Accurate load prediction plays an important role in smart power management system, either for planning, facing the increasing of load demand, maintenance issues, or power distribution system. In order to achieve a reasonable prediction, authors have applied and compared two features extraction technique presented by kernel partial least square regression and kernel principal component regression, and both of them are carried out by polynomial and Gaussian kernels to map the original features’ to high dimension features’ space, and then draw new predictor variables known as scores and loadings, while kernel principal component regression draws the predictor features to construct new predictor variables without any consideration to response vector. In contrast, kernel partial least square regression does take the response vector into consideration. Models are simulated by three different cities’ electric load data, which used historical load data in addition to weekends and holidays as common predictor features for all models. On the other hand temperature has been used for only one data as a comparative study to measure its effect. Models’ results evaluated by three statistic measurements, show that Gaussian Kernel Partial Least Square Regression offers the more powerful features and significantly can improve the load prediction performance than other presented models.
References
[1]
Soliman, A.H. and Al-Kandari, A.M. (2010) 3-Load Modeling for Short-Term Forecasting. Electric Load Forecasting, Modeling and Model Construction, 79-82.
https://doi.org/10.1016/B978-0-12-381543-9.00003-8
[2]
Amral, N., Ozveren, C.S. and King, D. (2007) Short Term Load Forecasting Using Multiple Linear Regression. Universities Power Engineering Conference, 4-6 September 2007, 1192-1198. https://doi.org/10.1109/upec.2007.4469121
[3]
Almeshaiei, E. and Soltan, H. (2011) A Methodology for Electric Power Load Forecasting. Alexandria Engineering Journal, 50, 137-144.
https://doi.org/10.1016/j.aej.2011.01.015
[4]
Pan, X. and Lee, B. (2012) A Comparison of Support Vector Machines and Artificial Neural Networks for Mid-Term Load Forecasting. IEEE International Conference on Industrial Technology, 2012, 95-101.
[5]
Othman, M.M., Harun, M.H.H. and Musirin, I. (2012) Short Term Load Forecasting Using Artificial Neural Network with Feature Extraction Method and Stationary Output. IEEE International Power Engineering and Optimization Conference, 6-7 June 2012, 480-484. https://doi.org/10.1109/PEOCO.2012.6230912
[6]
Shawetaylor, J. (2006) Pattern Analysis Using Convex Optimisation. In: Kernel Methods for Pattern Analysis, Cambridge, New York, 230-240.
[7]
Elattar, E.E., Goulermas, J.Y. and Wu, Q.H. (2010) Integrating KPCA and Locally Weighted Support Vector Regression for Short-Term Load Forecasting. IEEE Mediterranean Electrotechnical Conference, 26-28 April 2010, 1528-1533.
https://doi.org/10.1109/melcon.2010.5476265
[8]
Rosipal, R. and Trejo, L.J. (2002) Kernel Partial Least Squares Regression in Reproducing Kernel Hilbert Space. Journal of Machine Learning Research, 2, 97-123.
[9]
Schölkopf, B., Smola, A. and Müller, K. (1998) Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation, 10, 1299-1319.
https://doi.org/10.1162/089976698300017467
[10]
Bishop, C.M. (2007) Continuous Latent Variables. In: Pattern Recognition and Machine Learning, Springer, New York, 559-569.
[11]
Smola, A.J. and Lkopf, B. (2004) A Tutorial on Support Vector Regression. Statistics and Computing, 14, 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
[12]
Rosipal, R., Girolami, M., Trejo, L.J. and Cichocki, A. (2001) Kernel PCA for Feature Extraction and De-Noising in Nonlinear Regression. Neural Computing and Applications, 10, 231-243. https://doi.org/10.1007/s521-001-8051-z
[13]
Wibowo, A. and Yamamoto, Y. (2012) A Note on Kernel Principal Component Regression. Computational Mathematics and Modeling, 23, 350-367.
https://doi.org/10.1007/s10598-012-9143-0
[14]
Rosipal, R. and Krämer, N. (2006) Overview and Recent Advances in Partial Least Squares. In: Saunders, C., Grobelnik, M., Gunn, S. and Shawe-Taylor, J., Eds., Subspace, Latent Structure and Feature Selection, Springer, Berlin, 34-51.
https://doi.org/10.1007/11752790_2
[15]
Lewi, P.J. (1995) Pattern Recognition, Reflections from a Chemometric Point of View. Chemometrics & Intelligent Laboratory Systems, 28, 23-33.
https://doi.org/10.1016/0169-7439(95)80037-A
[16]
Rosipal, R. (2003) Kernel Partial Least Squares for Nonlinear Regression and Discrimination. Neural Network World, 13, 291-300.
[17]
Jong, S.D. (1993) SIMPLS: An Alternative Approach to Partial Least Squares Regression. Chemometrics & Intelligent Laboratory Systems, 18, 251-263.
https://doi.org/10.1016/0169-7439(93)85002-X
[18]
Helander, E., Silén, H., Virtanen, T. and Gabbouj, M. (2012) Voice Conversion Using Dynamic Kernel Partial Least Squares Regression. IEEE Transactions on Audio Speech & Language Processing, 20, 806-817.
https://doi.org/10.1109/TASL.2011.2165944
[19]
World-Wide Competition within the EUNITE Network (2002) Eastern Slovakian Electricity Corporation. http://neuron.tuke.sk/competition/index.php
[20]
Iso New England Data Set.
http://www.iso-ne.com/isoexpress/web/reports/pricing/-/tree/zone-info
[21]
Victoria Data Set Australian Energy Market Operator (AEMO).
http://www.aemo.com.au/Electricity/National-Electricity-Market-NEM/Data
