Application of recurrent neural network for short term load forecasting in electric power system
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5, 2694-2698
- https://doi.org/10.1109/icnn.1995.487837
Abstract
In recent years multilayered feedforward networks with backpropagation learning algorithm have been extensively applied to short term load forecasting in electric power systems with very good results. In this paper we investigate the feasibility of applying recurrent neural network (RNN) for short term load forecasting. Different network architectures from fully recurrent (complete connectivity) to no feedback paths (only feedforward paths) are modelled and their characteristics for short term load forecasting are compared.Keywords
This publication has 4 references indexed in Scilit:
- Electric load forecasting using an artificial neural networkIEEE Transactions on Power Systems, 1991
- An expert system based algorithm for short term load forecastIEEE Transactions on Power Systems, 1988
- Generalization of back-propagation to recurrent neural networksPhysical Review Letters, 1987
- Short-term load forecastingProceedings of the IEEE, 1987