A Regime-Switching Recurrent Neural Network Model Applied to Wind Time Series

Tools

Nikolaev, Nikolay; Smirnov, Evgueni; Stamate, Daniel and Zimmer, Robert. 2019. A Regime-Switching Recurrent Neural Network Model Applied to Wind Time Series. Applied Soft Computing, 80, pp. 723-734. ISSN 1568-4946 [Article]

Preview

Text
NNWIND.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Download (449kB) | Preview

Official URL: https://doi.org/10.1016/j.asoc.2019.04.009

Abstract or Description

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 elaborated switching dynamic nonlinear regimes make the RS-RNN especially attractive for describing non-stationary environmental time series. 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.

Item Type:

Article

Identification Number (DOI):

https://doi.org/10.1016/j.asoc.2019.04.009