A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning
Short-term wind speed forecasting plays an increasingly important role in the security, scheduling, and optimization of power systems. As wind speed signals are usually nonlinear and nonstationary, how to accurately forecast future states is a challenge for existing methods. In this paper, for highl...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/8811407 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849306154200465408 |
|---|---|
| author | Yuanyuan Xu Genke Yang |
| author_facet | Yuanyuan Xu Genke Yang |
| author_sort | Yuanyuan Xu |
| collection | DOAJ |
| description | Short-term wind speed forecasting plays an increasingly important role in the security, scheduling, and optimization of power systems. As wind speed signals are usually nonlinear and nonstationary, how to accurately forecast future states is a challenge for existing methods. In this paper, for highly complex wind speed signals, we propose a multiple kernel learning- (MKL-) based method to adaptively assign the weights of multiple prediction functions, which extends conventional wind speed forecasting methods using a support vector machine. First, empirical mode decomposition (EMD) is used to decompose complex signals into several intrinsic mode function component signals with different time scales. Then, for each channel, one multiple kernel model is constructed for forecasting the current sequence signal. Finally, several experiments are carried out on different New Zealand wind farm data, and the relevant prediction accuracy indexes and confidence intervals are evaluated. Extensive experimental results show that, compared with existing machine learning methods, the EMD-MKL model proposed in this paper has better performance in terms of the prediction accuracy evaluation indexes and confidence intervals and shows a better ability to generalize. |
| format | Article |
| id | doaj-art-385730b62c6f49aaa18ce3ea0f8aeec7 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-385730b62c6f49aaa18ce3ea0f8aeec72025-08-20T03:55:11ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/88114078811407A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel LearningYuanyuan Xu0Genke Yang1Department of Automation, Shanghai Jiaotong University, Shanghai 200240, ChinaDepartment of Automation, Shanghai Jiaotong University, Shanghai 200240, ChinaShort-term wind speed forecasting plays an increasingly important role in the security, scheduling, and optimization of power systems. As wind speed signals are usually nonlinear and nonstationary, how to accurately forecast future states is a challenge for existing methods. In this paper, for highly complex wind speed signals, we propose a multiple kernel learning- (MKL-) based method to adaptively assign the weights of multiple prediction functions, which extends conventional wind speed forecasting methods using a support vector machine. First, empirical mode decomposition (EMD) is used to decompose complex signals into several intrinsic mode function component signals with different time scales. Then, for each channel, one multiple kernel model is constructed for forecasting the current sequence signal. Finally, several experiments are carried out on different New Zealand wind farm data, and the relevant prediction accuracy indexes and confidence intervals are evaluated. Extensive experimental results show that, compared with existing machine learning methods, the EMD-MKL model proposed in this paper has better performance in terms of the prediction accuracy evaluation indexes and confidence intervals and shows a better ability to generalize.http://dx.doi.org/10.1155/2020/8811407 |
| spellingShingle | Yuanyuan Xu Genke Yang A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning Complexity |
| title | A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning |
| title_full | A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning |
| title_fullStr | A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning |
| title_full_unstemmed | A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning |
| title_short | A Short-Term Wind Speed Forecasting Hybrid Model Based on Empirical Mode Decomposition and Multiple Kernel Learning |
| title_sort | short term wind speed forecasting hybrid model based on empirical mode decomposition and multiple kernel learning |
| url | http://dx.doi.org/10.1155/2020/8811407 |
| work_keys_str_mv | AT yuanyuanxu ashorttermwindspeedforecastinghybridmodelbasedonempiricalmodedecompositionandmultiplekernellearning AT genkeyang ashorttermwindspeedforecastinghybridmodelbasedonempiricalmodedecompositionandmultiplekernellearning AT yuanyuanxu shorttermwindspeedforecastinghybridmodelbasedonempiricalmodedecompositionandmultiplekernellearning AT genkeyang shorttermwindspeedforecastinghybridmodelbasedonempiricalmodedecompositionandmultiplekernellearning |