Wind power generation via ground wind station and topographical feedforward neural network (T-FFNN) model for small-scale applications

详细信息    查看全文

• 作者：S.M. Lawan^a ; ^b ; ^{13010004@siswa.unimas.my} ; W.A.W.Z. Abidin^a ; T. Masri^a ; W.Y. Chai^c ; A. Baharun^d
• 关键词：Wind energy and renewable energy ; Neural network ; Sarawak ; Miri ; Power density
• 刊名：Journal of Cleaner Production
• 出版年：2017
• 出版时间：1 February 2017
• 年：2017
• 卷：143
• 期：Complete
• 页码：1246-1259
• 全文大小：3300 K
• 卷排序：143

文摘

This study comes out with an improved machine learning method for the prediction of wind speed. A new approach for the estimation of missing data using cubic spline function was formulated. Improved models for computing wind power were used taking into account the study area is located in a hot and humid region. The performances of small-scale wind turbines were demonstrated using manufacturers curves and formulated models.