A regime-switching recurrent neural network model applied to wind time series

Nikolay Y. Nikolaev*, Evgueni Smirnov, Daniel Stamate, Robert Zimmer

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Web of Science)

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 languageEnglish
Pages (from-to)723-734
Number of pages12
JournalApplied Soft Computing
Volume80
DOIs
Publication statusPublished - Jul 2019

Keywords

  • FORECASTING WIND
  • DENSITY FORECASTS
  • SPEED
  • POWER
  • ENSEMBLE

Cite this