Comparison of Decision Tree Attribute Selection Methods for Static Voltage Stability Margin Assessment

Decision tree (DT) as an effective data mining method has been widely used in voltage stability assessment. The selection of decision tree’s input attributes is critical because input attributes affect the accuracy and efficiency of the decision tree. This paper compares two attribute selection methods: participation factor method and Relief-F algorithm. Participation factor method is based on modal analysis of Jacobi matrix, while Relief-F algorithm is a mathematical approach that does not require power system knowledge. Two DTs with the same number of input attributes identified by participation factor analysis and Relief-F algorithm respectively are constructed for comparison in term of accuracy and efficiency. A case study on a practical power system indicates that two methods identify similar attributes and the accuracy of two DTs are close.

[1]  S. Henry,et al.  Efficient Database Generation for Decision Tree Based Power System Security Assessment , 2011, IEEE Transactions on Power Systems.

[2]  Larry A. Rendell,et al.  A Practical Approach to Feature Selection , 1992, ML.

[3]  Vijay Vittal,et al.  An Online Dynamic Security Assessment Scheme Using Phasor Measurements and Decision Trees , 2007 .

[4]  Mujahed Al-Dhaifallah,et al.  Features selection for arrhythmia diagnosis using Relief-F algorithm and support vector machine , 2017, 2017 14th International Multi-Conference on Systems, Signals & Devices (SSD).

[5]  H. Khoshkhoo,et al.  On-line dynamic voltage instability prediction based on decision tree supported by a wide-area measurement system , 2012 .

[6]  Gevork B. Gharehpetian,et al.  Application of core vector machines for on-line voltage security assessment using a decisiontree-based feature selection algorithm , 2009 .

[7]  G. Andersson,et al.  Use of participation factors in modal voltage stability analysis of multi-infeed HVDC systems , 1998 .

[8]  Mariana Kamel,et al.  Development and Application of a New Voltage Stability Index for On-Line Monitoring and Shedding , 2018, IEEE Transactions on Power Systems.

[9]  You Shang.  Research on PSVM Ensemble Algorithm Based on Relief (F) Object to Robot , 2012, 2012 International Conference on Computer Science and Electronics Engineering.

[10]  Teng Yun,et al.  Regional Voltage Stability Prediction Based on Decision Tree Algorithm , 2015, 2015 International Conference on Intelligent Transportation, Big Data and Smart City.

[11]  M. Beiraghi,et al.  Online Voltage Security Assessment Based on Wide-Area Measurements , 2013, IEEE Transactions on Power Delivery.

[12]  Jacek M. Zurada,et al.  Normalized Mutual Information Feature Selection , 2009, IEEE Transactions on Neural Networks.

[13]  Min Wei,et al.  Dimensionality reduction of hybrid data using mutual information-based unsupervised feature transformation: With application on intrusion detection , 2015, 2015 IEEE 13th International Conference on Industrial Informatics (INDIN).

[14]  Bai Di,et al.  Equivalent Expression of Participation Factor for Weak Buses Ranking of Static Voltage Sability , 2010, 2010 International Conference on Intelligent System Design and Engineering Application.

[15]  Chern-Lin Chen,et al.  Identification of optimum location for stabiliser applications using participation factors , 1987 .

[16]  Innocent Kamwa,et al.  Preventive control approach for voltage stability improvement using voltage stability constrained optimal power flow based on static line voltage stability indices , 2014, IET Generation, Transmission & Distribution.

[17]  Xin Li,et al.  Real-Time Static Voltage Stability Assessment in Large-Scale Power Systems Based on Maximum-Relevance Minimum-Redundancy Ensemble Approach , 2017, IEEE Access.

[18]  Harita Shah,et al.  Voltage stability monitoring by different ANN architectures using PCA based feature selection , 2016, 2016 IEEE 7th Power India International Conference (PIICON).

[19]  Nikhil Chaudhari,et al.  Dynamic security analysis for voltage security using Decision Trees , 2016, 2016 IEEE Region 10 Conference (TENCON).

[20]  Mitali Chakravorty,et al.  Voltage stability analysis using conventional methods , 2016, 2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES).

[21]  Paul Tschirhart,et al.  Using participation factors to improve the consistency and accuracy of Prony analysis for voltage stability monitoring applications , 2014, ISGT 2014.

[22]  Xingyuan Li,et al.  Feature Selection Method Based on Overlapped Probability for Transient Voltage Stability Assessment , 2012, 2012 Asia-Pacific Power and Energy Engineering Conference.

[23]  H. Khoshkhoo,et al.  Fast online dynamic voltage instability prediction and voltage stability classification , 2014 .