Online Voltage Security Assessment Based on Wide-Area Measurements

Online voltage security assessment is necessary to choose appropriate remedial and corrective actions in order to prevent a large-scale blackout. This paper presents a new online voltage security assessment method based on wide-area measurements and decision-tree algorithm. For the predicted load and generation variation scenarios (i.e., a day ahead), the database is obtained using continuation power flow. Moreover, each operating point is labeled as “secure” or “insecure” from voltage stability points of view based on WECC voltage security criteria. Decision trees are trained on the subset of the existing data by applying two famous splitting rules and various predictors. Bagging and adaptive boosting (AdaBoost) methods are employed to generate a combined model in order to increase the accuracy and eliminate dependency on selection of the predictors. Subsequently, this combined model is applied to predict the voltage security of the power system using continuous wide-area measurements. Since prediction by decision trees is very fast, the procedure will be completely online. The proposed method is tested on an IEEE 118-bus test system. The results indicate the applicability on the supervisory control and data-acquisition/energy-management system of a realistic power system.

[1]  F. Gubina,et al.  Voltage collapse proximity index determination using voltage phasors approach , 1995 .

[2]  F. Gubina,et al.  A simple approach to voltage stability assessment in radial networks , 1997 .

[3]  Geza Joos,et al.  Catastrophe Predictors From Ensemble Decision-Tree Learning of Wide-Area Severity Indices , 2010, IEEE Transactions on Smart Grid.

[4]  H. Sasaki,et al.  A predictor/corrector scheme for obtaining Q-limit points for power flow studies , 2005, IEEE Transactions on Power Systems.

[5]  K12-M Group,et al.  Voltage Collapse Mitigation Report to IEEE Power System , 2004 .

[6]  E. Vaahedi,et al.  Dynamic security constrained optimal power flow/VAr planning , 2001 .

[7]  Xindong Wu,et al.  The Top Ten Algorithms in Data Mining , 2009 .

[8]  R. Suganya,et al.  Data Mining Concepts and Techniques , 2010 .

[9]  N. Senroy,et al.  Decision Tree Assisted Controlled Islanding , 2006, IEEE Transactions on Power Systems.

[10]  N.D. Hatziargyriou,et al.  Decision Trees-Aided Self-Organized Maps for Corrective Dynamic Security , 2008, IEEE Transactions on Power Systems.

[11]  A. Bose,et al.  A fast voltage security assessment method using adaptive bounding , 1999, Proceedings of the 21st International Conference on Power Industry Computer Applications. Connecting Utilities. PICA 99. To the Millennium and Beyond (Cat. No.99CH36351).

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

[13]  Ruisheng Diao,et al.  Decision Tree-Based Online Voltage Security Assessment Using PMU Measurements , 2009, IEEE Transactions on Power Systems.

[14]  M. Begovic,et al.  Use of local measurements to estimate voltage-stability margin , 1997, Proceedings of the 20th International Conference on Power Industry Computer Applications.

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

[16]  Louis Wehenkel,et al.  Decision trees and transient stability of electric power systems , 1991, Autom..

[17]  Xi Chen,et al.  Fault Diagnosis of Transformer Based on Random Forest , 2011, 2011 Fourth International Conference on Intelligent Computation Technology and Automation.

[18]  Venkataramana Ajjarapu,et al.  The continuation power flow: a tool for steady state voltage stability analysis , 1991 .

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

[20]  C. W. Taylor,et al.  Decision trees using apparent resistance to detect impending loss of synchronism , 2000 .

[21]  A.G. Phadke,et al.  Real-time estimation of security from voltage collapse using synchronized phasor measurements , 2004, IEEE Power Engineering Society General Meeting, 2004..

[22]  D. Steinberg.  CART: Classification and Regression Trees , 2009 .

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

[24]  K. R. Padiyar,et al.  On-line detection of loss of synchronism using locally measurable quantities , 2001, 2001 IEEE/PES Transmission and Distribution Conference and Exposition. Developing New Perspectives (Cat. No.01CH37294).

[25]  James S. Thorp,et al.  Decision trees for real-time transient stability prediction , 1994 .

[26]  A. M. Abed.  WSCC voltage stability criteria, undervoltage load shedding strategy, and reactive power reserve monitoring methodology , 1999, 1999 IEEE Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.99CH36364).

[27]  Geza Joos,et al.  On the Accuracy Versus Transparency Trade-Off of Data-Mining Models for Fast-Response PMU-Based Catastrophe Predictors , 2012, IEEE Transactions on Smart Grid.

[28]  Wei-Yin Loh,et al.  Split Selection Methods for Classication Trees Published in Statistica Sinica, 1997, Vol. 7, pp. 815{840 , 1997 .