上海交通大学学报

上海交通大学学报 >

2019 , Vol. 53 >Issue 6: 749 - 756

DOI: https://doi.org/10.16183/j.cnki.jsjtu.2019.06.017

学报（中文）

基于极限学习机的电力系统暂态稳定评估方法

展开
  • 1. 山东大学 电气工程学院， 济南 250061； 2. 中国石油大学(华东) 信息与控制工程学院， 山东 青岛 266580； 3. 中国电力科学研究院有限公司， 北京 100192
张林林(1994-)，男，山东省德州市人，硕士生，从事配电网故障诊断研究.

网络出版日期: 2019-07-23

基金资助

山东省自然科学基金项目资助（ZR201808210126）

收起

Power System Transient Stability Assessment Based on Extreme Learning Machine

Expand
  • 1. School of Electrical Engineering, Shandong University, Jinan 250061, China; 2. College of Information and Control Engineering, China University of Petroleum (East China), Qingdao 266580, Shandong, China; 3. China Electric Power Research Institute, Beijing 100192, China

Online published: 2019-07-23

Fold

摘要

随着清洁能源替代和电力系统电力电子化的趋势增强，传统的基于理论模型的电力系统数值仿真方法将面临新的挑战，不依赖于元件模型的数据驱动型电网稳定评估方法逐渐受到重视.基于极限学习机(ELM)理论，提出适于在线应用的电力系统暂态稳定评估方法.首先，通过调节稳定和失稳仿真样本的比例进行样本筛选，减轻样本集中失稳样本较少而引起的样本不均衡现象，并引入递归特征消除法进一步处理样本集；然后利用交叉验证法优化ELM的网络结构，并用处理后的样本集进行ELM的训练；最后，根据神经网络的输出结果预测系统的稳定性，并改进泛化能力评价标准对结果的可靠性进行评估.算例分析表明，递归特征消除法可明显降低特征冗余度，改善模型性能，所提出算法的训练时间短且具有较高的预测准确度.

关键词： 电力系统； 暂态稳定； 极限学习机； 递归特征消除； 交叉验证

本文引用格式

张林林，胡熊伟，李鹏，石访，于之虹 . 基于极限学习机的电力系统暂态稳定评估方法[J]. 上海交通大学学报, 2019 , 53(6) : 749 -756 . DOI: 10.16183/j.cnki.jsjtu.2019.06.017

Abstract

With the enhanced trend of alternative clean energy and power electronics in power system, the traditional numerical simulation methods based on theoretical model will face new challenges, while the self-adaptive data-driven power system stability assessment method is gaining more and more attention. Based on the theory of extreme learning machine (ELM), a transient stability assessment method suitable for online application is proposed. Firstly, the samples are screened by adjusting the ratio of stable and unstable simulation samples, to reduce the sample imbalance in which unstable samples are far less than stable ones in the sample set, and the recursive feature elimination is used to further process the sample set. Then, the cross-validation is used to optimize the ELM network structure, and the processed sample set is used to train the ELM. Finally, the system stability based on the output of the neural network is predicted, and the reliability of the results with the improved evaluation criteria is evaluated. Test results show that the recursive feature elimination can significantly reduce the feature redundancy and improve the performance of the model, and the proposed algorithm has a shorter training time while can provide more accurate results.

Key words： power system; transient stability; extreme learning machine (ELM); recursive feature elimination; cross-validation

参考文献

［1］刘威, 张东霞, 王新迎, 等. 基于随机矩阵理论的电力系统暂态稳定性分析［J］. 中国电机工程学报, 2016, 36(18): 4854-4863. LIU Wei, ZHANG Dongxia, WANG Xinying, et al. Power system transient stability analysis based on random matrix theory ［J］. Proceedings of the CSEE, 2016, 36(18): 4854-4863. ［2］吴贵辉. 大力发展清洁能源推进电力可持续发展［J］. 电网与清洁能源, 2008, 24(3): 1-2. WU Guihui. Vigorous development of renewable energy promote continuous development of electricity ［J］. Power System and Clean Energy, 2008, 24(3): 1-2. ［3］徐心怡, 贺兴, 艾芊, 等. 基于随机矩阵理论的配电网运行状态相关性分析方法［J］. 电网技术, 2016, 40(3): 781-790. XU Xinyi, HE Xing, AI Qian, et al. A correlation analysis method for operation status of distribution network based on random matrix theory ［J］. Power System Technology, 2016, 40(3): 781-790. ［4］KATIRAEI F, IRAVANI R, HATZIARGYRIOU N, et al. Microgrids management ［J］. IEEE Power and Energy Magazine, 2008, 6(3): 54-65. ［5］吴茜, 张东霞, 刘道伟, 等. 基于随机矩阵理论的电网静态稳定态势评估方法［J］. 中国电机工程学报, 2016, 36(20): 5414-5420. WU Qian, ZHANG Dongxia, LIU Daowei, et al. A method for power system steady stability situation assessment based on random matrix theory ［J］. Proceedings of the CSEE, 2016, 36(20): 5414-5420. ［6］薛禹胜, 赖业宁. 大能源思维与大数据思维的融合(一)大数据与电力大数据［J］. 电力系统自动化, 2016, 40(1): 1-8. XUE Yusheng, LAI Yening. Integration of macro energy thinking and big data thinking. Part One. Big data and power big data ［J］. Automation of Electric Power Systems, 2016, 40(1): 1-8. ［7］薛禹胜, 赖业宁. 大能源思维与大数据思维的融合(二)应用及探索［J］. 电力系统自动化, 2016, 40(8): 1-13. XUE Yusheng, LAI Yening. Integration of macro energy thinking and big data thinking. Part Two. Applications and explorations ［J］. Automation of Electric Power Systems, 2016, 40(8): 1-13. ［8］刘天琪. 现代电力系统分析: 理论与方法［M］. 第二版. 北京: 中国电力出版社, 2016. LIU Tianqi. Modern power system analysis: Theory and method ［M］. 2nd ed. Beijing: China Electric Power Press, 2016. ［9］李杨. 基于广域动态信息的电力系统暂态稳定评估研究［D］. 北京: 华北电力大学, 2014. LI Yang. Research on transient stability assessment of power systems based on wide-area dynamic information ［D］. Beijing: North China Electric Power University, 2014. ［10］仲悟之, 汤涌. 电力系统微分代数方程模型的暂态电压稳定性分析［J］. 中国电机工程学报, 2010, 30(25): 10-16. ZHONG Wuzhi, TANG Yong. Transient voltage stability analysis of differential-algebra equation in power system ［J］. Proceedings of the CSEE, 2014, 30(25): 10-16. ［11］刘振亚. 智能电网技术［M］. 北京: 中国电力出版社, 2010. LIU Zhenya. Smart grid technology ［M］. Beijing: China Electric Power Press, 2010. ［12］YIN J, SHARMA P, GORTON I, et al. Large-scale data challenges in future power grids ［C］//7th International Symposium on Service-Oriented System Engineering. Redwood City, CA, USA: IEEE, 2013: 324-328. ［13］侯子良, 潘钢. 建设数字化电厂示范工程加快火电厂信息化进程［J］. 中国电力, 2005, 38(2): 78-80. HOU Ziliang, PAN Gang. Constructing demonstration projects of digitized power plant to speed up the informatization process in fossil-fired power plants ［J］. Electric Power, 2005, 38(2): 78-80. ［14］HE X, AI Q, QIU R C, et al. A big data architecture design for smart grids based on random matrix theory ［J］. IEEE Transactions on Smart Grid, 2017, 8(2): 674-686. ［15］QIU R C, HU Z, LI H, et al. Cognitive radio communications and networking: Principles and practice ［M］. New York: John Wiley and Sons, 2012. ［16］李晗, 萧德云. 基于数据驱动的故障诊断方法综述［J］. 控制与决策, 2011, 26(1): 1-9. LI Han, XIAO Deyun. Survey on data driven fault diagnosis methods ［J］. Control and Decision, 2011, 26(1): 1-9. ［17］于之虹, 黄彦浩, 鲁广明, 等. 基于时间序列关联分析的稳定运行规则提取方法［J］. 中国电机工程学报, 2015, 35(3): 519-526. YU Zhihong, HUANG Yanhao, LU Guangming, et al. A time series associative classification method for the operation rule extracting of transient stability ［J］. Proceedings of the CSEE, 2015, 35(3): 519-526. ［18］PASSARO M C, DA SILVA A P A, LIMA A C S. Preventive control stability via neural network sensitivity ［J］. IEEE Transactions on Power Systems, 2014, 29(6): 2846-2853. ［19］周艳真, 吴俊勇, 于之虹, 等. 基于转子角轨迹簇特征的电力系统暂态稳定评估［J］. 电网技术, 2016, 40(5): 1482-1487. ZHOU Yanzhen, WU Junyong, YU Zhihong, et al. Power system transient stability assessment based on cluster features of rotor angle trajectories ［J］. Power System Technology, 2016, 40(5): 1482-1487. ［20］冀鲁豫, 吴俊勇, 周艳真, 等. 基于WAMS 受扰电压轨迹簇特征的电力系统暂态稳定性预测［J］. 高电压技术, 2015, 41(3): 807-814. JI Luyu, WU Junyong, ZHOU Yanzhen, et al. Transient stability prediction of power system based on WAMS characteristic of perturbed voltage trajectory clusters ［J］. High Voltage Engineering, 2015, 41(3): 807-814. ［21］HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: A new learning scheme of feedforward neural networks ［C］//International Joint Conference on Neural Networks. Budapest, Hungary: IEEE, 2004: 985-990. ［22］HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: Theory and applications ［J］. Neurocomputing, 2006, 70(1/2/3): 489-501. ［23］李代高. 矩阵理论及其应用［M］. 重庆: 重庆大学出版社, 1989. LI Daigao. Matrix theory and its application ［M］. Chongqing: Chongqing University Press, 1989. ［24］叶圣永. 基于机器学习的电力系统暂态稳定评估研究［D］. 成都: 西南交通大学, 2010. YE Shengyong. Study on power systems transient stability assessment based on machine learning me-thod ［D］. Chengdu: Southwest Jiaotong University, 2010. ［25］王同文, 管霖, 章小强, 等. 基于扩展k阶近邻法的电力系统稳定评估新算法［J］. 电力系统自动化, 2008, 32(3): 18-21. WANG Tongwen, GUAN Lin, ZHANG Xiaoqiang, et al. A new method for power system stability assessment based on extended k-nearest neighbor classifier ［J］. Automation of Electric Power Systems, 2008, 32(3): 18-21. ［26］李扬, 顾雪平. 基于改进最大相关最小冗余判据的暂态稳定评估特征选择［J］. 中国电机工程学报, 2013, 33(34): 179-186. LI Yang, GU Xueping. Feature selection for tran-sient stability assessment based on improved maximal relevance and minimal redundancy criterion ［J］. Proceedings of the CSEE, 2013, 33(34): 179-186. ［27］GUYON I, WESTON J, BARNHILL S, et al. Gene selection for cancer classification using support vector machines ［J］. Machine Learning, 2002, 46(1/2/3): 389-422. ［28］周志华. 机器学习［M］. 北京: 清华大学出版社, 2016. ZHOU Zhihua. Machine learning ［M］. Beijing: Tsinghua University Press, 2016. ［29］GOMEZ F R, RAJAPAKSE A D, ANNAKKAGE U D, et al. Support vector machine-based algorithm for post-fault transient stability status prediction using synchronized measurements ［J］. IEEE Transactions on Power Systems, 2011, 26(3): 1474-1483.
Options
文章导航

/

〈 〉