Application of Improved Sammon Mapping Algorithm in Input Features Validity Analysis of Transient Stability Assessment

doi:10.3969/j.issn.1000－7229.2016.12.013

Abstract

Abstract: In the method of power system transient stability assessment based on machine learning technology, the reasonableness of the input feature extraction decides the final classification result. However, there were no tools to judge whether the selected input features are the separable. Therefore, this paper introduces the Sammon mapping algorithm to map high dimensional sample data to low dimensional space, determines the effectiveness of selected feature through observing the distribution of mapping points, and improves the original algorithm according to its deficiencies. Firstly, we adopted principal component analysis (PCA) method to obtain the first two dimensional principal component vectors containing the most original data information, which worked as the initial value of the mapping point coordinate vector instead of the random selection method in the original algorithm. Then, we used the iterative method to solve the coordinate vector of mapping points to accelerate the solving speed. Finally, we used the improved Sammon mapping algorithm as a tool to analyze the effectiveness of selected features of the numerical simulation data in IEEE39-bus system and the actual online historical data of a certain area. The analysis results show that the improved algorithm has a good application prospect in guiding feature selection.

Key words: transient stability, machine learning, Sammon mapping, feature effectiveness

CLC Number:

TM 71

ZHANG Chun, TIAN Fang, YU Zhihong, LI Yansong, ZHANG Shuang, TIAN Bei.

Application of Improved Sammon Mapping Algorithm in Input Features Validity Analysis of Transient Stability Assessment

[J]. Electric Power Construction, 2016, 37(12): 96-.

References

［1］李亚楼, 张星, 李勇杰,等. 交直流混联大电网仿真技术现状及面临挑战［J］. 电力建设, 2015, 36(12):1-8.

LI Yalou, ZHANG Xing, LI Yongjie, et al. Present situation and challenges of AC/DC hybrid large-scale power grid simulation technology ［J］. Electric Power Construction, 2015, 36(12):1-8.

［2］赵春晖, 姜大为, 崔灿,等. 大数据时代下的新型电网规划体系［J］. 电力建设, 2014, 35(10):17-20.

ZHAO Chunhui, JIANG Dawei, CUI Can, et al. New power grid planning system in big-data era［J］. Electric Power Construction,2014,35(10):17-20.

［3］张沛, 吴潇雨, 和敬涵. 大数据技术在主动配电网中的应用综述［J］. 电力建设, 2015, 36(1):52-59.

ZHANG Pei, WU Xiaoyu, HE Jinghan. Review on big data technology applied in active distribution network［J］. Electric Power Construction, 2015, 36(1):52-59.

［4］童晓阳，叶圣永．数据挖掘在电力系统暂态估中的应用综述［J］．电网技术，2009，33(20)：88-93．

TONG Xiaoyang，YE Shengyong．A survey on application of data mining in transient stability assessment of power system［J］．Power System Technology，2009，33(20)：88-93．

［5］王同文，管霖，张尧．人工智能技术在电网稳定评估中的应用综述［J］．电网技术，2009，33(12)：60-65．

WANG Tongwen，GUAN Lin，ZHANG Yao．A survey on application of artificial intelligence technology in power system stability assessment［J］．Power System Technology，2009，33(12)：60-65．

［6］SAMMON J W. A nonlinear mapping for data structure analysis［J］. IEEE Transactions on Computers, 1969, C-18(5): 401-409.

［7］顾雪平,张志刚,张文勤. 基于神经网络的暂态稳定评估输入空间可分性［J］. 华北电力大学学报,2000,27（2）:16-20.

GU Xueping, ZHANG Zhigang , ZHANG Wenqin. Input space separability analysis of artificial neural networks based transient stability assessment［J］.Journal of North China Electric Power University,2000,27(2):16-20.

［8］顾雪平,曹绍杰,张文勤. 基于神经网络暂态稳定评估方法的一种新思路［J］. 中国电机工程学报,2000,20(4):78-82.

GU Xueping, TSO Shiukit, ZHANG Wenqin. A new framework for transient stability assessment based on neural networks［J］. Proceedings of the CSEE, 2000, 20(4):77-82.

［9］YU Zhihong, ZHOU Xiaoxin, WU Zhongxi. Transient stability boundary visualization for power system［C］// International Conference on Power System Technology. IEEE, 2006.

［10］RADVANSKY M, KUDELKA M, SNASEL V. Identifying power profiles in the photovoltaic power station data by self-organizing maps and dimension reduction by Sammons projection［C］//Soft Computing and Pattern Recognition (SoCPaR).IEEE, 2013.

［11］陈敏. 智舌非线性模式识别方法研究［D］.杭州：浙江工商大学,2012.

CHEN Min. The research of nonlinear pattern recognition methods for smartongue［D］.Hangzhou: Zhejiang Gongshang University, 2012.

［12］周凌岚,叶浩欢,柳征,等. 基于改进Sammon映射的辐射源个体特征有效性分析［J］.电子信息对抗技术,2010, 1(25):21-24.

ZHOU Linglan, YE Haohuan, LIU Zheng, et al. Validity analysis of emitter individual features based on an improved Sammon mapping ［J］.Electronic Warfare Technology, 2010, 1(25):21-24.

［13］崔巍，都秀文，杨海峰．基于主成分分析法的电力需求影响因素分析［J］．电力建设，2013，34( 8) : 34-39．

CUI Wei, DU Xiuwen, YANG Haifeng. Analysis on influencial factor of power demand based on principal component analysis［J］. Electric Power Construction,2013,34(8) : 34-39．

［14］LERNER B, GUTERMAN H, ALADJ E M, et al. Feature extraction by neural network nonlinear mapping for pattern classification［C］//13th International Conference on Pattern Recognition ( ICPR96). IEEE, 1996:320-324.

［15］KOVCS A, ABONYI J. Visualization of fuzzy clustering results by modified Sammon mapping［C］// IEEE International Conference on Fuzzy Systems. IEEE, 2004, 1(1):365-370.

［16］BACHE K, LICHMAN M. UCI Machine Learning Repository［EB/OL］.［2016-06-05］. http//archive.ics.uci.edu/ml/datsets/wine.

［17］Kohonen T. Self-organizing Maps［ M］. 3rd Edition, Kerlin: Springer-Verlag, 2001.

［18］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 transient stability assessment based on improved maximal relevance and minimal redundancy criterion ［J］．Proceedings of the CSEE，2013，33(34)：179-186．

［19］张伯明，陈寿孙，严正. 高等电力网络分析［M］. 北京：清华大学出版社，2007.

［20］叶圣永，王晓茹，刘志刚，等．基于支持向量机的暂态稳定评估双阶段特征选择［J］．中国电机工程学报，2010，30(31)：28-34．

YE Shengyong，WANG Xiaoru，LIU Zhigang，et al． Dual-stage feature selection for transient stability assessment based on support vector machine ［J］．Proceedings of the CSEE，2010，30(31)：28-34．

［21］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 System，2011,26(3):1474-1483.

［22］章小强. 智能稳定评估中的关键特征识别研究［D］.广州：华南理工大学,2010.

ZHANG Xiaoqiang. Studies on kernel feature recognition for intelligent stability assessment ［D］．Guangzhou: South China University of Technology，2010.

［23］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．

［24］国家电网公司．国家电网安全稳定计算技术规范: Q/GDW 404—2010［S］. 北京：国家电网公司，2010．

［25］黄彦浩，于之虹，史东宇，等. 基于海量在线历史数据的大电网快速判稳策略［J］. 中国电机工程学报，2016，36(3)：596-603.

HUANG Yanhao，YU Zhihong，SHI Dongyu，et al. Strategy of huge electric power system stability quick judgment based on massive historical online data ［J］．Proceedings of the CSEE，2016，36(3)：596-603.

[1]	LIANG Xiurui, LIU Daowei, YANG Hongying, LI Weixing, SHAO Guanghui, XU Xingwei, WANG Kefei, LI Zonghan, ZHAO Gaoshang. Data-Driven Situation Assessment of Power System Static Voltage Stability [J]. Electric Power Construction, 2020, 41(1): 126-132.
[2]	XIAO Zeqing， HUA Haochen， CAO Junwei. Overview of the Application of Artificial Intelligence in Energy Internet [J]. Electric Power Construction, 2019, 40(5): 63-70.
[3]	ZHOU Yue, TAN Bendong, LI Miao, YANG Xuan, ZHOU Qiangming, ZHANG Zhenxing, TAN Min, YANG Jun . Transient Stability Assessment of Power System Based on Deep Learning Technology [J]. Electric Power Construction, 2018, 39(2): 103-.
[4]	DAI Yan, WANG Liuwang, LI Yuan, YAN Yong, HAN Jiajia, WEN Fushuan. A Brief Survey on Applications of New Generation Artificial Intelligence in Smart Grids [J]. Electric Power Construction, 2018, 39(10): 1-11.
[5]	WANG Qin, JIANG Huaiguang,WEN Fushuan, MEI Tianhua. Concept, Technology and Challengs of Big Data in Smart Grids [J]. Electric Power Construction, 2016, 37(12): 1-.