Faculty Recruiting Support CICS

CICS Assistant Professor Mohammad Hajiesmaili Granted Google Research Award for Machine Learning Project to Optimize Energy Procurement in Data Centers

Mohammad Hajiesmaili

Data centers are using increasingly massive amounts of power, consuming by some estimates up to 3% of the world’s power supply and doubling their appetite every four years. While companies such as Google and Amazon are offsetting the energy consumption of their data centers with on-site wind and solar farms, they continue to face the challenge of how to most efficiently procure energy from multiple sources, such as renewables, batteries, and the public power grid.

To tackle this problem, College of Information and Computer Sciences (CICS) Research Assistant Professor Mohammad Hajiesmaili has been granted a Google Faculty Research Award for “Optimizing Energy Procurement for Data Centers using Machine Learning,” a project he is leading with co-investigators Ramesh Sitaraman, professor at CICS and David Irwin, professor of electrical and computer engineering.

Their proposal aims to follow up on proven successes in using machine learning to improve the energy efficiency of data centers—for example, at one of Google’s centers, the DeepMind AI reduced the cooling bill by 40%—by using machine learning to optimize the energy procurement process. The proposed framework will learn procurement policies purely through experience, gradually learning to make the right procurement decisions through reinforcement in the form of reward signals.

“For these multiple energy sources, we have an abundance of historical data that can be used to train learning algorithms for online decision making,” Hajiesmaili explains. “We aim to use a set of machine learning tools with the ability to infer, in real time, the optimal control and energy procurement decisions.”

By modeling how to more efficiently use renewable sources and energy storage systems, this research has ramifications beyond data centers.

“A broad goal of my research is to ease the reliable and efficient incorporation of renewable energy into IT infrastructure and the electric grid,” says Hajiesmaili. “This research is a significant step towards reducing the energy cost of data centers and thereby reducing the overall cost of internet services. More broadly, by providing a robust way to incorporate local renewable sources to the energy portfolio of large energy customers, it facilitates the integration of renewables into the electric grid, leading to a more green and sustainable world.”

The Google Faculty Research Awards Program is a highly-competitive funding opportunity that aims to recognize and support world-class, permanent faculty pursuing cutting-edge research in areas of mutual interest.

Mohammad Hajiesmaili is a research assistant professor at CICS. He received his Ph.D. and M.Sc. degrees from the University of Tehran, and his B.Sc. degree from Sharif University of Technology. His research centers on studying fundamental design problems under uncertainty in wide range of application domains, including computer networks and energy systems.