Scalable and energy-efficient networked systems at the edge

Project Details

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.
AcronymSENSE
StatusFinished
Effective start/end date01/01/202412/01/2024

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.