Research on Short-Term Prediction Methods for Small-Scale Three-Dimensional Wind Fields
Abstract
:1. Introduction
2. WRF-CFD Coupled Small-Scale Wind Field Simulation
2.1. WRF Model Settings
2.2. CFD Model Settings
2.3. Analysis of CFD Results
3. ConvLSTM-DSConvGRU Hybrid Prediction Model
3.1. ConvLSTM
3.2. ConvGRU
3.3. Depthwise Separable Convolution
3.4. Improved Hybrid Network
- (1)
- The encoder module consists of two ConvLSTM layers and one DSConvGRU layer. A BatchNorm layer is added after each of the network layers to regularise the output results and accelerate the training process while improving the model stability. The encoder is used to receive samples of WRF output variables and extract the spatiotemporal features of the variable sequence, compressing the high-dimensional input frame sequence into a low-dimensional vector that contains historical spatiotemporal information.
- (2)
- The decoder module consists of one DSConvGRU layer, two ConvLSTM layers, and one Conv3D layer. The DSConvGRU layer and ConvLSTM layers are used to decode the spatiotemporal feature vector output from the encoder module. Finally, the Conv3D layer compresses the last dimension of the decoded feature vector and unfolds it into an output frame sequence.
3.5. Small-Scale Wind Field Prediction Model
4. Experimental Simulation and Result Analysis
4.1. Construction of Datasets
4.2. Experimental Environment
4.3. Evaluation Indicators for Prediction Performance
4.4. Ablation Experiment
4.5. Comparison between Different Prediction Models
4.6. Visualisation of Boundary Condition Prediction Results
5. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Castorrini, A.; Gentile, S.; Geraldi, E.; Bonfiglioli, A. Investigations on offshore wind turbine inflow modelling using numerical weather prediction coupled with local-scale computational fluid dynamics. Renew. Sustain. Energy Rev. 2023, 171, 113008. [Google Scholar] [CrossRef]
- Barbaresco, F.; Thobois, L.; Dolfi-Bouteyre, A.; Jeannin, N.; Wilson, R.; Valla, M.; Hallermeyer, A.; Feneyrou, P.; Brion, V.; Besson, L.; et al. Monitoring wind, turbulence and aircraft wake vortices by high resolution RADAR and LIDAR remote sensors in all weather conditions. EMBO Rep. 2015, 7, 1140–1146. [Google Scholar]
- Keohan, C. Ground-based wind shear detection systems have become vital to safe operations. ICAO J. 2007, 62, 16–34. [Google Scholar]
- Li, S.; Sun, X.; Zhang, S.; Zhao, S.; Zhang, R. A study on microscale wind simulations with a coupled WRF–CFD model in the chongli mountain region of Hebei Province, China. Atmos. Multidiscip. Digit. Publ. Inst. 2019, 10, 731. [Google Scholar] [CrossRef]
- Yang, Y.; Tan, J.; Jin, B.; Liu, M. Multi-scale simulation on the wind field for complex terrain based on coupled WRF and CFD techniques. J. South China Univ. Technol. (Nat. Sci. Ed.) 2021, 49, 10. [Google Scholar]
- Luo, X.; Cao, Y. Simulation of the wind fields over complex terrain with coupling of CFD and WRF. J. Comput. Methods Sci. Eng. 2021, 21, 1155–1166. [Google Scholar] [CrossRef]
- Chen, F.; Peng, H.; Chan, P.W.; Huang, Y.; Hon, K.K. Identification and analysis of terrain-induced low-level windshear at Hong Kong International Airport based on WRF–LES combining method. Meteorol. Atmos. Phys. 2022, 134, 60. [Google Scholar] [CrossRef]
- Li, L.; Chan, P.W. Numerical simulation study of the effect of buildings and complex terrain on the low-level winds at an airport in typhoon situation. Meteorol. Z. 2012, 21, 183–192. [Google Scholar] [CrossRef]
- Gao, H.; Shen, C.; Zhou, Y.; Wang, X.; Chan, P.-W.; Hon, K.-K.; Zhou, D.; Li, J. A spatio-temporal neural network for fine-scale wind field nowcasting based on lidar observation. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2022, 15, 5596–5606. [Google Scholar] [CrossRef]
- Nijhuis, A.O.; Krasnov, O.K.; Unal, C.M.H.; Russchenberg, H.W.J.; Yarovoy, A. Outlook for a new wind field retrieval technique: The 4D-Var wind retrieval. In Proceedings of the 2014 International Radar Conference, Lille, France, 13–17 October 2014; pp. 1–6. [Google Scholar]
- Rihan, F.A.; Collier, C.G.; Roulstone, I. Four-dimensional variational data assimilation for Doppler radar wind data. J. Comput. Appl. Math. 2005, 176, 15–34. [Google Scholar] [CrossRef]
- Bauer, P.; Thorpe, A.; Brunet, G. The quiet revolution of numerical weather prediction. Nature 2015, 525, 47–55. [Google Scholar] [CrossRef]
- Lam, R.; Sanchez-Gonzalez, A.; Willson, M.; Wirnsberger, P.; Fortunato, M.; Alet, F.; Ravuri, S.; Ewalds, T.; Eaton-Rosen, Z.; Hu, W.; et al. Learning skillful medium-range global weather forecasting. Science 2023, 382, 1416–1421. [Google Scholar] [CrossRef]
- Bi, K.; Xie, L.; Zhang, H.; Chen, X.; Gu, X.; Tian, Q. Pangu-weather: A 3d high-resolution model for fast and accurate global weather forecast. arXiv 2022, arXiv:2211.02556. [Google Scholar]
- Pathak, J.; Subramanian, S.; Harrington, P.; Raja, S.; Chattopadhyay, A.; Mardani, M.; Kurth, T.; Hall, D.; Li, Z.; Azizzadenesheli, K.; et al. Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators. arXiv 2022, arXiv:2202.11214. [Google Scholar]
- Zhu, Q.; Chen, J.; Shi, D.; Zhu, L.; Bai, X.; Duan, X.; Liu, Y. Learning temporal and spatial correlations jointly: A unified framework for wind speed prediction. IEEE Trans. Sustain. Energy 2020, 11, 509–523. [Google Scholar] [CrossRef]
- Yetis, Y.; Tehrani, K.; Jamshidi, M. Wind speed forecasting using machine learning approach based on meteorological data-a case study. Energy Environ. Res. 2022, 12, 1–11. [Google Scholar] [CrossRef]
- Woo, S.; Park, J.; Park, J.; Manuel, L. Wind field-based short-term turbine response forecasting by stacked dilated convolutional LSTMs. IEEE Trans. Sustain. Energy 2020, 11, 2294–2304. [Google Scholar] [CrossRef]
- Sari, A.P.; Suzuki, H.; Kitajima, T.; Yasuno, T.; Prasetya, D.A.; Nachrowie, N. Prediction model of wind speed and direction using convolutional neural network-long short term memory. In Proceedings of the 2020 IEEE International Conference on Power and Energy (PECon), Penang, Malaysia, 7–8 December 2020; IEEE: New York, NY, USA, 2020; pp. 356–361. [Google Scholar]
- Zhao, Z.; Yun, S.; Jia, L.; Guo, J.; Meng, Y.; He, N.; Li, X.; Shi, J.; Yang, L. Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features. Eng. Appl. Artif. Intell. 2023, 121, 105982. [Google Scholar] [CrossRef]
- Tewari, M.; Kusaka, H.; Chen, F.; Coirier, W.J.; Kim, S.; Wyszogrodzki, A.A.; Warner, T.T. Impact of coupling a microscale computational fluid dynamics model with a mesoscale model on urban scale contaminant transport and dispersion. Atmos. Res. 2010, 96, 656–664. [Google Scholar] [CrossRef]
- Hon, K.K. Simulated satellite imagery at sub-kilometre resolution by the Hong Kong Observatory. Weather 2018, 73, 139–144. [Google Scholar] [CrossRef]
- Li, L.; Zhang, L.; Chen, B. The Application of CFD Techniques on the Wind Field Simulation over Steep Mountains: A Method Study. Acta Meteorol. Sin. 2016, 74, 613–622. [Google Scholar]
- Xie, Z.T. Modelling street-scale flow and dispersion in realistic winds—Towards coupling with mesoscale meteorological models. Bound.-Layer Meteorol. 2011, 141, 53–75. [Google Scholar] [CrossRef]
- Li, L.; Zhang, L.J.; Zhang, N.; Hu, F.; Jiang, Y.; Jiang, W. Application of FLUENT on the fine-scale simulation of the wind field over complex terrain. Plateau Meteor 2010, 29, 621–628. [Google Scholar]
- Li, L.; Chan, P.W.; Zhang, L.-J.; Mao, H. Numerical simulation of terrain-induced vortex/wave shedding at the Hong Kong International Airport. Meteorol. Z. 2013, 22, 317–327. [Google Scholar] [CrossRef]
- Shi, X.; Chen, Z.; Wang, H.; Yeung, D.Y.; Wong, W.K.; Woo, W.C. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Adv. Neural Inf. Process. Syst. 2015, 28, 802–810. [Google Scholar]
- Ballas, N.; Yao, L.; Pal, C.; Courville, A. Delving deeper into convolutional networks for learning video representations. Comput. Sci. 2015, 1511, 06432. [Google Scholar]
- Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv 2017, arXiv:1704.04861. [Google Scholar]
- Helmy, I.; Tarafder, P.; Choi, W. LSTM-GRU model-based channel prediction for one-bit massive MIMO system. IEEE Trans. Veh. Technol. 2023, 72, 11053–11057. [Google Scholar] [CrossRef]
- Ali, M.; Hassan, M.; Kifayat, K.; Kim, J.Y.; Hakak, S.; Khan, M.K. Social media content classification and community detection using deep learning and graph analytics. Technol. Forecast. Soc. Chang. 2023, 188, 122252. [Google Scholar] [CrossRef]
- Cheng, L.; Zang, H.; Ding, T.; Sun, R.; Wang, M.; Wei, Z.; Sun, G. Ensemble recurrent neural network based probabilistic wind speed forecasting approach. Energies 2018, 11, 1958. [Google Scholar] [CrossRef]
- Mathieu, M.; Couprie, C.; LeCun, Y. Deep multi-scale video prediction beyond mean square error. In International Conference on Learning Representations; ICLR Press: San Juan, Puerto Rico, 2016; pp. 1–14. [Google Scholar]
- Lin, Z.; Li, M.; Zheng, Z.; Cheng, Y.; Yuan, C. Self-attention convlstm for spatiotemporal prediction. Proc. AAAI Conf. Artif. Intell. 2020, 34, 11531–11538. [Google Scholar] [CrossRef]
- Tran, D.; Bourdev, L.; Fergus, R.; Torresani, L.; Paluri, M. Learning spatiotemporal features with 3d convolutional networks. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7–13 December 2015; IEEE: Santiago, Chile, 2015; pp. 4489–4497. [Google Scholar]
Nested Domain | dx/km | dy/km | Number of Regional Grid Points | Regional Integration Step/s |
---|---|---|---|---|
d01 | 9 | 9 | 61 × 61 | 36 |
d02 | 3 | 3 | 61 × 61 | 12 |
d03 | 1 | 1 | 61 × 61 | 4 |
Type | Parameter | Setting |
---|---|---|
Boundary condition | Inflow boundary | Grid point speed and temperature |
Outflow boundary | Pressure outlet boundary | |
Top boundary | Grid point speed and temperature | |
Bottom boundary | Non-slip wall surface | |
Solving solution | Solver software | Fluent 2022R1 |
Turbulence model | Realizable k-ε model | |
Pressure–speed coupling scheme | SIMPLE | |
Spatial discretization scheme | Second-order upwind scheme |
Error Assessment Indicator | WRF | WRF + CFD | |
---|---|---|---|
Nearest Neighbour Interpolation | Inverse Distance Weighted Interpolation | ||
Average error (BIAS) (m·s−1) | 2.952 | 0.819 | 0.333 |
Root mean square error (RMSE) (m·s−1) | 4.684 | 2.844 | 2.724 |
Mean absolute error (MAE) (m·s−1) | 4.052 | 2.334 | 2.080 |
Model | Conv- LSTM | Conv- GRU | DSConv- GRU | Number of Parameters | Runtime (s) | RMSE1 (m/s) | MAPE1 (%) | RMSE2 (K) | MAPE2 (%) |
---|---|---|---|---|---|---|---|---|---|
1 | √ | × | × | 5.804 M | 0.968 | 1.509 | 22.1643 | 0.494 | 0.109 |
2 | × | √ | × | 4.354 M | 0.768 | 1.449 | 20.2898 | 0.471 | 0.105 |
3 | × | × | √ | 0.494 M | 0.353 | 1.475 | 21.5941 | 0.480 | 0.107 |
4 | √ | √ | × | 5.243 M | 0.859 | 1.386 | 19.2707 | 0.470 | 0.104 |
5 | √ | × | √ | 3.767 M | 0.735 | 1.384 | 18.3817 | 0.465 | 0.102 |
Method | Number of Parameters | Runtime (s) | RMSE1 (m/s) | MAPE1 (%) | RMSE2 (K) | MAPE2 (%) |
---|---|---|---|---|---|---|
2D-CNN | 0.697 M | 0.198 | 1.678 | 28.688 | 0.596 | 0.226 |
3D-CNN | 2.475 M | 0.370 | 1.549 | 23.669 | 0.537 | 0.121 |
3D-ConvLSTM | 11.596 M | 1.735 | 1.448 | 18.778 | 0.462 | 0.100 |
SA-ConvLSTM | 5.933 M | 1.194 | 1.545 | 23.509 | 0.499 | 0.111 |
The algorithm of this study | 3.767 M | 0.735 | 1.384 | 18.382 | 0.465 | 0.102 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ma, Y.; Han, H.; Tang, X.; Chan, P.-W. Research on Short-Term Prediction Methods for Small-Scale Three-Dimensional Wind Fields. Appl. Sci. 2024, 14, 1871. https://doi.org/10.3390/app14051871
Ma Y, Han H, Tang X, Chan P-W. Research on Short-Term Prediction Methods for Small-Scale Three-Dimensional Wind Fields. Applied Sciences. 2024; 14(5):1871. https://doi.org/10.3390/app14051871
Chicago/Turabian StyleMa, Yuzhao, Haoran Han, Xu Tang, and Pak-Wai Chan. 2024. "Research on Short-Term Prediction Methods for Small-Scale Three-Dimensional Wind Fields" Applied Sciences 14, no. 5: 1871. https://doi.org/10.3390/app14051871