Application of rough set theory and artificial neural network for load forecasting

Accurate forecasting model requires the ability to select relevant factors so that the influences of irrelevant factors can be reduced substantially. The rough set theory in data mining, which provides a useful tool to analyze data can help solve the above problem. This paper proposes a novel hybrid method to integrate the rough set theory, genetic algorithm and artificial neural network. Our method consists of two stages: in the first procedure, the rough set theory and genetic algorithm are applied to find relevant factors to the load and the results are used as inputs of the neural network; in the second procedure, an active selection of training sets is carried out by k-nearest neighbors, and the neural network is used to predict the load. The method is characterized not only by using attribute reduction as a preprocessing technique of the neural network, but also presenting an improved attribute reduction algorithm. The prediction accuracy is improved by applying the method on a real power system, which shows that the proposed method is promising for load forecasting in power systems.

[1]  H. Mori,et al.  Deterministic annealing clustering for ANN- based short-term load forecasting , 2001, PICA 2001. Innovative Computing for Power - Electric Energy Meets the Market. 22nd IEEE Power Engineering Society. International Conference on Power Industry Computer Applications (Cat. No.01CH37195).

[2]  W. Charytoniuk,et al.  Very short-term load forecasting using artificial neural networks , 2000 .

[3]  Saifur Rahman,et al.  Short-term load forecasting with local ANN predictors , 1999 .

[4]  Nick Cercone,et al.  Applying Knowledge Discovery to Predict Water-Supply Consumption , 1997, IEEE Expert.

[5]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[6]  Hiroyuki Mori,et al.  Short-term load forecasting with fuzzy regression tree in power systems , 2001, 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236).

[7]  Gonzalo Joya,et al.  Global model for short-term load forecasting using artificial neural networks , 2002 .

[8]  Xiaohua Hu,et al.  Mining knowledge rules from databases: a rough set approach , 1996, Proceedings of the Twelfth International Conference on Data Engineering.

[9]  Y.-Y. Hsu,et al.  Short term load forecasting using a multilayer neural network with an adaptive learning algorithm , 1992 .