Short term load forecasting model using support vector machine based on artificial neural network

A new sample preprocessing method is put forward in this paper. Firstly, the data points are classified into three types as the following: the high load type, the medium load type and the low load type; then, the artificial neural network is adopted to forecast the load type of the predict point; finally a support vector machine forecasting model is created on the basis of data points whose load type is the same as the predict point. It is the first time for artificial neural network to be combined with support vector machine in short term load forecasting. The practical examples show that the model established in this paper is better than other methods in forecasting accuracy and computing speed.

[1]  Michael T. Manry,et al.  Comparison of very short-term load forecasting techniques , 1996 .

[2]  Alan McLachlan.  An improved novelty criterion for resource allocating networks , 1997 .

[3]  Gary William Flake,et al.  Efficient SVM Regression Training with SMO , 2002, Machine Learning.

[4]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[5]  T. Hesterberg,et al.  A regression-based approach to short-term system load forecasting , 1989, Conference Papers Power Industry Computer Application Conference.