Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization
In this paper, a novel hybrid model of decomposition and deep learning embedded with GA optimization was proposed to forecast 24-hour ahead wind speed. The historical wind speed time series was pre-processed and then decomposed into intrinsic mode functions (IMFs) using Ensemble Empirical Mode Decom...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722009581 |
| _version_ | 1828058034371297280 |
|---|---|
| author | Thi Hoai Thu Nguyen Quoc Bao Phan |
| author_facet | Thi Hoai Thu Nguyen Quoc Bao Phan |
| author_sort | Thi Hoai Thu Nguyen |
| collection | DOAJ |
| description | In this paper, a novel hybrid model of decomposition and deep learning embedded with GA optimization was proposed to forecast 24-hour ahead wind speed. The historical wind speed time series was pre-processed and then decomposed into intrinsic mode functions (IMFs) using Ensemble Empirical Mode Decomposition. Each IMFs then was trained and tested through a models of CNN-Bidirectional LSTM model. The hyperparameters of the hybrid CNN-Bi-LSTM model was optimized using GA. CNN can extract the internal characteristics of the time series directly meanwhile Bi-LSTM network can utilize the information in both forward and backward directions completely. The forecasting results of each IMFs were reconstructed to obtain the final forecast. The proposed method was applied to real WS dataset in Hanoi compared with 6 other methods. The result shows that the proposed method has demonstrated much better performance than the other methods. |
| first_indexed | 2024-04-10T21:21:24Z |
| format | Article |
| id | doaj.art-137bf53cf103499aa58c152ad23b19fe |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-04-10T21:21:24Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-137bf53cf103499aa58c152ad23b19fe2023-01-20T04:24:59ZengElsevierEnergy Reports2352-48472022-11-0185360Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimizationThi Hoai Thu Nguyen0Quoc Bao Phan1Corresponding author.; Hanoi University of Science and Technology, School of Electrical and Electronic Engineering, Viet NamHanoi University of Science and Technology, School of Electrical and Electronic Engineering, Viet NamIn this paper, a novel hybrid model of decomposition and deep learning embedded with GA optimization was proposed to forecast 24-hour ahead wind speed. The historical wind speed time series was pre-processed and then decomposed into intrinsic mode functions (IMFs) using Ensemble Empirical Mode Decomposition. Each IMFs then was trained and tested through a models of CNN-Bidirectional LSTM model. The hyperparameters of the hybrid CNN-Bi-LSTM model was optimized using GA. CNN can extract the internal characteristics of the time series directly meanwhile Bi-LSTM network can utilize the information in both forward and backward directions completely. The forecasting results of each IMFs were reconstructed to obtain the final forecast. The proposed method was applied to real WS dataset in Hanoi compared with 6 other methods. The result shows that the proposed method has demonstrated much better performance than the other methods.http://www.sciencedirect.com/science/article/pii/S2352484722009581Wind speed forecastHybrid modelDecompositionCNN-Bi-LSTMGA optimization |
| spellingShingle | Thi Hoai Thu Nguyen Quoc Bao Phan Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization Energy Reports Wind speed forecast Hybrid model Decomposition CNN-Bi-LSTM GA optimization |
| title | Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization |
| title_full | Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization |
| title_fullStr | Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization |
| title_full_unstemmed | Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization |
| title_short | Hourly day ahead wind speed forecasting based on a hybrid model of EEMD, CNN-Bi-LSTM embedded with GA optimization |
| title_sort | hourly day ahead wind speed forecasting based on a hybrid model of eemd cnn bi lstm embedded with ga optimization |
| topic | Wind speed forecast Hybrid model Decomposition CNN-Bi-LSTM GA optimization |
| url | http://www.sciencedirect.com/science/article/pii/S2352484722009581 |
| work_keys_str_mv | AT thihoaithunguyen hourlydayaheadwindspeedforecastingbasedonahybridmodelofeemdcnnbilstmembeddedwithgaoptimization AT quocbaophan hourlydayaheadwindspeedforecastingbasedonahybridmodelofeemdcnnbilstmembeddedwithgaoptimization |