Price spike forecasting using concept-tree approach based on cloud model

There are many techniques for electricity market price forecasting. The challenge of spike prediction is the accuracy of the prediction that is on how a classifier can capture all spikes that would happen. In this paper, we introduce a novel data discretization approach using cloud models to implement concept hierarchies and data reduction. An effective framework of predicting the occurrence of spikes has been discussed in details. A concept-tree approach based on cloud model is presented to give a reliable forecast of the occurrence of price spikes with low dimension space and automated concept level. Combined with the spike value prediction techniques, the proposed approach aims at providing a comprehensive tool for price spike forecasting are discussed in detail. Realistic market data are used to test the proposed model with promising results.

[1]  Eamonn J. Keogh,et al.  HOT SAX: efficiently finding the most unusual time series subsequence , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[2]  Jiang Rong.  Automatic Generation of Pan Concept Tree on Numerical Data , 2000 .

[3]  Marco van Akkeren,et al.  A GARCH forecasting model to predict day-ahead electricity prices , 2005, IEEE Transactions on Power Systems.

[4]  J. Contreras,et al.  Forecasting Next-Day Electricity Prices by Time Series Models , 2002, IEEE Power Engineering Review.

[5]  P. Luh,et al.  Selecting input factors for clusters of Gaussian radial basis function networks to improve market clearing price prediction , 2003 .

[6]  Zhao Yang Dong,et al.  Short-term electricity price forecasting using wavelet and SVM techniques , 2003 .

[7]  A.J. Conejo,et al.  Day-ahead electricity price forecasting using the wavelet transform and ARIMA models , 2005, IEEE Transactions on Power Systems.

[8]  Jiawei Han,et al.  Dynamic Generation and Refinement of Concept Hierarchies for Knowledge Discovery in Databases , 1994, KDD Workshop.

[9]  Z. Dong,et al.  Electricity market price spike forecast with data mining techniques , 2005 .

[10]  Junhua Zhao,et al.  A general method for electricity market price spike analysis , 2005, IEEE Power Engineering Society General Meeting, 2005.

[11]  Antonio J. Conejo,et al.  Electricity price forecasting through transfer function models , 2006, J. Oper. Res. Soc..

[12]  D. Gan,et al.  Price forecasting using an integrated approach , 2004, 2004 IEEE International Conference on Electric Utility Deregulation, Restructuring and Power Technologies. Proceedings.

[13]  Jiawei Han,et al.  Knowledge discovery in databases: A rule-based attribute-oriented approach , 1994 .

[14]  J. Contreras,et al.  ARIMA Models to Predict Next-Day Electricity Prices , 2002, IEEE Power Engineering Review.

[15]  Xuemei Shi,et al.  Uncertainty reasoning based on cloud models in controllers , 1998 .

[16]  Arthur Tay,et al.  Time Series Forecast with Elman Neural Networks and Genetic Algorithms , 2002, Asia-Pacific Conference on Simulated Evolution and Learning.