Time Series Forecasting using CCA and Kohonen Maps - Applications to Electricity Consumption
暂无分享,去创建一个
Using large regressors in non-linear time series forecasting makes the fitting of the model difficult. This paper shows how to reduce the size of regressors in order to improve the forecasting performances, using the Curvilinear Component Analysis as projection tool. The method is applied to the Polish electrical load forecasting.
[1] Jeanny Hérault,et al. Curvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets , 1997, IEEE Trans. Neural Networks.
[2] Patrick Rousset,et al. Daily Electrical Power Curves: Classification and Forecasting Using a Kohonen Map , 1995, IWANN.
[3] George E. P. Box,et al. Time Series Analysis: Forecasting and Control , 1977 .