ISE PhD Student Wins Best Student Poster Competition at the IISE Annual Conference
Feng Ye, a doctoral student in the School of Engineering Department of Industrial and Systems Engineering, took first place in the Best Student Poster contest at the Institute of Industrial and Systems Engineers (IISE) annual conference.
Ye was among a group of ISE undergraduate and graduate students attending the May conference – the world’s largest industrial and systems engineering conference – in Montreal, Canada along with ISE professors David Coit ,Aziz Ezzat, and Randall Reagan.
“My poster, ‘Multi-Height, Spatio-Temporal Offshore Wind Forecasting Using a Statistical Deep Learning Model,’ showcases an innovative approach to enhancing wind energy forecasting accuracy at multiple heights and locations by integrating statistical and deep learning techniques,” explains Ye. His work has been guided by both Ezzat, his ISE advisor, and statistics professor Michael Stein.
Ezzat, notes that “Feng’s most recent research investigates an interesting and timely question related to offshore wind energy production. In order to unlock access to stronger winds, offshore wind turbines are getting bigger and higher, reaching altitudes comparable to many of the world’s tallest landmarks.”
Yet, Ezzat adds, “this increase in scale creates the need for new models tailored to the operation of these next generation, ultra-scale turbines. To do so, Feng proposes innovative solutions using advanced machine learning techniques to produce more accurate predictions for offshore wind energy.”
“The work presented in this poster is an integral piece of Feng’s dissertation, that nicely complements his prior and ongoing work,” says Ezzat. “This recognition is another testament to the relevance and novelty of his work. This is the third time that his innovation on offshore wind energy forecasting has received an award, joining two previous best paper recognitions from IISE and INFORMS.”
Ye says that while he is especially proud of his project’s proposal for a new wind energy forecasting model that merges the strengths of both statistical as well as deep learning methodologies, he is also grateful for a travel funding award from the Rutgers Climate and Energy Institute (RCEI), which enabled him to travel to Montreal for the conference.
