Faculty

NSF & VMware Award Prof. Asaf Cidon & Team a $3M Grant for Sustainable Data Centers

April 13, 2021
nsf

Columbia Prof. Asaf Cidon and a team of researchers from UW (Tom Anderson and Irene Zhang), MIT (Adam Belay) and University of Michigan (Mosharaf Chowdhury) have been awarded the $3M NSF/Vmware grant for sustainable data centers, one of only two teams to have won the award. Their proposal, TreeHouse, establishes a set of foundations for developing the software infrastructure that can help track and control the energy consumption and carbon footprint of cloud data centers.

Data center energy consumption represents about 1% of worldwide electricity consumption. However, with demand for data center computing projected to double every few years, especially with the rise of energy-hungry AI and large-scale data science, the electric consumption of computing is set to grow exponentially, and is set to become a major source of carbon emissions. 

While there has been a large amount of work in making the hardware infrastructure of data centers more energy efficient, much less attention has been paid to energy efficiency at the data center software layer. For example, organizations that run applications in the cloud have no way today to determine how much energy their applications are consuming over time, what their carbon footprint is, and what steps they can take to reduce their digital carbon footprint. In addition, even with perfect hardware-level efficiency, cloud software applications often poorly utilize their available hardware, which leads to wasted energy.

The PIs' proposal, TreeHouse, aims to solve these problems, by providing visibility and accountability at the software layer, allowing cloud application developers for the first time to track and control their carbon footprint. In addition, TreeHouse will allow application developers to explicitly specify their application's performance goals and deadlines. Using this information TreeHouse will be able to make scheduling decisions that reduce energy consumption. For example, non-delay-sensitive batch jobs, such as crunching the data for assembling a daily business report, or retraining a machine learning model, may be scheduled for times where demand is lower, or when renewable energy (e.g., wind/solar) is available. Finally, the project aims to design a set of new software abstractions that provide much finer-grained and energy-efficient computing, which will lead to higher utilization of existing hardware resources.

TreeHouse will serve as a new vehicle for collaboration on tackling the carbon emissions caused by cloud computing, bringing together researchers from all four universities, as well as industry partners, including from VMware, Microsoft and IBM.

***

The Columbia University Climate Mission is to deepen understanding of how climate affects human sustainability by accelerating innovative climate research at Columbia University and providing expert analysis on climate impacts and solutions.

Columbia carries out its mission by:

  • Funding high-risk, high-reward research that helps society understand and generate solutions to climate change.
  • Building partnerships with private and public sector entities to apply new climate knowledge for the benefit of humanity.
  • Providing insight into the emerging knowledge and technologies that shape the understanding of climate impacts and solutions.
  • Supporting and training the next generation of Earth scientists.