Collaborative Research: National Science Foundation Expeditions in Computing: Carbon Connect -- An Ecosystem for Sustainable Computing
- Institution
- University of Pennsylvania, PA
- Principal investigator
- Benjamin Lee
- Funding
- $4.2M
- Duration
- 2024–2029
Moonbase score
Still being scored
Abstract
Computing is at a moment of profound opportunity and promise. Emerging applications – such as capable artificial intelligence, immersive virtual realities, and pervasive sensor systems – drive unprecedented demand for computer systems that offer scalable performance and environmental sustainability. Despite recent advances, the computing industry’s gross energy usage continues to rise at an alarming rate, outpacing the growth of new energy installations and renewable energy deployments. The Carbon Connect Expedition is a multi-institutional, five-year research initiative that builds the foundations for sustainable computing. This shift towards sustainability could spark a transformation in how computer systems are manufactured, allocated, and consumed, leading to a more responsible and sustainable approach to advancing computing technologies. By redefining the way computer scientists consider environmental sustainability, Carbon Connect will establish new standards for carbon accounting in the computing industry, thereby influencing future energy policy and legislation. By fostering an interdisciplinary community of researchers dedicated to sustainable computing, Carbon Connect will train the next generation of innovators in the combined fields of computer science, electrical engineering, environmental science, and energy policy. By creating an academic-industry consortium, Carbon Connect will accelerate the adoption of sustainable computing practices. Finally, by organizing workshops and curricula, Carbon Connect will educate future leaders in computer science and engineering. The Carbon Connect Expedition re-thinks computing’s infrastructure, from semiconductor chips to hyperscale datacenters. Embodied carbon arises from a hardware component’s entire lifecycle, including its manufacture, transportation, and eventual disposal. This aspect of the Expedition seeks to minimize the environmental impact of producing semiconductor chips, which are fundamental to all electronic devices but come with a high carbon cost. Operational carbon, on the other hand, arises from energy consumed during a hardware component’s operational life. Given rapidly increasing energy demands from global datacenters that power the Internet, cloud services, and the emerging capabilities in artificial intelligence, addressing operational emissions at datacenter scale is particularly important. The Carbon Connect Expedition seeks to reduce the carbon footprint of information and communication technology by pursuing three main objectives. First, the Expedition will create transparent and accurate carbon accounting methods, which will include standardized protocols for measuring and reporting carbon as well as techniques for overcoming inconsistent estimates and broad error margins. Second, it will develop innovative tools and strategies for reducing computing’s carbon footprint by 45% within the next decade. These innovations will include the exploration of energy-efficient hardware design, advanced hardware recycling and disposal strategies to minimize embodied carbon, and the intelligent use of renewable energy to reduce operational carbon from datacenters. Third, the Carbon Connect Expedition will coordinate the design and management of future computer systems to sustainability deliver performance for artificial intelligence and virtual reality systems. This coordination will allow computer scientists and engineers to balance embodied and operational carbon, which cannot often be reduced simultaneously and require intelligent compromises. Together, these technical objectives will ensure continued advances in computational performance and capability yet ensure environmental sustainability. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
Research team
- Benjamin LeePI
- Benjamin C Pierce
- Linh Thi Xuan Phan
- Arthur Van Benthem
- Vincent Liu
LOADING MOONBASE SCORE
Questions for University of Pennsylvania
Answered by the team behind this research.
No questions yet. Sign in to ask the first one
Related grants
Same researchers, same institution, same topic, scored first.
- NSF · University of PennsylvaniaNot yet scored
SHF: Medium: Usable Property-Based Testing
Benjamin C Pierce · $1.0M · 2024–2027
- NSF · University of PennsylvaniaNot yet scored
Collaborative Research: CISE: Large: Systems Support for Run-Anywhere Serverless
Vincent Liu · $1.7M · 2023–2028
- NIH · University of Pennsylvania70
Epitranscriptomic regulation in the mammalian nervous system
Guo-Li Ming · $985K · 2024–2032