Classification of mode damping and amplitude in power systems using synchrophasor measurements and classification trees

This paper details the use of classification trees to predict mode damping using powerflow data from power system models. Power systems are complex with vast amounts of data being collected from measurements made via wide-area measurement (WAMS) and SCADA systems. Classification trees are introduced as a means to handle vast quantities of powerflow data which can be used to classify mode damping and amplitude. In reality, the classification trees would be trained on real power system data from SCADA and WAMS. A case study based on real field data from the Ecuadorian power system is presented where interconnectors to Colombia tripped in response to a poorly damped mode of oscillation. Testing of this methodology shows the feasibility of this approach with accurate classification of mode damping and amplitude on training and testing data sets. By highlighting significant variables affecting mode damping and amplitude, a decision tool for system operators can be developed that will suggest the optimal course of action to remedy any near instability or unstable electromechanical oscillations in transmission networks.

[1]  Lior Rokach,et al.  Top-down induction of decision trees classifiers - a survey , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[2]  H. Wold.  Path Models with Latent Variables: The NIPALS Approach , 1975 .

[3]  Simon Patrick Teeuwsen.  Oscillatory Stability Assessment of Power Systems Using Computational Intelligence , 2005 .

[4]  Joe H. Chow,et al.  Performance comparison of three identification methods for the analysis of electromechanical oscillations , 1999 .

[5]  Louis Wehenkel,et al.  Decision tree based transient stability method a case study , 1994 .

[6]  Graham Rogers,et al.  Power System Oscillations , 1999 .

[7]  E F Cook,et al.  Empiric comparison of multivariate analytic techniques: advantages and disadvantages of recursive partitioning analysis. , 1984, Journal of chronic diseases.

[8]  Zhenyu Huang,et al.  Deriving optimal operational rules for mitigating inter-area oscillations , 2011, 2011 IEEE/PES Power Systems Conference and Exposition.

[9]  Udaya Annakkage,et al.  Accurate prediction of damping in large interconnected power systems with the aid of regression analysis , 2009, 2009 IEEE Power & Energy Society General Meeting.

[10]  Janusz Bialek,et al.  IDENTIFYING SOURCES OF DAMPING ISSUES IN THE ICELANDIC POWER SYSTEM , 2008 .

[11]  A. Afifi,et al.  Comparison of Stopping Rules in Forward “Stepwise” Regression , 1977 .

[12]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[13]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[14]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[15]  George C. Runger,et al.  Bias of Importance Measures for Multi-valued Attributes and Solutions , 2011, ICANN.