Correlation aware multi-step ahead wind speed forecasting with heteroscedastic multi-kernel learning
Energy Conversion and Management(2018)
摘要
•A novel multi-step ahead wind speed forecasting method is designed based on multi-kernel learning.•The method considers the task correlation and the heteroscedasticity of forecasting errors.•The optimization is solved within the framework of variational Bayesian.•The proposed model is tested comprehensively in different wind farms and different seasons.
更多查看译文
关键词
Multi-step ahead wind speed forecasting,Heteroscedasticity,Task correlation,Multi-kernel learning,Matrix-variate Gaussian,Variational Bayesian
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要