论文信息 - Badanie jakości predykcji obciążeń elektroenergetycznych za pomocą sieci neuronowych SVM, RBF i MLP

Badanie jakości predykcji obciążeń elektroenergetycznych za pomocą sieci neuronowych SVM, RBF i MLP

This paper compares three methods of load forecasting in a small power system in Poland. The solution is based on application of the SVM, RBF and MLP neural networks. The simulations of neural networks performed in MATLAB were conducted for two tasks of prognosis: one hour ahead and 24-hour ahead. The results have been compared to the naive prognoses. Comparison of three methods of load forecasting in a small power system based on neural networks

Stanislaw Osowski | T. Ciechulski

[1] Tomonobu Senjyu,et al. A neural network based several-hour-ahead electric load forecasting using similar days approach , 2006 .

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

[3] Maarouf Saad,et al. An efficient approach for short term load forecasting using artificial neural networks , 2006 .

[4] Krzysztof Siwek,et al. Regularization of neural networks for improved load forecasting in power system , 2001, ICECS 2001. 8th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.01EX483).

[5] Amaury Lendasse,et al. Methodology for long-term prediction of time series , 2007, Neurocomputing.

[6] Krzysztof Siwek,et al. The selforganizing neural network approach to load forecasting in the power system , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).