
Investment in Data Infrastructure Powers Smart Energy Management
Stanford’s Facilities Energy Management group integrates AI with a foundation of well-maintained data and its own experts.
The Cooler Research Program was launched in 2020 to provide a quantitative assessment of the impact of different chilled water demand management strategies. The program leverages new technological resources available to the university, including smart building control systems and new data management platforms that enable acquisition and analysis of large and complex data sets.
The program is a collaboration between Stanford Land, Buildings & Real Estate (LBRE) and senior faculty affiliated with the Stanford Precourt Institute for Energy. It entails experimenting with different chilled water load management measures within multiple operating buildings. A unique aspect of this research is the ability to test at the individual room level. This unlocks the potential for much more precise and targeted control strategies, opening the door to gradual demand reductions in non-critical spaces while simultaneously preserving critical zones.
As of summer 2022, Cooler has on-boarded a dozen campus buildings. Research thus far has demonstrated significant, consistent, and predictable impacts on chilled water loads from simple measures like raising room temperature setpoints by 2 to 4 degrees F, while maintaining zone temperatures within target boundaries. Extrapolating these results to the campus level suggests the university could reduce system-level demand by 10-15% during periods of stress. Beyond emergencies, the research data that were collected will also be of value to LBRE in more regular operations. For example, it could help LBRE to more accurately estimate the energy saved by raising room temperatures in unoccupied spaces.

Stanford’s Facilities Energy Management group integrates AI with a foundation of well-maintained data and its own experts.

Info about the wide range of goods and services is spread across a number of sources, and machine learning helps Stanford make sense of this data.

Stanford is testing whether machine learning can close the gap on making lower-carbon design decisions during initial planning stages.