Prediction of Undervoltage Load Shedding Using Quantum-Inspired Evolutionary Programming-Support Vector Machine

Abstract:

This paper presents a new technique to predict the optimal amount of load to be shed at various loading conditions using Quantum-Inspired Evolutionary Programming–Support Vector Machine (QIEP-SVM). QIEP is utilised to optimise the RBF Kernel parameters in Least-Square Support Vector Machine (LS-SVM). The objective of the optimisation is to minimise the mean square error (MSE). The performance of QIEP-SVM technique was compared with those obtained from LS-SVM technique with prediction accuracy through a 10-fold cross-validation procedure. All simulations in this study were carried out using IEEE 69-bus distribution test system. QIEP-SVM model had shown better prediction performance as compared to LS-SVM. The results also indicate that the proposed approach outperforms the most recently reported technique in terms of accuracy and fast computation time.

• Periodical: Applied Mechanics and Materials (Volume 785)
• Pages: 43-47
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.785.43
• Online since: August 2015
• Authors: Zuhaila Mat Yasin*, Zuhaina Zakaria, Titik Khawa Abdul Rahman
• Keywords: Least-Square Support Vector Machine, Prediction, Quantum-Inspired Evolutionary Programming, Undervoltage Load Shedding

References

[1] W. Helmy, Y. G. Hegazy, M. A. Mostafa and M. A. Badr, Strategic Placement of Distributed Generation Units to Avoid Load Shedding in Overloaded Power Systems, WSEAS Trans. on Power Systems, vol. 2, pp.261-270, Dec (2007).

DOI: 10.1109/mepcon.2008.4562369

[2] M. Nizam, A. Mohamed, M. Al-Dabbagh and A. Hussain, Using Support vector Machines for Determining Voltage Unstable Areas in Power Systems, 2nd Int. Conference on Power and Energy Conference (PECon2008), pp.878-883, (2008).

DOI: 10.1109/pecon.2008.4762599

[3] Z. M. Yasin, T. K. A. Rahman and Z. Zakaria, Optimal Undervoltage Load Shedding using Quantum-Inspired Evolutionary Programming, IEEE TENCON Spring Conference, pp.337-341, 17-19 April (2013).

DOI: 10.1109/tenconspring.2013.6584467

[4] T. Hacib, et al., Microvawe Charaterization using Ridge Polynomial Neural Networks and Least-Squares Support Vector Machines, IEEE Trans. on Magnetics, vol. 47, pp.990-993, (2011).

DOI: 10.1109/tmag.2010.2087743

[5] T. V. Gestel, et al, Financial Time Series Prediction using Least Squares Support Vector Machines within the Evidence Framework, IEEE Trans. on Neural Networks, vol. 12, pp.809-821, (2001).

DOI: 10.1109/72.935093

[6] J. Suykens, T.V. Gestel, J.D. Brabanter, B.D. Moor and J. Vandewalle, LS_SVMlab: A Matlab/C Toolbox for Least Squares Support Vector Machines, [online]. Available: http: /www. esat. kuleuven. be/sista/LSSVMlab, (2002).

DOI: 10.1142/5089

[7] M. De-yue and L. Wen-ying, Application of Least Squares Support Vector Machine(LS-SVM) Based on Time Series in Power System Monthly Load Forecasting, Asia-Pacific Power and Energy Conference, pp.1-4, 2011 (2011).

DOI: 10.1109/appeec.2011.5748632

[8] C. Schaffer, Technical Note: Selecting a Classification Method by Cross-Validation, Machine Learning, vol. 13, pp.135-143, (1993).

DOI: 10.1007/bf00993106

[9] Z. M. Yasin, T. K. A. Rahman and Z. Zakaria, Multiobjective Quantum-Inspired Evolutionary Programming for Optimal Location and Sizing of Distributed Generation, IEEE Conference on Sustainable Technology Sustainable Utilization and Development in Engineering and Technology (STUDENT), pp.233-238, 6 - 9 Oct (2012).

DOI: 10.1109/student.2012.6408410

[10] Z. M. Yasin, T. K. A. Rahman and Z. Zakaria, Quantum-Inspired Evolutionary Programming-Artificial Neural Network for Prediction of Undervoltage Load Shedding, 8th IEEE Conference on Industrial Electronics and Application (ICIEA), April (2013).

DOI: 10.1109/iciea.2013.6566436