Researchers at the University of Missouri are leveraging artificial intelligence technology to revolutionize energy management models for large campuses (including their own), aiming to help colleges and universities nationwide improve efficiency, reduce operating costs, and decrease carbon emissions.
Engineering College researchers Sanjeev Khanna and Saad Alsamraee, in their recent study published in Energy Strategy Reviews titled "High-Resolution Energy Consumption Forecasting for University Campus Power Plants Based on Advanced Machine Learning Techniques," analyzed six years of data (2017–2022) from the University of Missouri's combined heat and power plant. The dataset covers campus energy usage as well as environmental variables including air temperature, humidity, wind speed/direction, and solar radiation, with records tracked on an hourly basis.
The research team successfully used machine learning to predict campus energy demand in 2023 with an accuracy of up to 94%. Professor of Mechanical Engineering and Director of the Midwest Industrial Assessment Center Khanna stated that understanding peak and valley energy demand helps power plants plan in advance to achieve efficient energy utilization. This research can assist universities and enterprises in reducing emissions and costs. In addition, predicting energy valleys allows universities to schedule maintenance more reasonably, minimizing disruptions.
Although the study focused on energy data from the University of Missouri, the results demonstrate that machine learning can help power plants across the country operate more efficiently. Notably, Professor Khanna has not only helped local industries in Missouri reduce energy use and carbon emissions, but has also decreased the state's electricity demand by approximately 300 megawatts, generating an economic impact exceeding $120 million and reducing carbon emissions by more than 800,000 tons annually. Khanna noted that collaboration with the University of Missouri sets it apart from other universities—the institution supports breaking conventional thinking, and its land-grant mission enables the research to serve industries statewide.
