Power Short-Term Load Forecasting Based on QPSO-SVM

Abstract:

The values of parameters of support vector machine have close contact with its forecast accuracy. In order to accurately forecast power short-term load,we presented a power short-term load forecasting method based on quantum-behaved particle swarm optimization and support vector machine.First,cauchy distribution was used to improve the quantum particle swarm algorithm.Secondly,the improved quantum particle swarm optimization algorithm was used to optimize the parameter of support vector machine.Finally, the support vector machine was used for power short-term load forecasting. In the proposed method such factors impacting loads as meteorology,weather and date types are comprehensively considered. The experimental results show that the root-mean-square relative error of the proposed method is only 1.90%, which is less than those of SVM and PSO-SVM model by 2.29% and 2.80%, respectively.

• Periodical: Advanced Materials Research (Volumes 591-593)
• Pages: 1311-1314
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.591-593.1311
• Online since: November 2012
• Authors: Xing Tong Zhu, Bo Xu
• Keywords: Accuracy, Forecast, Quantum Particle Swarm Optimization, Short-Term Load, Support Vector Machine (SVM)

References

[1] X.B. Zhang and J.S. Chen, "Short-Term Power System Load Forecasting Based On Improved BP Artificial Neural Network," Proc. 2011 IEEE International Conference on Computer Science and Automation Engineering, IEEE Press,Jun. 2011, pp.14-17.

DOI: 10.1109/csae.2011.5953161

[2] J.Z. Wang, "Method of short-term load forecasting based on BAYESIAN theorem," Proc. 2011 International Conference on Mechatronic Science,Electric Engineering and Computer, IEEE Press,Aug. 2011, pp.966-969.

DOI: 10.1109/mec.2011.6025625

[3] X.C. Li, L. Wang and Q.W. Li et al, "The Short-term Load Forecasting Based on Grey Theory and RBF Neural Network," Proc. the 3rd Asia-Pacific Power and Energy Engineering Conference, IEEE Press, Mar. 2011, pp.1-4.

DOI: 10.1109/appeec.2011.5748765

[4] C. Cortes and V.N. Vapnik, "Supporter vector networks," Machine Learning, vol. 20, No.3, pp.273-297, 1995.

[5] J. Kennedy and R.C. Eberhart, "Particle swarm optimization," Proc. IEEE International Conference on Neural Networks, IEEE Press. 1995, pp.1942-1948.

[6] J. Sun, B. Feng and W.B. Xu, "Particle swarm optimization with particles having quantum behavior," Proc. IEEE International Conference on Evolutionary Computation, IEEE Press. 2004, pp.325-331.

DOI: 10.1109/cec.2004.1330875

[7] X.G. Wang H.X. Long and J. Sun, "Quantum-behaved particle swarm optimization based on Gaussian disturbance," Application Research of Computers,vol.27,No.6,pp.2093-2096,June 2010.