Abstract
We use one year’s subset to train the Support Vector Machines (SVM) and the next year’s data was used for testing with Kernel Principal Components Analysis (KPCA). This is clearly not optimal for a non-stationary time series such as we have here nevertheless the MAPE of peak load data set with back-propagation neural network [Chuang et al., 1998] is 3.0 and Support Vector Machine is 2.6.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chuang, S.J., Fyfe, C., Hwang, R.C.: Fuzzy backpropagation for power load forecasting: a comparative study. Soft Computing (1998)
Chuang, S.J., Fyfe, C., Hwang, R.C.: Power load forecasting by neural network with weights-limited training algorithm. In: ESS 1998 (1998)
Lin, Y., Wahba, G., Zhang, H., Lee, Y.: Statistical Properties and Adaptive Tuning of Support Vector Machines. TR 1022 (September 2000)
Swee, E.G.T., Elangovan, S.: Applications of systems for denosing and load forecasting. In: Proceedings of the IEEE Signal Processing Workshop on Higher-Order Statistics, 1999, pp. 165–169 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, FT., Chen, CH., Chuang, SJ., Ou, TC. (2010). The Power Load Forecasting by Kernel PCA. In: Pan, JS., Chen, SM., Nguyen, N.T. (eds) Computational Collective Intelligence. Technologies and Applications. ICCCI 2010. Lecture Notes in Computer Science(), vol 6422. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16732-4_44
Download citation
DOI: https://doi.org/10.1007/978-3-642-16732-4_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16731-7
Online ISBN: 978-3-642-16732-4
eBook Packages: Computer ScienceComputer Science (R0)