Abstract
There are different patterns for wind speed variation in different seasons. The patterns are not only related to the statistical characteristics, but also to the trends of wind speed fluctuation and variation. However, the classical clustering can’t take the trend information as an independent overall feature in the algorithm. In this paper, multi-view clustering is introduced to extract patterns of wind speed variation from both statistical information and the trends. For about 1.5-year historical data, the trends of wind speed variation and fluctuation, and other five statistical characteristics are selected as features to characterize patterns of wind speed variation. Then four patterns are obtained with multiple clustering. It is found that mean wind speed and fluctuation level are very important and the behavior of wind speed is significantly different in the past states in different clusters. Forecasting model performs worse for the cluster with large mean wind speed and fluctuation range.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IOP Conference Series: Earth and Environmental Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
