated neural networks[J]．Power System Technology，2021，45(9)：3658-3667．
10	KAMWA I， SAMANTARAY S R， JOOS G ．Development of rule-based classifiers for rapid stability assessment of wide-area post-disturbance records[J]．IEEE Transactions on Power Systems，2009，24(1)：258-270． doi:10.1109/tpwrs.2008.2009430
11	吴俊勇，张若愚，季佳伸，等．计及漏判/误判代价的两阶段电力系统暂态稳定预测方法[J]．电力系统自动化，2020，44(24)：44-52． doi:10.7500/AEPS20200521003
	WU J Y， ZHANG R Y， JI J S，et al ．Two-stage transient stability prediction method of power system considering cost of misdetection and false alarm[J]．Automation of Electric Power Systems，2020，44(24)：44-52． doi:10.7500/AEPS20200521003
12	邵美阳，吴俊勇，李宝琴，等．基于两阶段集成深度置信网络的电力系统暂态稳定评估[J]．电网技术，2020，44(5)：1776-1787．
	SHAO M Y， WU J Y， LI B Q，et al ．Transient stability assessment of power system based on two-stage ensemble deep belief network[J]．Power System Technology，2020，44(5)：1776-1787．
13	李欣，刘晨凯，郭攀锋，等．考虑拓扑变化的电力系统暂态稳定评估[J]．智慧电力，2021，49(12)：59-65． doi:10.3969/j.issn.1673-7598.2021.12.010
	LI X， LIU C K， GUO P F，et al ．Transient stability assessment of power system considering change in network topology[J]．Smart Power，2021，49(12)：59-65． doi:10.3969/j.issn.1673-7598.2021.12.010
14	李宝琴，吴俊勇，邵美阳，等．基于集成深度置信网络的精细化电力系统暂态稳定评估[J]．电力系统自动化，2020，44(6)：17-26． doi:10.7500/AEPS20190528009
	LI B Q， WU J Y， SHAO M Y，et al ．Refined transient stability evaluation for power system based on ensemble deep belief network[J]．Automation of Electric Power Systems，2020，44(6)：17-26． doi:10.7500/AEPS20190528009
15	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．
	TIAN F， ZHOU X X， SHI D Y，et al ．A preventive control method of power system transient stability based on a convolutional neural network[J]．Power System Protection and Control，2020，48(18)：1-8．
16	朱乔木，陈金富，李弘毅，等．基于堆叠自动编码器的电力系统暂态稳定评估[J]．中国电机工程学报，2018，38(10)：2937-2946．
	ZHU Q M， CHEN J F， LI H Y，et al ．Transient stability assessment based on stacked autoencoder[J]．Proceedings of the CSEE，2018，38(10)：2937-2946．
17	刘颂凯，袁铭洋，杨超，等．基于XGBoost和ASPSO的电力系统暂态稳定预防控制方法[J]．电网与清洁能源，2023，39(10)：9-18． doi:10.3969/j.issn.1674-3814.2023.10.002
	LIU S K， YUAN M Y， YANG C，et al ．A transient stability preventive control method of power systems based on XGBoost and ASPSO[J]．Power System and Clean Energy，2023，39(10)：9-18． doi:10.3969/j.issn.1674-3814.2023.10.002
18	孙景强，房大中，周保荣．基于轨迹灵敏度的电力系统动态安全预防控制算法研究[J]．电网技术，2004，28(21)：26-30． doi:10.3321/j.issn:1000-3673.2004.21.006
	SUN J Q， FANG D Z， ZHOU B R ．Study on preventive control algorithm for dynamic security of power systems based on trajectory sensitivity method[J]．Power System Technology，2004，28(21)：26-30． doi:10.3321/j.issn:1000-3673.2004.21.006
19	CAI H R， CHUNG C Y， WONG K P ．Application of differential evolution algorithm for transient stability constrained optimal power flow[J]．IEEE Transactions on Power Systems，2008，23(2)：719-728． doi:10.1109/tpwrs.2008.919241
20	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．
	YANG Y， LIU Y B， LIU J Y，et al ．Preventive transient stability control based on neural network security predictor[J]．Power System Technology，2018，42(12)：4076-4084．
21	周艳真，吴俊勇，冀鲁豫，等．基于两阶段支持向量机的电力系统暂态稳定预测及预防控制[J]．中国电机工程学报，2018，38(1)：137-147．
	ZHOU Y Z， WU J Y， JI L Y，et al ．Two-stage support vector machines for transient stability prediction and preventive control of power systems[J]．Proceedings of the CSEE，2018，38(1)：137-147．
22	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
	SU T， LIU Y B， SHEN X D，et al ．Deep learning-driven evolutionary algorithm for preventive control of power system transient stability[J]．Proceedings of the CSEE，2020，40(12)：3813-3824． doi:10.13334/j.0258-8013.pcsee.191114
23	YANG Z， DENG L， WANG Y，et al ．Aptenodytes Forsteri optimization：algorithm and applications[J]．Knowledge-Based Systems，2021，232：107483． doi:10.1016/j.knosys.2021.107483
24	徐继伟，杨云．集成学习方法：研究综述[J]．云南大学学报(自然科学版)，2018，40(6)：1082-1092．
	XU J W， YANG Y ．A survey of ensemble learning approaches[J]．Journal of Yunnan University (Natural Sciences Edition)，2018，40(6)：1082-1092．
25	史佳琪，张建华．基于多模型融合Stacking集成学习方式的负荷预测方法[J]．中国电机工程学报，2019，39(14)：4032-4042． doi:10.13334/j.0258-8013.pcsee.181510
	SHI J Q， ZHANG J H ．Load forecasting based on multi-model by stacking ensemble learning[J]．Proceedings of the CSEE，2019，39(14)：4032-4042． doi:10.13334/j.0258-8013.pcsee.181510

[1]	Hongbo LIU, Shencheng LIU, Xueyang GAI, Yongfa LIU, Yutong YAN. Overview of Active Distribution Network Planning With High Proportion of New Energy Access [J]. Power Generation Technology, 2024, 45(1): 151-161.
[2]	Haoyong CHEN, Yuxiang HUANG, Yang ZHANG, Fei WANG, Liang ZHOU, Junbo TANG, Xiaobin WU. Architecture Design of Virtual Power Plant Based on “Three Flow Separation-Convergence” [J]. Power Generation Technology, 2023, 44(5): 616-624.
[3]	Bofei WANG, Haozhe XIAO, Guohao LI, Wenheng XIU, Yunhao MO, Mingjie ZHU, Zhen WU. A Review of Energy Management Strategy for Hydrogen-Electricity Hybrid Power System Based on Control Target [J]. Power Generation Technology, 2023, 44(4): 452-464.
[4]	Chunyan ZHANG, Zhenlan DOU, Jun WANG, Liangliang ZHU, Xiaotong SUN, Gendi LI. Development Route of Hydrogen Production by Water Electrolysis, Hydrogen Storage and Hydrogen Supply in Power System [J]. Power Generation Technology, 2023, 44(3): 305-317.
[5]	Hao WU, Xiao XU, Zinan PENG, Ninghui GUO, Qifeng WANG. Research on Electrical Equipment Big Data Mobile Laboratory Based on Power Grid Cloud Data Management and Its Application [J]. Power Generation Technology, 2023, 44(3): 417-424.
[6]	Jiangwu DU, Xiaoqiang TANG, Zhiwei LUO, Dunnan LIU, Jixu CHEN, Erfeng XU, Sheng BI. Pricing Method for Season of Use in Integrated Energy Park [J]. Power Generation Technology, 2023, 44(2): 261-269.
[7]	Xin YIN, Feng ZHANG, Balati ADILI, Xiqiang CHANG, Wuhui CHEN, Changjun LI, Xueming LI, Shaowei YUAN. Study on Participation of Electricity-driven Thermal Load in Real-time Scheduling of New Power System [J]. Power Generation Technology, 2023, 44(1): 115-124.
[8]	Chen DONG, Qiang WU, He HUANG, Rui ZHANG, Xiuyuan YANG. Power Grid Topology Identification Based on Immune Algorithm [J]. Power Generation Technology, 2023, 44(1): 125-135.
[9]	Qian GAO, Junyi YANG, Yu HONG, Xiaolei SUN, Qianjin ZHU, Tian YU, Xin WANG, Linyuan WANG, Zesen LI. Research on Digital Transformation Architecture and Path of Power Grid Development Planning Business Under New Power System Blueprint [J]. Power Generation Technology, 2022, 43(6): 851-859.
[10]	Jianlin LI, Ziyang DING, Haitao LIU, Hang YANG. Research on Grid-Forming Energy Storage Converters and Control Strategies [J]. Power Generation Technology, 2022, 43(5): 679-686.
[11]	Zehang LI, Hao ZHOU, Haomiao LI, Kangli WANG, Kai JIANG. Liquid Metal Battery Energy Storage Technology for Power System [J]. Power Generation Technology, 2022, 43(5): 760-774.
[12]	Rui DONG, Lin GAO, Song HE, Dongtai YANG. Significance and Challenges of CCUS Technology for Low-carbon Transformation of China’s Power Industry [J]. Power Generation Technology, 2022, 43(4): 523-532.
[13]	Ziwen FENG, Yongli ZHU. Generation Method of Substation Switching Operation Ticket Based on Finite State Machine [J]. Power Generation Technology, 2022, 43(3): 501-509.
[14]	Chao HUANG, Siqi BU, Qiyu CHEN, Hiu Hung LEE. Meta-Power: Next-Generation Smart Grid [J]. Power Generation Technology, 2022, 43(2): 287-304.
[15]	Bowen ZHOU, Chao XI, Guangdi LI, Bo YANG. Metaverse Application in Power Systems [J]. Power Generation Technology, 2022, 43(1): 1-9.