{"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/smooth-pinball-neural-network-for","title":"Smooth Pinball Neural Network for Probabilistic Forecasting of Wind Power","arxiv_id":"1710.01720","date":"2017-10-04","proceeding":null,"authors":["Kostas Hatalis","Alberto J. Lamadrid","Katya Scheinberg","Shalinee Kishore"],"abstract":"Uncertainty analysis in the form of probabilistic forecasting can\nsignificantly improve decision making processes in the smart power grid for\nbetter integrating renewable energy sources such as wind. Whereas point\nforecasting provides a single expected value, probabilistic forecasts provide\nmore information in the form of quantiles, prediction intervals, or full\npredictive densities. This paper analyzes the effectiveness of a novel approach\nfor nonparametric probabilistic forecasting of wind power that combines a\nsmooth approximation of the pinball loss function with a neural network\narchitecture and a weighting initialization scheme to prevent the quantile\ncross over problem. A numerical case study is conducted using publicly\navailable wind data from the Global Energy Forecasting Competition 2014.\nMultiple quantiles are estimated to form 10%, to 90% prediction intervals which\nare evaluated using a quantile score and reliability measures. Benchmark models\nsuch as the persistence and climatology distributions, multiple quantile\nregression, and support vector quantile regression are used for comparison\nwhere results demonstrate the proposed approach leads to improved performance\nwhile preventing the problem of overlapping quantile estimates.","url_abs":"http://arxiv.org/abs/1710.01720v1","url_pdf":"http://arxiv.org/pdf/1710.01720v1.pdf","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":"smooth-pinball-neural-network-for","repo_url":"https://github.com/EvgeniyaMartynova/MLiP_M5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"form","task_name":"Form"},{"task_slug":"prediction-intervals","task_name":"Prediction Intervals"},{"task_slug":"quantile-regression","task_name":"quantile regression"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1710.01720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}