Yu David Liu
Binghamton University, NY·Computer Science
Computing has a growing environmental cost. Billions of smartphones are made, used and thrown away.
- Fields
Computer Science
Engineering
Earth & Environmental Science
- Topics
sustainable computing
green computing
carbon footprint
- Grants
- 2 known grants, through Jun 2028
What they work on
- Develop an operating system principle that continuously measures, tracks and rewards the sustainability impact of software activity on smartphones.
- Build runtime systems that detect and avoid software activity likely to cause sudden shutdowns on smartphones with aging batteries, extending how long phones remain usable.
- Design hardware and software systems that reuse old smartphones for specific tasks and combine several broken phones with complementary working parts.
- Create a full-stack measurement framework for SASSY that estimates each data center job's end-to-end sustainability cost, including lifetime carbon, energy source and device reliability.
- Design programming models and tools that let data center users state sustainability and performance goals, which then guide data-center-wide management decisions.
More about the research
Data centers burn more and more energy to run big data and machine learning jobs. These two collaborative projects design software that treats sustainability as a core goal alongside speed. They do this by measuring the environmental cost of computing and using those measurements to make hardware last longer and run cleaner.
Why it matters
Phones that last longer and data centers that consider carbon costs could reduce electronic waste and the carbon footprint of computing. Data center operators, software developers and smartphone users could benefit from the open-source tools. The tools let them measure environmental cost and choose cleaner options without giving up needed performance.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Emma Strubell
Carnegie Mellon University, PA·Computer Science
Develop transparent and accurate carbon accounting for computing, including standardized protocols for measuring and reporting emissions and methods to reconcile inconsistent estimates and broad error margins across hardware lifecycles.
Simon Peter
University of Washington, WA·Computer Science
Design a programmable memory controller that moves data among memory tiers connected by Compute Express Link based on usage patterns, module age and reliability.
Divya Mahajan
Georgia Institute of Technology, GA·Computer Science·Early-career
Build a cross-platform framework that measures how thermal hotspots, frequency throttling, power spikes and energy limits restrict distributed AI training performance on GPUs and other accelerators.
The school
Binghamton University: 14 labs on PI Pages, $161M a year on research, 132 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.