- author = "Giovanna Martinez-Arellano and Lars Nolle",
- title = "Genetic Programming for Wind Power Forecasting and Ramp Detection",
- booktitle = "Proceedings of the Thirty-third SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence (AI 2013)",
- year = "2013",
- editor = "Max Bramer and Miltos Petridis",
- pages = "403--417",
- address = "Cambridge, UK",
- month = dec # " 10-12",
- organisation = "British Computer Society's Specialist Group on Artificial Intelligence",
- publisher = "Springer",
- keywords = "genetic algorithms, genetic programming",
- bibdate = "2013-12-08",
- bibsource = "DBLP, http://dblp.uni-trier.de/db/conf/sgai/sgai2013.html#Martinez-ArellanoN13",
- language = "English",
- isbn13 = "978-3-319-02620-6",
-
URL = "
http://dx.doi.org/10.1007/978-3-319-02621-3",
-
URL = "http://dx.doi.org/10.1007/978-3-319-02621-3_30",
-
DOI = "
doi:10.1007/978-3-319-02621-3_30",
- abstract = "In order to incorporate large amounts of wind power into the electric grid, it is necessary to provide grid operators with wind power forecasts for the day ahead, especially when managing extreme situations: rapid changes in power output of a wind farm. These so-called ramp events are complex and difficult to forecast. Hence, they introduce a high risk of instability to the power grid. Therefore, the development of reliable ramp prediction methods is of great interest to grid operators. Forecasting ramps for the day ahead requires wind power forecasts, which usually involve numerical weather prediction models at very high resolutions. This is resource and time consuming. This paper introduces a novel approach for short-term wind power prediction by combining the Weather Research and Forecasting advanced Research WRF model (WRF-ARW) with genetic programming. The latter is used for the final downscaling step and as a prediction technique, estimating the total hourly power output for the day ahead at a wind farm located in Galicia, Spain. The accuracy of the predictions is above 85 percent of the total power capacity of the wind farm, which is comparable to computationally more expensive state-of-the-art methods. Finally, a ramp detection algorithm is applied to the power forecast to identify the time and magnitude of possible ramp events. The proposed method clearly outperformed existing ramp prediction approaches.",
-
notes = "http://www.bcs-sgai.org/ai2013/
Research and Development in Intelligent Systems XXX, Incorporating Applications and Innovations in Intelligent Systems XXI. Proceedings of AI-2013, The Thirty-third SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence
Nottingham Trent University, UK",
