A short-term electric load forecasting method using an Adaptive Multiresolution-based BiLinear Recurrent NeuralNetwork (AMBLRNN) is proposed in this paper. The AMBLRNN is based on the BLRNN that has been proven to have robust abilities in modeling and predicting time series. The learning process is further improved by using a multiresolution-based learning algorithm which employs the wavelet transform for multiresolution analysis of signal. Experiments are conducted on load data from the North-American Electric Utility (NAEU). Results show that the AMBLRNN out performs other conventional models 10%-25% in terms of MAPE (Mean Absolute Percentage Error) on forecasting accuracies.
Electric Load Forecasting Using Adaptive Multiresolution-Based Bilinear Recurrent Neural Network
2008 Congress on Image and Signal Processing ; 4 ; 393-397
2008-05-01
249959 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Long-Term Load Forecasting Using Improved Recurrent Neural Network
Online Contents | 1994
|Daily Electric Load Forecasting Using Artificial Neural Network
Online Contents | 1995
|Adaptive Maneuver Load Alleviation via Recurrent Neural Networks
Online Contents | 2016
|Adaptive Maneuver Load Alleviation via Recurrent Neural Networks
Online Contents | 2016
|