Academy of Finland  
Funding decision
Organisation University of Helsinki
Project title Scalable and energy-efficient networked systems at the edge
Applicant / Contact person Premsankar, Gopika
Decision No. 338854
Decision date 03.06.2021
Funding period 01.09.2021 - 31.08.2024
Funding 240 820
Project description
Edge computing is a key enabler for several emerging applications such as augmented reality and connected cars. With edge computing, data centers are widely distributed closer to users, with resources always available for on-demand, flexible scaling of applications. Artificial intelligence (AI) applications are increasingly being used to run inference at the edge. They result in increasing workloads; thus, the environmental footprint of such data centers is large. To meet sustainability goals, it is critical to minimize the energy consumed while still supporting the always-on, connected services of the future. SENSE aims to establish energy-efficiency as a fundamental metric in designing and deploying AI at the edge. It devises novel optimization models and energy models to allocate resources in edge data centers such that energy consumed is minimized. Finally, it demonstrates the practical feasibility of the proposed solutions through a proof of concept.