A multimodal approach to chaotic renewable energy prediction using meteorological and historical information
Wind energy, which exhibits non-stationarity, randomness, and intermittency, is inextricably linked to meteorological data. The wind power series can be broken down into several subsequences using data decomposition techniques to make forecasting simpler and more accurate. Because of this, a single...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Elsevier
2022
|
| Subjects: | |
| Online Access: | https://eprints.ums.edu.my/id/eprint/32766/1/A%20multimodal%20approach%20to%20chaotic%20renewable%20energy%20prediction%20using%20meteorological%20and%20historical%20information.ABSTRACT.pdf https://eprints.ums.edu.my/id/eprint/32766/2/A%20multimodal%20approach%20to%20chaotic%20renewable%20energy%20prediction%20using%20meteorological%20and%20historical%20information.pdf |
| _version_ | 1825714753287225344 |
|---|---|
| author | Goh, Hui Hwang He, Ronghui Zhang, Dongdong Liu, Hui Dai, Wei Lim, Chee Shen Tonni Agustiono Kurniawan Teo, Kenneth Tze Kin Goh, Kai Chen |
| author_facet | Goh, Hui Hwang He, Ronghui Zhang, Dongdong Liu, Hui Dai, Wei Lim, Chee Shen Tonni Agustiono Kurniawan Teo, Kenneth Tze Kin Goh, Kai Chen |
| author_sort | Goh, Hui Hwang |
| collection | UMS |
| description | Wind energy, which exhibits non-stationarity, randomness, and intermittency, is inextricably linked to meteorological data. The wind power series can be broken down into several subsequences using data decomposition techniques to make forecasting simpler and more accurate. Because of this, a single prediction model does not perform well in extracting hidden information from each subsequence. To predict different frequency series, this paper employed shallow and deep learning models and proposed an improved hybrid wind power prediction model based on secondary decomposition, extreme learning machines (ELM), convolutional neural networks (CNN), and bidirectional long shortterm memory (BiLSTM). To begin, secondary decomposition was employed to break down the wind power series into several components. The ELM was used to forecast the low-frequency components. Following that, CNN was utilized to reintegrate the input characteristics of the high-frequency components, followed by BiLSTM prediction. Finally, the forecasting values for each component were added to generate the final prediction results. For one-, two-, and three-step predictions, the model was applied to the La Haute Borne wind farm. Additionally, four comparative experiments were conducted to validate the model’s usefulness. The suggested model’s mean absolute error (MAE), mean absolute percentage error (MAPE), and R-squared (R2) values for one-step prediction of the March data were 14.87 kW, 22.24 kW, and 0.984, respectively, which indicate the proposed model’s superiority to other prediction models. |
| first_indexed | 2024-03-06T03:16:29Z |
| format | Article |
| id | ums.eprints-32766 |
| institution | Universiti Malaysia Sabah |
| language | English English |
| last_indexed | 2024-03-06T03:16:29Z |
| publishDate | 2022 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | ums.eprints-327662022-06-09T04:37:53Z https://eprints.ums.edu.my/id/eprint/32766/ A multimodal approach to chaotic renewable energy prediction using meteorological and historical information Goh, Hui Hwang He, Ronghui Zhang, Dongdong Liu, Hui Dai, Wei Lim, Chee Shen Tonni Agustiono Kurniawan Teo, Kenneth Tze Kin Goh, Kai Chen QC851-999 Meteorology. Climatology Including the earth's atmosphere TJ807-830 Renewable energy sources Wind energy, which exhibits non-stationarity, randomness, and intermittency, is inextricably linked to meteorological data. The wind power series can be broken down into several subsequences using data decomposition techniques to make forecasting simpler and more accurate. Because of this, a single prediction model does not perform well in extracting hidden information from each subsequence. To predict different frequency series, this paper employed shallow and deep learning models and proposed an improved hybrid wind power prediction model based on secondary decomposition, extreme learning machines (ELM), convolutional neural networks (CNN), and bidirectional long shortterm memory (BiLSTM). To begin, secondary decomposition was employed to break down the wind power series into several components. The ELM was used to forecast the low-frequency components. Following that, CNN was utilized to reintegrate the input characteristics of the high-frequency components, followed by BiLSTM prediction. Finally, the forecasting values for each component were added to generate the final prediction results. For one-, two-, and three-step predictions, the model was applied to the La Haute Borne wind farm. Additionally, four comparative experiments were conducted to validate the model’s usefulness. The suggested model’s mean absolute error (MAE), mean absolute percentage error (MAPE), and R-squared (R2) values for one-step prediction of the March data were 14.87 kW, 22.24 kW, and 0.984, respectively, which indicate the proposed model’s superiority to other prediction models. Elsevier 2022-01-31 Article PeerReviewed text en https://eprints.ums.edu.my/id/eprint/32766/1/A%20multimodal%20approach%20to%20chaotic%20renewable%20energy%20prediction%20using%20meteorological%20and%20historical%20information.ABSTRACT.pdf text en https://eprints.ums.edu.my/id/eprint/32766/2/A%20multimodal%20approach%20to%20chaotic%20renewable%20energy%20prediction%20using%20meteorological%20and%20historical%20information.pdf Goh, Hui Hwang and He, Ronghui and Zhang, Dongdong and Liu, Hui and Dai, Wei and Lim, Chee Shen and Tonni Agustiono Kurniawan and Teo, Kenneth Tze Kin and Goh, Kai Chen (2022) A multimodal approach to chaotic renewable energy prediction using meteorological and historical information. Applied Soft Computing, 118. pp. 1-17. ISSN 1568-4946 https://www.sciencedirect.com/science/article/abs/pii/S1568494622000412 https://doi.org/10.1016/j.asoc.2022.108487 https://doi.org/10.1016/j.asoc.2022.108487 |
| spellingShingle | QC851-999 Meteorology. Climatology Including the earth's atmosphere TJ807-830 Renewable energy sources Goh, Hui Hwang He, Ronghui Zhang, Dongdong Liu, Hui Dai, Wei Lim, Chee Shen Tonni Agustiono Kurniawan Teo, Kenneth Tze Kin Goh, Kai Chen A multimodal approach to chaotic renewable energy prediction using meteorological and historical information |
| title | A multimodal approach to chaotic renewable energy prediction using meteorological and historical information |
| title_full | A multimodal approach to chaotic renewable energy prediction using meteorological and historical information |
| title_fullStr | A multimodal approach to chaotic renewable energy prediction using meteorological and historical information |
| title_full_unstemmed | A multimodal approach to chaotic renewable energy prediction using meteorological and historical information |
| title_short | A multimodal approach to chaotic renewable energy prediction using meteorological and historical information |
| title_sort | multimodal approach to chaotic renewable energy prediction using meteorological and historical information |
| topic | QC851-999 Meteorology. Climatology Including the earth's atmosphere TJ807-830 Renewable energy sources |
| url | https://eprints.ums.edu.my/id/eprint/32766/1/A%20multimodal%20approach%20to%20chaotic%20renewable%20energy%20prediction%20using%20meteorological%20and%20historical%20information.ABSTRACT.pdf https://eprints.ums.edu.my/id/eprint/32766/2/A%20multimodal%20approach%20to%20chaotic%20renewable%20energy%20prediction%20using%20meteorological%20and%20historical%20information.pdf |
| work_keys_str_mv | AT gohhuihwang amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT heronghui amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT zhangdongdong amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT liuhui amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT daiwei amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT limcheeshen amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT tonniagustionokurniawan amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT teokennethtzekin amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT gohkaichen amultimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT gohhuihwang multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT heronghui multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT zhangdongdong multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT liuhui multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT daiwei multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT limcheeshen multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT tonniagustionokurniawan multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT teokennethtzekin multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation AT gohkaichen multimodalapproachtochaoticrenewableenergypredictionusingmeteorologicalandhistoricalinformation |