Uncertainty modeling for chaotic time series based on optimal multi-input multi-output architecture: Application to offshore wind speed
- Publication Type:
- Journal Article
- Citation:
- Energy Conversion and Management, 2018, 156 pp. 597 - 617
- Issue Date:
- 2018-01-15
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
1-s2.0-S0196890417311238-main.pdf | Published Version | 3.41 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© 2017 Elsevier Ltd Wind energy is attracting more attention with the growing demand for energy. However, the efficient development and utilization of wind energy are restricted due to the intermittency and randomness of wind speed. Although abundant investigations concerning wind speed forecasting have been conducted by numerous researchers, most of the studies merely attach importance to point forecasts, which cannot quantitatively characterize the uncertainties as developing intervals. In this study, a novel interval prediction architecture has been designed, aiming at constructing effective prediction intervals for a wind speed series, composed of a preprocessing module, a feature selection module, an optimization module, a forecast module and an evaluation module. The feature selection module, in cooperation with the preprocessing module, is developed to determine the optimal model input. Furthermore, the forecast module optimized by the optimization module is considered a predictor for giving prediction intervals. The experimental results shed light on the architecture that not only outperforms the benchmark models considered, but also has great potential for application to wind power systems.
Please use this identifier to cite or link to this item: