<div class="csl-bib-body">
<div class="csl-entry">May, D., Tundo, A., Ilager, S., & Brandic, I. (2025). <i>Towards Energy-Efficient Split Computing: A Hardware-Software Co-Design Perspective</i> [Poster Presentation]. EuroSys 2025, Rotterdam, Netherlands (the). http://hdl.handle.net/20.500.12708/225745</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/225745
-
dc.description.abstract
Edge ML faces resource and energy constraints, requiring
optimized split computing, which partitions inference be-
tween edge and cloud. We propose a two-phase framework
combining offline optimization and dynamic scheduling. It
jointly configures split points and hardware settings to bal-
ance energy and latency.
en
dc.language.iso
en
-
dc.subject
Edge AI
en
dc.subject
Split Computing
en
dc.subject
Hardware–Software Co-Design
en
dc.subject
Multi-Objective Optimization
en
dc.title
Towards Energy-Efficient Split Computing: A Hardware-Software Co-Design Perspective
