{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/wind-speed-forecasting-using-the-stationary","title":"Wind speed forecasting using the stationary wavelet transform and quaternion adaptive\u0002gradient methods","arxiv_id":null,"date":"2021-09-10","proceeding":"journal 2021 9","authors":["Lyes Saad Saoud","Hasan Al-Marzouqi","Mohamed Deriche"],"abstract":"Accurate wind speed forecasting is a fundamental requirement for advanced and economically \r\nviable large-scale wind power integration. The hybridization of the quaternion-valued neural networks and \r\nstationary wavelet transform has not been proposed before. In this paper, we propose a novel wind-speed \r\nforecasting model that combines the stationary wavelet transform with quaternion-valued neural networks. \r\nThe proposed model represents wavelet subbands in quaternion vectors, which avoid separating the naturally\r\ncorrelated subbands. The model consists of three main steps. First, the wind speed signal is decomposed using \r\nthe stationary wavelet transform into sublevels. Second, a quaternion-valued neural network is used to \r\nforecast wind speed components in the stationary wavelet domain. Finally, the inverse stationary wavelet \r\ntransform is applied to estimate the predicted wind speed. In addition, a softplus quaternion variant of the \r\nRMSProp learning algorithm is developed and used to improve the performance and convergence speed of \r\nthe proposed model. The proposed model is tested on wind speed data collected from different sites in China \r\nand the United States, and the results demonstrate that it consistently outperforms similar models. In the \r\nmeteorological terminal aviation routine (METAR) dataset experiment, the proposed wind speed forecasting \r\nmodel reduces the mean absolute error, and root mean squared error of predicted wind speed values by 26.5% \r\nand 33%, respectively, in comparison to several existing approaches.","url_abs":"https://ieeexplore.ieee.org/abstract/document/9535164","url_pdf":"https://ieeexplore.ieee.org/abstract/document/9535164","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"wind-speed-forecasting-using-the-stationary","repo_url":"https://github.com/LyesSaadSaoud/Wind_forecast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}