DOI QR코드

DOI QR Code

A multi-step wind speed prediction method based on WRF simulation, an optimized data-generating model, and an error correction strategy

  • Lian Shen (School of Civil Engineering, Changsha University) ;
  • Lihua Mi (Hunan Province Research Center for Safety Control Technology and Equipment of Bridge Engineering, Changsha University of Science & Technology) ;
  • Yan Han (School of Civil Engineering, Changsha University) ;
  • Chunsheng Cai (Department of Bridge Engineering, School of Transportation, Southeast University) ;
  • Kai Li (Hunan Province Research Center for Safety Control Technology and Equipment of Bridge Engineering, Changsha University of Science & Technology) ;
  • Lidong Wang (Hunan Province Research Center for Safety Control Technology and Equipment of Bridge Engineering, Changsha University of Science & Technology)
  • Received : 2022.06.12
  • Accepted : 2023.09.10
  • Published : 2023.05.25

Abstract

Improving the accuracy of wind speed predictions is crucial to the scheduling plan and operating stability of the power grid system. However, few studies utilize the generative adversarial network (GAN) to implement wind speed predictions considering the influence of other meteorological factors. Additionally, the accuracy of wind speed predictions needs to be further improved, especially for multi-step wind speed predictions. Subsequently, a novel hybrid wind speed prediction model is proposed, including four modules: (1) data collection of the weather research and forecasting (WRF) simulation, (2) data generation of the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and GAN with the generator of bidirectional long short-term memory (BLSTM), (3) an error correction strategy of the CEEMDAN and GAN-BLSTM, and (4) hyperparameters optimization of the grid search (GS) and particle swarm optimization (PSO). Three datasets are utilized to validate the forecasting accuracy of the proposed model. The verification results demonstrate that the forecasting performance of the proposed model outperforms other baseline models. Taking the mean absolute percentage error (MAPE) of the ten-step prediction for the three datasets as an example, the MAPE values are respectively 0.51%, 0.46%, and 0.55% with correction, leading to 9.16%, 9.77%, 9.59% lower than those without correction. Above all, the proposed model possesses excellent wind speed prediction accuracy, especially in multi-step wind speed predictions, due to its lower values of MAPE with similar coefficients of determination (R2) values.

Keywords

Acknowledgement

This work was supported by the National Natural Science Foundation of China (Grant No. 52178452, 51808059), the Science and Technology Innovation Program of Hunan Province (Grant No. 2021RC4031), the Natural Science Foundation of Hunan Province (Grant No. 2021JJ40587), the Training Program for Excellent Young Innovators of Changsha of China (Grant No. kq1905005), the project of Open Fund of Hunan Province Research Center for Safety Control Technology and Equipment of Bridge Engineering (18 KC04, 14KC07), the Educational Commission of Hunan Province of China (22A0596).

References

  1. Altan, A., Karasu, S. and Zio, E. (2021), "A new hybrid model for wind speed forecasting combining long short-term memory neural network, decomposition methods and grey wolf optimizer", Appl. Soft Comput., 100, 106996. https://doi.org/10.1016/j.asoc.2020.106996.
  2. Chen, Y.R., Wang, Y., Dong, Z.K., Su, J., Han, Z.L., Zhou, D., Zhao, Y.S. and Bao, Y. (2021), "2-D regional short-term wind speed forecast based on CNN-LSTM deep learning model", Energy Convers. Manage., 244, 114451. https://doi.org/10.1016/j.enconman.2021.114451.
  3. Croonenbroeck, C. and Ambach, D. (2015), "A selection of time series models for short- to medium-term wind power forecasting", J. Wind Eng. Ind. Aerod., 136, 201-210. https://doi.org/10.1016/j.jweia.2014.11.014.
  4. Dayal, K.K., Bellon, G., Cater, J.E., Kingan, M.J. and Sharma, R.N. (2021), "High-resolution mesoscale wind-resource assessment of Fiji using the Weather Research and Forecasting (WRF) model", Energy, 232, 121047. https://doi.org/10.1016/j.energy.2021.121047.
  5. Duan, J.K., Zuo, H.C., Bai, Y.L., Duan, J.Z., Chang, M.H. and Chen, B.L. (2021), "Short-term wind speed forecasting using recurrent neural networks with error correction", Energy, 217, 119397. https://doi.org/10.1016/j.energy.2020.119397.
  6. Emeksiz, C. and Tan, M. (2022), "Multi-step wind speed forecasting and Hurst analysis using novel hybrid secondary decomposition approach", Energy, 238(PartA), 121764. https://doi.org/10.1016/j.energy.2021.121764.
  7. Heng, J.N., Hong, Y.M., Hu, J.M. and Wang, S.Y. (2022), "Probabilistic and deterministic wind speed forecasting based on non-parametric approaches and wind characteristics information", Appl. Energy, 306(Part A), 118029. https://doi.org/10.1016/j.apenergy.2021.118029.
  8. Hu, H.L., Wang, L. and Tao, R. (2021), "Wind speed forecasting based on variational mode decomposition and improved echo state network", Renew. Energy, 164, 729-751. https://doi.org/10.1016/j.renene.2020.09.109.
  9. Hu, J.M., Heng, J.N., Wen, J.M. and Zhao, W.G. (2020), "Deterministic and probabilistic wind speed forecasting with de-noising-reconstruction strategy and quantile regression based algorithm", Renew. Energy, 162, 1208-1226. https://doi.org/10.1016/j.renene.2020.08.077.
  10. Jager, D. and Andreas, A. (1996), NREL National Wind Technology Center (NWTC): M2 Tower; Boulder, Colorado (Data), NREL Report No. DA-5500-56489. http://dx.doi.org/10.5439/1052222.
  11. Jahangir, H., Golkar, M.A., Alhameli, F., Mazouz, A., Ahmadian, A. and Elkamel, A. (2020), "Short-term wind speed forecasting framework based on stacked denoising auto-encoders with rough ANN", Sustain. Energy Techn., 38, 100601. https://doi.org/10.1016/j.seta.2019.100601.
  12. Kennedy, J. and Eberhart, R. (1995), "Particle swarm optimization", Proceedings of the International Conference on Neural Networks, 1942-1948. https://doi.org/10.1109/ICNN.1995.488968.
  13. Li, D., Jiang, F.X., Chen, M. and Qian, T. (2022), "Multi-step-ahead wind speed forecasting based on a hybrid decomposition method and temporal convolutional networks", Energy, 238 (Part C), 121981. https://doi.org/10.1016/j.energy.2021.121981.
  14. Lim, J.Y., Kim, S., Kim, H.K. and Kim, Y.K. (2022), "Long short-term memory (LSTM)-based wind speed prediction during a typhoon for bridge traffic control", J. Wind Eng. Ind. Aerod., 220, 104788. https://doi.org/10.1016/j.jweia.2021.104788.
  15. Liu, H., Tian, H.Q. and Li, Y.F. (2015), "An EMD-recursive ARIMA method to predict wind speed for railway strong wind warning system", J. Wind Eng. Ind. Aerod., 141, 27-38. https://doi.org/10.1016/j.jweia.2015.02.004.
  16. Liu, M.S., Cao, Z.M., Zhang, J., Wang, L., Huang, C. and Luo, X. (2020), "Short-term wind speed forecasting based on the Jaya-SVM model", Int. J. Elec. Power, 121, 106056. https://doi.org/10.1016/j.ijepes.2020.106056.
  17. Liu, Z.Y., Hara, R. and Kita, H. (2021), "Hybrid forecasting system based on data area division and deep learning neural network for short-term wind speed forecasting", Energy Convers. Manage., 238, 114136. https://doi.org/10.1016/j.enconman.2021.114136.
  18. Louka, P., Galanis, G., Siebert, N., Kariniotakis, G., Katsafados, P., Pytharoulis, I. and Kallos, G. (2008), "Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering", J. Wind Eng. Ind. Aerod., 96(12), 2348-2362. https://doi.org/10.1016/j.jweia.2008.03.013.
  19. Rahmani, R., Yusof, R., Seyedmahmoudian, M. and Mekhilef, S. (2013), "Hybrid technique of ant colony and particle swarm optimization for short term wind energy forecasting", J. Wind Eng. Ind. Aerod., 123(PartA), 163-170. https://doi.org/10.1016/j.jweia.2013.10.004.
  20. Salcedo-Sanz, S., Perez-Bellido, A .M., Ortiz-Garcia, E.G., Portilla-Figueras, A., Prieto, L. and Paredes, D. (2009), "Hybridizing the fifth generation mesoscale model with artificial neural networks for short-term wind speed prediction", Renew. Energy, 34, 1451-1457. https://doi.org/10.1016/j.renene.2008.10.017.
  21. Shang, Z.H., He, Z.S., Chen, Y., Chen, Y.H. and Xu, M.L. (2022), "Short-term wind speed forecasting system based on multivariate time series and multi-objective optimization", Energy, 238(PartC), 122024. https://doi.org/10.1016/j.energy.2021.122024.
  22. Sharma, R., Shikhola, T. and Kohli, J.K. (2020), "Modified fuzzy Q-learning based wind speed prediction", J. Wind Eng. Ind. Aerod., 206, 104361. https://doi.org/10.1016/j.jweia.2020.104361.
  23. Sun, N., Zhou, J.Z., Chen, L., Jia, B.J., Tayyab, M. and Peng, T. (2018), "An adaptive dynamic short-term wind speed forecasting model using secondary decomposition and an improved regularized extreme learning machine", Energy, 165 (Part B), 939-957. https://doi.org/10.1016/j.energy.2018.09.180.
  24. Sun, W., Tan, B. and Wang, Q.Q. (2021), "Multi-step wind speed forecasting based on secondary decomposition algorithm and optimized back propagation neural network", Appl. Soft Comput., 113(PartA), 107894. https://doi.org/10.1016/j.asoc.2021.107894.
  25. Sun, Z.X., Zhao, M.Y., Dong, Y., Cao, X. and Sun, H.X. (2021), "Hybrid model with secondary decomposition, randomforest algorithm, clustering analysis and long short memory network principal computing for short-term wind power forecasting on multiple scales", Energy, 221, 119848. https://doi.org/10.1016/j.energy.2021.119848.
  26. Wang, H., Zhang, Y.M., Mao, J.X. and Wan, H.P. (2020), "A probabilistic approach for short-term prediction of wind gust speed using ensemble learning", J. Wind Eng. Ind. Aerod., 202, 104198. https://doi.org/10.1016/j.jweia.2020.104198.
  27. Wang, J. and Yang, Z.S. (2021), "Ultra-short-term wind speed forecasting using an optimized artificial intelligence algorithm", Renew. Energy, 171, 1418-1435. https://doi.org/10.1016/j.renene.2021.03.020.
  28. Wei, D.X., Wang, J.Z., Niu, X.S. and Li, Z.W. (2021), "Wind speed forecasting system based on gated recurrent units and convolutional spiking neural networks", Appl. Energy, 292, 116842. https://doi.org/10.1016/j.apenergy.2021.116842.
  29. Xiang, L., Li, J.X., Hu, A.J. and Zhang, Y. (2020), "Deterministic and probabilistic multi-step forecasting for short-term wind speed based on secondary decomposition and a deep learning method", Energy Conver. Manag., 220, 113098. https://doi.org/10.1016/j.enconman.2020.113098.
  30. Yang, W.D., Tian, Z.R. and Hao, Y. (2022), "A novel ensemble model based on artificial intelligence and mixed-frequency techniques for wind speed forecasting", Energy Convers. Manage., 252, 115086. https://doi.org/10.1016/j.enconman.2021.115086.
  31. Yu, C.J., Li, Y.L., Xiang, H.Y. and Zhang, M.J. (2018), "Data mining-assisted short-term wind speed forecasting by wavelet packet decomposition and Elman neural network", J. Wind Eng. Ind. Aerod., 175, 136-143. https://doi.org/10.1016/j.jweia.2018.01.020.
  32. Zhang, G.W. and Liu, D. (2020), "Causal convolutional gated recurrent unit network with multiple decomposition methods for short-term wind speed forecasting", Energy Convers. Manage., 226, 113500. https://doi.org/10.1016/j.enconman.2020.113500.
  33. Zhang, L.F., Wang, J.Z., Niu, X.S. and Liu, Z.K. (2021), "Ensemble wind speed forecasting with multi-objective Archimedes optimization algorithm and sub-model selection", Appl. Energy, 301, 117449. https://doi.org/10.1016/j.apenergy.2021.117449.
  34. Zhang, Y.G., Pan, G.F., Chen, B., Han, J.Y., Zhao, Y. and Zhang, C.H. (2020), "Short-term wind speed prediction model based on GA-ANN improved by VMD", Renew. Energy, 156, 1373-1388. https://doi.org/10.1016/j.renene.2019.12.047.