Real-time power system dynamic security assessment based on advanced feature selection for decision tree classifiers

This paper proposes a novel algorithm based on an advanced feature selection technique for the decisiontree (DT) classifier to assess the dynamic security in a power system. The proposed methodology utilizes symmetricaluncertainty (SU) to reduce the data redundancy in a dataset for DT classifier-based dynamic security assessment (DSA)tools. The results show that SU reduces the dimension of the dataset used for DSA significantly. Subsequently, theapproach improves the performance of the DT classifier. The effectiveness of the proposed technique is demonstratedon the modified IEEE 30-bus test system model. The results show that the DT classifier with SU outperforms theDT classifier without SU. The performance of the proposed algorithm indicates that the DT classifier with SU is ableto assess the dynamic security of the system in near real time. Therefore, it is able to provide vital information forprotection and control applications in power system operation.

PDF

___

[1] Kundur P, Taylor C, Pourbeik P. Blackout Experiences and Lessons, Best Practices for System Dynamic Performance, and the Role of New Technologies. IEEE Task Force Report. New York, NY, USA: IEEE, 2007.
[2] Ariff MAM, Pal BC. Adaptive protection and control in the power system for wide-area blackout prevention. IEEE T Power Deliver 2016; 31: 1815-1825.
[3] Lin Z, Wen F, Xue Y. A restorative self-healing algorithm for transmission systems based on complex network theory. IEEE T Smart Grid 2016; 7: 2154-2162.
[4] Martin JA, Hiskens IA. Corrective model-predictive control in large electric power systems. IEEE T Power Syst 2017; 32: 1651-1662.
[5] Grigsby LL, editor. Power System Stability and Control. 3rd ed. Boca, Raton, FL, USA: CRC Press, 2012.
[6] Phadke AG, Thorp JS. Synchronized Phasor Measurements and Their Applications. Vol. 1. New York, NY, USA: Springer, 2008.
[7] Kerin U, Heyde C, Krebs R, Lerch E. Real-time dynamic security assessment of power grids. Eur Phys J-Spec Top 2014; 223: 2503-2516.
[8] Xue Y, Yu Y, Li J, Gao Z, Ding C, Xue F, Wang L, Morison GK, Kundur P. A new tool for dynamic security assessment of power systems. Control Eng Pract 1998; 12: 1511-1516.
[9] Geeganage J, Annakkage UD, Weekes T, Archer BA. Application of energy-based power system features for dynamic security assessment. IEEE T Power Syst 2015; 30: 1957-1965.
[10] Padiyar KR. Power System Dynamics. 2nd ed. Hyderabad, India: BS Publications, 2008.
[11] Sun K, Likhate S, Vittal V, Kolluri VS, Mandal S. An online dynamic security assessment scheme using phasor measurements and decision trees. IEEE T Power Syst 2007; 22: 1935-1943.
[12] Yu L, Liu H. Feature selection for high-dimensional data: A fast correlation-based filter solution. In: Proceedings of the 20th International Conference on Machine Learning; 21–24 August 2003; Washington, DC, USA. Menlo Park, CA, USA: AAAI Press. pp. 856-863.
[13] Algamal ZY, Lee MH. High dimensional logistic regression model using adjusted elastic net penalty. Pakistan J Stat Oper Res 2015; 11: 667-676.
[14] Savulescu SC. Real-time Stability Assessment in Modern Power System Control Centers. Hoboken, NJ, USA: Wiley-IEEE Press, 2009.
[15] Vittal V, Sauer P, Meliopoulos S, Stefopoulos G. On-line Transient Stability Assessment Scoping Study. Final Project Report. Madison, WI, USA: PSERC Publications, 2005.
[16] Alvarez JMG, Mercado PE. Online inference of the dynamic security level of power systems using fuzzy techniques. IEEE T Power Syst 2007; 22: 717-726.
[17] Xu Y, Dong ZY, Zhao JH, Zhang P, Wong KP. A reliable intelligent system for real-time dynamic security assessment of power systems. IEEE T Power Syst 2012; 27: 1253-1263.
[18] He M, Zhang J, Vittal V. Robust online dynamic security assessment using adaptive ensemble decision-tree learning. IEEE T Ind Inform 2013; 28: 4089-4098.
[19] Luo F, Dong Z, Chen G, Xu Y, Meng K, Chen YY, Wong K. Advanced pattern discovery-based fuzzy classification method for power system dynamic security assessment. IEEE T Ind Inform 2015; 11: 416-426.
[20] Voumvoulakis EM, Gavoyiannis AE, Hatziargyriou ND. Decision trees for dynamic security assessment and load shedding scheme. In: 2006 Power Engineering Society General Meeting; 18–22 June 2006; Montreal, Canada. New York, NY, USA: IEEE. pp. 1-7.
[21] Jensen CA, El-Sharkawi MA, Marks RJ. Power system security assessment using neural networks: feature selection using Fisher discrimination. IEEE T Power Syst 2001; 16: 757-763.
[22] Zhang R, Xu Y, Dong ZY, Hill DJ. Feature selection for intelligent stability assessment of power systems. In: 2012 Power and Energy Society General Meeting, 22–26 July 2012; San Diego, CA, USA. New York, NY, USA: IEEE. pp. 1-7.
[23] Kannan SS, Ramaraj N. A novel hybrid feature selection via symmetrical uncertainty ranking based local mimetic search algorithm. Knowledge-Based Syst 2010; 23: 580-585.
[24] Yu L, Liu H. Efficient feature selection via analysis of relevance and redundancy. J Mach Learn Res 2004; 5: 1205-1224.
[25] Kaladhar D, Chandana B, Kumar PB. Predicting cancer survivability using classification algorithms. Int J Res Rev Comp Sci 2011; 2: 340-343.
[26] Ruiz R, Riquelme JC, Aguilar-Ruiz JS. Incremental wrapper-based gene selection from microarray data for cancer classification. Pattern Recogn 2006; 39: 2383-2392.
[27] Kumar A, Zhang D. Personal recognition using hand shape and texture. IEEE T Image Process 2006; 15: 2454-2461.
[28] Landwehr N, Hall M, Frank E. Logistic model trees. J Mach Learn Res 2005; 59: 161-205.
[29] Demetriou P, Asprou M, Quiros-Tortos J, Kyriakides E. Dynamic IEEE test systems for transient analysis. IEEE Syst J 2015; 99: 1-10.
[30] Witten IH, Frank E. Data Mining: Practical Machine Learning Tools and Techniques. 2nd ed. San Francisco, CA, USA: Morgan Kaufmann Publishers, 2005.