Abstract
This paper proposes a regime-switching recurrent network model (RS-RNN) for non-stationary time series. The RS-RNN model emits a mixture density with dynamic nonlinear regimes that fit flexibly data distributions with non-Gaussian shapes. The key novelties are: development of an original representation of the means of the component distributions by dynamic nonlinear recurrent networks, and derivation of a corresponding expectation maximization (EM) training algorithm for finding the model parameters. The results show that the RS-RNN applied to a real-world wind speed time series achieves standardized residuals similar to popular previous models, but it is more accurate distribution forecasting than other linear switching (MS-AR) and nonlinear neural network (MLP and RNN) models.
Original language | English |
---|---|
Pages (from-to) | 723-734 |
Number of pages | 12 |
Journal | Applied Soft Computing |
Volume | 80 |
DOIs | |
Publication status | Published - Jul 2019 |
Keywords
- FORECASTING WIND
- DENSITY FORECASTS
- SPEED
- POWER
- ENSEMBLE