Feature Selection Method for Power System Transient Stability Status Prediction Considering Class Imbalanced Characteristic

Power system transient stability status prediction (TSSP)has class imbalanced characteristic, including the imbalance of sample size and class importance. Therefore, a new feature selection method is proposed for TSSP. On the basis of analyzing the imbalanced characteristic of TSSP., the basic criteria of feature selection are put forward., and then the index of class weighted accuracy is proposed as the evaluation index. Under the guidance of the new evaluation index., the wrapper method combing sequential forward search and extreme learning machine is utilized for TSSP feature selection. The effectiveness of the proposed method is verified on Northeast Power Coordinated Council (NPCC)48-machine 140-bus system.

[1]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Joe H. Chow,et al.  A toolbox for power system dynamics and control engineering education and research , 1992 .

[3]  C. Jensen,et al.  Power System Security Assessment Using Neural Networks: Feature Selection Using Fisher Discrimination , 2001, IEEE Power Engineering Review.

[4]  Yang Li,et al.  Feature Selection for Transient Stability Assessment Based on Improved Maximal Relevance and Minimal Redundancy Criterion , 2019, ArXiv.

[5]  Zhihong Yu,et al.  A Hierarchical Method for Transient Stability Prediction of Power Systems Using the Confidence of a SVM-Based Ensemble Classifier , 2016 .

[6]  Qian Qing-quan.  Dual-stage Feature Selection for Transient Stability Assessment Based on Support Vector Machine , 2010 .

[7]  Shiu Kit Tso,et al.  Feature selection by separability assessment of input spaces for transient stability classification based on neural networks , 2004 .

[8]  Carson W. Taylor,et al.  Definition and Classification of Power System Stability , 2004 .

[9]  D. Andina,et al.  Feature selection using Sequential Forward Selection and classification applying Artificial Metaplasticity Neural Network , 2010, IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society.

[10]  Yin Zhang,et al.  Real-time transient stability status prediction using cost-sensitive extreme learning machine , 2015, Neural Computing and Applications.

[11]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[12]  Zhen Yang,et al.  Application of EOS-ELM With Binary Jaya-Based Feature Selection to Real-Time Transient Stability Assessment Using PMU Data , 2017, IEEE Access.

[13]  Hongbin Sun,et al.  Data driven method for transient stability prediction of power systems considering incomplete measurements , 2017, 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2).

[14]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[15]  Bingyang Li,et al.  Feature Reduction for Power System Transient Stability Assessment Based on Neighborhood Rough Set and Discernibility Matrix , 2018 .