Application of core vector machines for on-line voltage security assessment using a decisiontree-based feature selection algorithm

This study presents a core vector machine (CVM)-based algorithm for on-line voltage security assessment of power systems. To classify the system security status, a CVM has been trained for each contingency. The proposed CVM-based security assessment algorithm has a very small training time and space in comparison with support vector machines (SVMs) and artificial neural networks (ANNs)-based algorithms. The proposed algorithm produces less support vectors (SVs). Therefore is faster than existing algorithms. One of the main points to apply a machine learning method is feature selection. In this study, a new decision tree (DT)-based feature selection algorithm has been presented. The proposed CVM algorithm has been applied to New England 39-bus power system. The simulation results show the effectiveness and the stability of the proposed method for on-line voltage security assessment. The effectiveness of the proposed feature selection algorithm has also been investigated. The proposed feature selection algorithm has been compared with different feature selection algorithms. The simulation results demonstrate the effectiveness of the proposed feature algorithm.

[1]  A. T. Johns,et al.  Kohonen neural network based approach to voltage weak buses/areas identification , 1997 .

[2]  M.A. El-Sharkawi,et al.  Support vector machines for transient stability analysis of large-scale power systems , 2004, IEEE Transactions on Power Systems.

[3]  Olav Bjarte Fosso,et al.  A method for calculation of margins to voltage instability applied on the Norwegian system for maintaining required security level , 1993 .

[4]  Alberto Berizzi,et al.  First and second order methods for voltage collapse assessment and security enhancement , 1998 .

[5]  A. A. El-Keib,et al.  Application of artificial neural networks in voltage stability assessment , 1995 .

[6]  N. Megiddo.  Linear-time algorithms for linear programming in R3 and related problems , 1982, FOCS 1982.

[7]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[8]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[9]  Y. H. Song,et al.  Hybrid supervised and unsupervised neural network approach to voltage stability analysis , 1998 .

[10]  Jihoon Yang,et al.  Feature Subset Selection Using a Genetic Algorithm , 1998, IEEE Intell. Syst..

[11]  Laxmi Srivastava,et al.  A hybrid neural network model for fast voltage contingency screening and ranking , 2000 .

[12]  Chanan Singh,et al.  Power system probabilistic security assessment using Bayes classifier , 2005 .

[13]  Gevork B. Gharehpetian,et al.  Power System On-Line Static Security Assessment by Using Multi-Class Support Vector Machines , 2008 .

[14]  Mohamed A. El-Sharkawi,et al.  Neural networks and support vector machines applied to power systems transient stability analysis , 2001 .

[15]  Peter W. Sauer,et al.  Power System Dynamics and Stability , 1997 .

[16]  Louis Wehenkel,et al.  Decision tree approaches to voltage security assessment , 1993 .

[17]  Venu Govindaraju,et al.  Half-Against-Half Multi-class Support Vector Machines , 2005, Multiple Classifier Systems.

[18]  F. L. Pagola,et al.  Estimating the loading limit margin taking into account voltage collapse areas , 1995 .

[19]  Nimrod Megiddo,et al.  Linear-time algorithms for linear programming in R3 and related problems , 1982, 23rd Annual Symposium on Foundations of Computer Science (sfcs 1982).

[20]  N. Hadjsaid,et al.  Emergency load shedding to avoid risks of voltage instability using indicators , 1994 .

[21]  T. Van Cutsem,et al.  Determination of secure operating limits with respect to voltage collapse , 1999 .

[22]  Manjaree Pandit,et al.  Contingency ranking for voltage collapse using parallel self-organizing hierarchical neural network , 2001 .

[23]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[24]  K. L. Lo,et al.  Fast real power contingency ranking using a counterpropagation network , 1998 .

[25]  B. Gao,et al.  Voltage Stability Evaluation Using Modal Analysis , 1992, IEEE Power Engineering Review.

[26]  Benjamin Jeyasurya.  Artificial neural networks for power system steady-state voltage instability evaluation , 1994 .

[27]  Jiansheng Huang,et al.  Worst-case identification of reactive power margin and local weakness of power systems , 1998 .

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

[29]  Ivor W. Tsang,et al.  Large-Scale Maximum Margin Discriminant Analysis Using Core Vector Machines , 2008, IEEE Transactions on Neural Networks.

[30]  Jacek M. Zurada,et al.  Generalized Core Vector Machines , 2006, IEEE Transactions on Neural Networks.

[31]  Claudio A. Canizares,et al.  Fast prediction of loadability margins using neural networks to approximate security boundaries of power systems , 2007 .

[32]  Kit Po Wong,et al.  Voltage stability constrained optimal dispatch in deregulated power systems , 2007 .

[33]  Ivor W. Tsang,et al.  Core Vector Machines: Fast SVM Training on Very Large Data Sets , 2005, J. Mach. Learn. Res..

[34]  Alberto Berizzi,et al.  A second order method for contingency severity assessment with respect to voltage collapse , 2000 .

[35]  H. Glavitsch,et al.  Estimating the Voltage Stability of a Power System , 1986, IEEE Transactions on Power Delivery.