Adaptively trained neural networks and their application to electric load forecasting
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1125-1128 vol.2
- https://doi.org/10.1109/iscas.1991.176564
Abstract
A training procedure that adapts the weights of a trained layered perceptron type artificial neural network to training data originating from a slowly varying nonstationary process is proposed. The procedure for adaptive dating assures proper response to previous training data by seeking to minimize a weight sensitivity cost function while, at the same time, minimizing the mean square error normally ascribed to the layered perceptron. The process is illustrated through application to an interpolation problem and by its use on an electric load forecasting problem with data collected from the power industry.<>Keywords
This publication has 5 references indexed in Scilit:
- An adaptively trained neural networkIEEE Transactions on Neural Networks, 1991
- Electric load forecasting using an artificial neural networkIEEE Transactions on Power Systems, 1991
- Preliminary results on using artificial neural networks for security assessment (of power systems)IEEE Transactions on Power Systems, 1991
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- On the identification of control systems by the quasi-linearization methodIEEE Transactions on Automatic Control, 1964