The Use of Time Series for Predicting HVAC Energy Consumption on the SIUC Campus

This presentation explores the use of artificial intelligence for analyzing time series data on energy consumption at Southern Illinois University Carbondale (SIUC). We applied various models, including recurrent neural networks (RNNs), long short-term memory (LSTM), and autoregressive integrated moving average (ARIMA), to historical HVAC electricity data from 2016 to 2024. Our analysis considers the impact of weather variables and the COVID-19 pandemic on HVAC electricity use. These models aid in predicting and managing plant operations and forecasting annual coal and natural gas consumption in the university.

Case Studies:

Keywords: AI/machine learning, energy consumption forecasting, load prediction

Nathaniel Gao

Undergraduate Sophomore

University of Illinois Urbana-Champaign

Nathaniel Gao is an undergraduate sophomore studying computer science at the University of Illinois at Urbana-Champaign. He has a keen interest in machine learning and is excited to explore the field more in the future. This conference marks his first opportunity to work hands-on with AI models, an experience that has further deepened his fascination with the field.

Jonathan Gao

Undergraduate Senior

University of Illinois Urbana-Champaign

Jonathan Gao is an undergraduate senior in computer science at the University of Illinois Urbana-Champaign. His experience specializes in machine learning and software engineering, and he is passionate about using technology for social impact.

Yong Gao, PhD

Professor

Southern Illinois University Carbondale

Prof. Yong Gao received a Ph.D. in Chemistry from the University of Alberta in Canada in 1998. After spending two years as a postdoctoral fellow at Harvard University, he accepted a tenure-track assistantship job offer from Southern Illinois University Carbondale in 2000. He then moved through the ranks of assistant professor, associate professor, and professor. Dr. Gao's research centers on renewable energy, such as flow batteries and fuel cells, and is supported by awards from the NSF and other funding agencies.