Wind and Structures

  • 제38권6호
  • /
  • Pages.461-475
  • /
  • 2024
  • /
  • 1226-6116(pISSN)
  • /
  • 1598-6225(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Multi-step wind speed forecasting synergistically using generalized S-transform and improved grey wolf optimizer

  • Ruwei Ma (School of Civil Engineering, Shanghai Normal University) ;
  • Zhexuan Zhu (Department of Civil Engineering, School of Mechanics and Engineering Science, Shanghai University) ;
  • Chunxiang Li (Department of Civil Engineering, School of Mechanics and Engineering Science, Shanghai University) ;
  • Liyuan Cao (Department of Civil Engineering, School of Mechanics and Engineering Science, Shanghai University)
  • 투고 : 2023.06.17
  • 심사 : 2024.05.22
  • 발행 : 2024.06.25
⟨ 이전 논문 다음 논문 ⟩

초록

A reliable wind speed forecasting method is crucial for the applications in wind engineering. In this study, the generalized S-transform (GST) is innovatively applied for wind speed forecasting to uncover the time-frequency characteristics in the non-stationary wind speed data. The improved grey wolf optimizer (IGWO) is employed to optimize the adjustable parameters of GST to obtain the best time-frequency resolution. Then a hybrid method based on IGWO-optimized GST is proposed to validate the effectiveness and superiority for multi-step non-stationary wind speed forecasting. The historical wind speed is chosen as the first input feature, while the dynamic time-frequency characteristics obtained by IGWO-optimized GST are chosen as the second input feature. Comparative experiment with six competitors is conducted to demonstrate the best performance of the proposed method in terms of prediction accuracy and stability. The superiority of the GST compared to other time-frequency analysis methods is also discussed by another experiment. It can be concluded that the introduction of IGWO-optimized GST can deeply exploit the time-frequency characteristics and effectively improving the prediction accuracy.

키워드

과제정보

This study is supported by the National Natural Science Foundation of China (Grant No. 52108460)

참고문헌

  1. Alexiadis, M.C., Dokopoulos, P.S., Sahsamanoglou, H.S. and Manousaridis, I.M. (1998), "Short-term forecasting of wind speed and related electrical power", Solar Energy. 63(1), 61-68.
  2. Chen, J., Zeng, G.Q., Zhou, W., Du, W. and Lu, K.D. (2018), "Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization", Energy Conversion Manage., 165, 681-695.
  3. Chen, M.R., Zeng, G.Q., Lu, K.D. and Weng, J. (2019), "A two-layer nonlinear combination method for short-term wind speed prediction based on ELM, ENN, and LSTM", IEEE Internet Things J., 6(4), 6997-7010.
  4. da Silva, A.F.G., de Andrade, C.R. and Zaparoli, E.L. (2021), "Wind power generation prediction in a complex site by comparing different numerical tools", J Wind Eng Ind Aerod. 216, 104728.
  5. De Giorgi, M.G., Campilongo, S., Ficarella, A. and Congedo, P.M. (2014), "Comparison between wind power prediction models based on wavelet decomposition with Least-Squares Support Vector Machine (LS-SVM) and Artificial Neural Network (ANN)", Energies, 7(8), 5251-5272.
  6. Diebold, F.X. (1994), "Comparing predictive accuracy (Reprinted)", J. Business Economic Statistics, 20(169), 134-144.
  7. Djurovic, I. and Stankovic, L. (1999), "A virtual instrument for time-frequency analysis", Ieee Transact. Instrumentation Measure., 48(6), 1086-1092.
  8. Djurovic, I., Sejdic, E. and Jiang, J. (2008), "Frequency-based window width optimization for S-transform", Aeu-Int. J. Electronics Commun., 62(4), 245-250.
  9. Fan, S., Xiao, N. and Dong, S. (2020), "A novel model to predict significant wave height based on long short-term memory network", Ocean Eng., 205, 107298.
  10. Heidari, A.A. and Pahlavani, P. (2017), "An efficient modified grey wolf optimizer with Levy flight for optimization tasks", Appl. Soft Comput., 60, 115-134.
  11. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural Comput., 9(8), 1735-1780.
  12. Hong, H.P. (2021), "Response and first passage probability of linear elastic SDOF systems subjected to nonstationary stochastic excitation modelled through S-transform", Struct. Safety. 88, 102007.
  13. Hong, H.P. and Cui, X.Z. (2023), "Use of transform pairs to represent and simulate nonstationary non-Gaussian process with applications", Struct. Safety. 100, 102267.
  14. Hu, W., Cheng, B., Yang, Q., Liu, Z., Yuan, Z., Li, K. and Zhang, M. (2023), "A novel two-layer hybrid model for ultra-short-term wind speed prediction based on SSP and BO-LSTM", Wind Struct., 36(5), 293-305.
  15. Hu, Y.L. and Chen, L. (2018), "A nonlinear hybrid wind speed forecasting model using LSTM network, hysteretic ELM and Differential Evolution algorithm", Energy Conversion Manage., 173, 123-142.
  16. Huang, G.B., Zhu, Q.Y. and Siew, C.K. (2006), "Extreme learning machine: Theory and applications", Neurocomputing. 70(1-3), 489-501.
  17. Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q. and Liu, H.H. (1998), "The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis", Proceedings of the Royal Society a-Mathematical Physical and Engineering Sciences. 454(1971), 903-995.
  18. Li, B., Zhang, P.L., Liu, D.S., Mi, S.S., Ren, G.Q. and Tian, H. (2011), "Feature extraction for rolling element bearing fault diagnosis utilizing generalized S transform and two-dimensional non-negative matrix factorization", J. Sound Vib., 330(10), 2388-2399.
  19. Li, C., Luo, K. and Cao, L. (2022), "Data-driven simulation of multivariate nonstationary wind velocity with explicit introduction of the time-varying coherence functions", J. Wind Eng. Ind. Aerod., 220, 104872.
  20. 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.
  21. Ling, Y., Ti, Z., You, H. and Li, Y. (2023), "A proof-of-concept study of estimating wind speed from acoustic frequency-domain signal using machine learning", Wind Struct., 36(5), 345-354.
  22. Liu, H., Tian, H.Q. and Li, Y.F. (2015), "Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms", Energy Conversion Manage., 100, 16-22.
  23. Mirjalili, S., Mirjalili, S.M. and Lewis, A. (2014), "Grey wolf optimizer", Adv. Eng. Softw., 69, 46-61.
  24. Nadimi-Shahraki, M.H., Taghian, S. and Mirjalili, S. (2021), "An improved grey wolf optimizer for solving engineering problems", Expert Syst. Appl., 166, 113917.
  25. Pinnegar, C.R. and Mansinha, L. (2003), "The S-transform with windows of arbitrary and varying shape", Geophysics. 68(1), 381-385.
  26. Shen, L., Mi, L., Han, Y., Cai, C., Li, K. and Wang, L. (2023), "A multi-step wind speed prediction method based on WRF simulation, an optimized data-generating model, and an error correction strategy", Wind Struct., 36(5), 333-344.
  27. Stankovic, L. (1994), "An analysis of some time-frequency and time-scale distributions", Annales Des Telecommunications. 49(9), 505-517.
  28. Stankovic, L. (1997), "Highly concentrated time-frequency distributions: Pseudo quantum signal representation", Ieee Transact. Signal Processing. 45(3), 543-551.
  29. Stankovic, L. (2001), "A measure of some time-frequency distributions concentration", Signal Processing. 81(3), 621-631.
  30. Stockwell, R.G., Mansinha, L. and Lowe, R.P. (1996), "Localization of the complex spectrum: The S transform", Ieee Transact. Signal Processing. 44(4), 998-1001.
  31. Sun, W. and Liu, M. (2016), "Wind speed forecasting using FEEMD echo state networks with RELM in Hebei, China", Energy Conversion Manage., 114, 197-208.
  32. Tang, Q., Qiu, W. and Zhou, Y. (2020), "Classification of complex power quality disturbances using optimized S-transform and Kernel SVM", Ieee Transact. Ind. Electronics. 67(11), 9715-9723.
  33. Tu, Q., Chen, X. and Liu, X. (2019), "Hierarchy strengthened grey wolf optimizer for numerical optimization and feature selection", Ieee Access. 7, 78012-78028.
  34. Wang, D., Wang, J., Liu, Y. and Xu, Z. (2015). "An adaptive time-frequency filtering algorithm for multi-component LFM signals based on generalized S-transform", 21st International Conference on Automation and Computing (ICAC), Univ Strathclyde Glasgow, Glasgow, ENGLAND, Sep 11-12.
  35. Wang, L., McCullough, M. and Kareem, A. (2013), "A data-driven approach for simulation of full-scale downburst wind speeds", J. Wind Eng. Ind. Aerod., 123, 171-190.
  36. Wang, L., McCullough, M. and Kareem, A. (2014), "Modeling and Simulation of Nonstationary Processes Utilizing Wavelet and Hilbert Transforms", J. Eng. Mech., 140(2), 345-360.
  37. Wang, S., Zhang, N., Wu, L. and Wang, Y. (2016), "Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method", Renew. Energy. 94, 629-636.
  38. Wen, Y.K. and Gu, P. (2004), "Description and simulation of nonstationary processes based on Hilbert spectra", J. Eng. Mech., 130(8), 942-951.
  39. Xu, W., Liu, P., Cheng, L., Zhou, Y., Xia, Q., Gong, Y. and Liu, Y. (2021), "Multi-step wind speed prediction by combining a WRF simulation and an error correction strategy", Renew. Energy. 163, 772-782.
  40. Yang, T.H. and Tsai, C.C. (2019), "Using numerical weather model outputs to forecast wind gusts during typhoons", J. Wind Eng. Ind. Aerod., 188, 247-259.
  41. Zhang, C., Zhou, J., Li, C., Fu, W. and Peng, T. (2017), "A compound structure of ELM based on feature selection and parameter optimization using hybrid backtracking search algorithm for wind speed forecasting", Energy Conversion Manage., 143, 360-376.