Seminar title: 

Data Science for Wind Energy

 

Abstract: Wind energy is one of the fastest-growing clean energy sources. Despite the significant growth in the past two decades, wind energy missed some intermediate goals set forth earlier.  According to an estimate by the Global Wind Energy Council, in order to achieve carbon net zero, the global wind power growth needs to be doubled. One critical element in accelerating wind energy growth is to significantly reduce its operational cost for boosting its market competitiveness.  In his book, Data Science for Wind Energy, the speaker discussed a set of wind operational problems through a general data science formulation of y=∫p(y│x)p(x)dx, where y is the power output and x is the wind and environmental input.  The conditional density, p(y│x), or its mean function,  E(y│x), is related to the power curve model of wind turbines.  The model characterizes and quantifies a wind turbine’s performance and production efficiency.  The data science of concern is in the form of nonparametric regression, functional curve comparison, and uncertainty quantification. The speaker will discuss the data science challenges encountered in wind applications and present use cases in which data science solutions make sensible impacts.

​

Speaker bio: 

Dr. Yu Ding is the Mike and Sugar Barnes Professor of Industrial & Systems Engineering at Texas A&M University and Associate Director for Research Engagement of Texas A&M Institute of Data Science.  Dr. Ding received his Ph.D. degree from the University of Michigan in 2001. His research interest is in data and quality science. Dr. Ding is a recipient of the 2018 Texas A&M Engineering Research Impact Award, the 2019 IISE Technical Innovation Award, the 2020 Texas A&M’s University-Level Distinguished Achievement Award in Research, and a Fellow of IISE and ASME.  Dr. Ding is serving as the Editor-in-Chief for IISE Transactions for the term of 2021-2024.