Evolutionary Support Vector Machines for Transient Stability Monitoring

Currently, power systems are in the need of fast and reliable contingency monitoring systems for the purpose of maintaining stability in the presence of deregulated and open market environment. In this paper, a quick and unfailing transient stability monitoring algorithm that considers both the symmetrical and unsymmetrical faults is presented. support vector machines (SVMs) are employed as pattern classifiers so as to construct fast relation mappings between the transient stability results and the selected input attributes using mutual information. The type of fault is recognized by a SVM classifier and the critical clearing time of the fault is estimated by a support vector regression machine. The SVM parameters are tuned by an elitist multi-objective non-dominated sorting genetic algorithm in such a manner that the best classification and regression performance are accomplished. To demonstrate the good potential of the scheme, IEEE 3 generator system and a South Indian Grid are utilized.

[1]  Kalyanmoy Deb,et al.  Multi-objective optimization using evolutionary algorithms , 2001, Wiley-Interscience series in systems and optimization.

[2]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[3]  James S. Thorp,et al.  Expose hidden failures to prevent cascading outages [in power systems] , 1996 .

[4]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  P. Kundur,et al.  Power system stability and control , 1994 .

[6]  D. P. Kothari,et al.  Power system optimization , 2004, 2012 2nd National Conference on Computational Intelligence and Signal Processing (CISP).

[7]  H. Happ.  Power system control and stability , 1979, Proceedings of the IEEE.

[8]  Li Xu,et al.  Multi-objective Parameters Selection for SVM Classification Using NSGA-II , 2006, ICDM.

[9]  D. Thukaram,et al.  Application of support vector machines for fault diagnosis in power transmission system , 2008 .

[10]  V. Vapnik,et al.  Bounds on Error Expectation for Support Vector Machines , 2000, Neural Computation.

[11]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[12]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[13]  Olivier Chapelle,et al.  Model Selection for Support Vector Machines , 1999, NIPS.

[14]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

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

[16]  Kalyanmoy Deb,et al.  MULTI-OBJECTIVE FUNCTION OPTIMIZATION USING NON-DOMINATED SORTING GENETIC ALGORITHMS , 1994 .

[17]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[18]  Jason Weston,et al.  Multi-Class Support Vector Machines , 1998 .