Veysel Murat İstemihan GENÇ, Peyman BEYRANVAND, Zehra ÇATALTEPE

Multilabel learning for the online transient stability assessment of electric power systems

Dynamic security assessment of a large power system operating over a wide range of conditions requires anintensive computation for evaluating the system’s transient stability against a large number of contingencies. In thisstudy, we investigate the application of multilabel learning for improving training and prediction time, along with theprediction accuracy, of neural networks for online transient stability assessment of power systems. We introduce a newmultilabel learning method, which uses a contingency clustering step to learn similar contingencies together in the samemultilabel multilayer perceptron. Experimental results on two different power systems demonstrate improved accuracy,as well as significant reduction in both training and testing time.

PDF

___

Sauer PW, Tomsovic KL, Vittal V. Dynamic security assessment. In: Grigsby LL, editor. Power System Stability and Control. Boca Raton, FL, USA: CRC Press, 2007. pp. 1-10.
Kezunovic M, Meliopoulos S, Venkatasubramanian V, Vittal V. Application of Time-Synchronized Measurements in Power System Transmission Networks. Cham, Switzerland: Springer, 2014.
Kundur P, Balu NJ, Lauby MG. Power System Stability and Control. New York, NY, USA: McGraw-Hill, 1994.
Fouad AA, Vittal V. Power System Transient Stability Analysis Using the Transient Energy Function Method. Englewood Cliffs, NJ, USA: Prentice-Hall, 1992.
Wehenkel LA. Automatic Learning Techniques in Power Systems. Norwell, MA, USA: Kluwer Academic Publishers, 1998.
Zhang ML, Zhou ZH. Multilabel neural networks with applications to functional genomics and text categorization. IEEE T Knowl Data En 2006; 18: 1338-1351.
Oliveira WD, Vieira JP, Bezerra UH, Martins DA, Rodrigues BDG. Power system security assessment for multiple contingencies using multiway decision tree. Electr Pow Syst Res 2017; 148: 264-272.
Kalyani S, Swarup KS. Classification and assessment of power system security using multiclass SVM. IEEE T Syst Man Cy C 2011; 41: 753-758.
Voumvoulakis EM, Gavoyiannis AE, Hatziargyriou ND. Application of machine learning on power system dynamic security assessment. In: Intelligent Systems Applications to Power Systems (ISAP); 5–8 November 2007; Toki Messe, Niigata, Japan: IEEE. pp. 1-6.
Hoballah A, Erlich I. Real-time operation of deregulated electricity market: an integrated approach to dynamic stability assurance. In: Energy Conference and Exhibition (EnergyCon); 18–22 December 2010; Manama, Bahrain: IEEE. pp. 262-267.
Kucuktezcan CF, Genc VMI. A comparison between ANN based methods of critical clearing time estimation. In: International Conference on Electrical and Electronics Engineering (ELECO); 28–30 November 2013; Bursa, Turkey: IEEE. pp. 132-136.
Swarup KS, Reddy KP. Neural network based pattern recognition for power system security assessment. In: International Conference on Intelligent Sensing and Information Processing; 4-7 January 2005; Chennai, India: IEEE. pp. 234-239.
Zhang ML, Zhou ZH. A review on multi-label learning algorithms. IEEE T Knowl Data En 2014; 26: 1819-1837.
Boutell MR, Luo J, Shen X, Brown CM. Learning multi-label scene classification. Pattern Recogn 2004; 37: 1757- 1771.
Read J, Pfahringer B, Holmes G, Frank E. Classifier chains for multi-label classification. Mach Learn 2011; 85: 333-359.
Gaber MM, Zaslavsky A, Krishnaswamy S. A survey of classification methods in data streams. In: Aggarwal CC, editor. Data Streams. Boston, MA, USA: Springer, 2007. pp. 39-59.
Zhang ML, Zhou ZH. ML-KNN: a lazy learning approach to multi-label learning. Pattern Recogn 2007; 40: 2038- 2048.
Clare A, King RD. Knowledge discovery in multi-label phenotype data. In: European Conference on Principles of Data Mining and Knowledge Discovery; 3–7 September 2001; Freiburg, Germany: Springer-Verlag. pp. 42-53.
Elisseeff A, Weston J. A kernel method for multi-labelled classification. In: Conference on Neural Information Processing Systems (NIPS); 3–8 December 2001; Vancouver, British Columbia, Canada: MIT Press. pp. 681-687.
Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature 1986; 323: 533-536.
Jain AK, Murty MN, Flynn PJ. Data clustering: a review. ACM Comput Surv 1999; 31: 264-323.
Zambelli AE. A data-driven approach to estimating the number of clusters in hierarchical clustering. International Society for Computational Biology Community Journal 2016; 5: 1-13.
Kojadinovic I. On the use of mutual information in data analysis: an overview. In: International Symposium on Applied Stochastic Models and Data Analysis (ASMDA); 17–20 May 2005; Brest, France: ENST Bretagne. pp. 738-747.
Witten IH, Frank E, Hall MA, Pal CJ. Data Mining: Practical Machine Learning Tools and Techniques. Cambridge, MA, USA: Morgan Kaufmann, 2017.
Sutskever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning; 16–21 June 2013; Atlanta, GA, USA: PMLR. pp. 1139-1147.
Rogers G. Power System Oscillations. New York, NY, USA: Springer Science & Business Media, 2012.
Fan D. Synchronized measurements and applications during power system dynamics. PhD, Virginia Tech, USA, 2008.
DSAToolsTM. Powertech Labs Inc., Surrey, British Columbia, Canada.
Bengio Y. Learning deep architectures for AI. Foundations and Trends in Machine Learning 2009; 2: 1-127.