<i> CO <sub>2</sub> CoDe </i> : Towards Carbon-Aware Hardware/Software Co-Design for Intermittently-Powered Embedded Systems

The upcoming battery-free Internet of Things comes with a major benefit: These systems operate energy-self-sufficiently during runtime by harvesting energy from the environment. However, the promise of thereby achieving sustainability neglects the fact that manufacturing such systems requires substantial carbon resources, eventually embodied into these systems' cradle-to-gate footprint. When developing these hard-/software systems, designers currently have no possibility to make carbon-aware decisions and assess their cross-cutting consequences throughout the system's stack (i.e., hardware, operating system, scheduler, application). To address these problems, we present CO 2 CoDe , an approach to carbon-aware co-design of embedded systems. In this paper, we exemplify the necessity of carbon-aware co-design by means of the energy-storage (e.g., capacitor) selections in intermittently-powered embedded systems. System designers have a choice of various storage types manufactured from different materials, which influence not only the environmental impact but also operational characteristics (e.g., internal resistances of capacitors). These differences in operational parameters have cross-cutting, system-wide ramifications: For example, specific types of storage have a smaller/higher carbon footprint while likewise making runtime scheduling decisions harder/easier. Our evaluations on a real-world intermittently-powered system with several capacitor types and scheduling approaches validate our optimization objective of co-designing for carbon awareness with the constraints of meeting energy budgets.

Authors

Institutions

Publication Details

Journal
ACM SIGEnergy Energy Informatics Review
Published
2024-12-01
DOI
https://doi.org/10.1145/3727200.3727219
Citations
2
Primary Topic
Parallel Computing and Optimization Techniques
Type
article
Field-Weighted Citation Impact
0.98
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

CO 2 CoDe : Towards Carbon-Aware Hardware/Software Co-Design for Intermittently-Powered Embedded Systems

Phillip Raffeck, Peter Wägemann, Sven Posner
2 citations
ACM SIGEnergy Energy Informatics Review
Parallel Computing and Optimization Techniques
0.98
article

CO 2 CoDe : Towards Carbon-Aware Hardware/Software Co-Design for Intermittently-Powered Embedded Systems

Phillip Raffeck, Peter Wägemann, Sven Posner
article en
2 citations

Abstract

The upcoming battery-free Internet of Things comes with a major benefit: These systems operate energy-self-sufficiently during runtime by harvesting energy from the environment. However, the promise of thereby achieving sustainability neglects the fact that manufacturing such systems requires substantial carbon resources, eventually embodied into these systems' cradle-to-gate footprint. When developing these hard-/software systems, designers currently have no possibility to make carbon-aware decisions and assess their cross-cutting consequences throughout the system's stack (i.e., hardware, operating system, scheduler, application). To address these problems, we present CO 2 CoDe , an approach to carbon-aware co-design of embedded systems. In this paper, we exemplify the necessity of carbon-aware co-design by means of the energy-storage (e.g., capacitor) selections in intermittently-powered embedded systems. System designers have a choice of various storage types manufactured from different materials, which influence not only the environmental impact but also operational characteristics (e.g., internal resistances of capacitors). These differences in operational parameters have cross-cutting, system-wide ramifications: For example, specific types of storage have a smaller/higher carbon footprint while likewise making runtime scheduling decisions harder/easier. Our evaluations on a real-world intermittently-powered system with several capacitor types and scheduling approaches validate our optimization objective of co-designing for carbon awareness with the constraints of meeting energy budgets.

ACM SIGEnergy Energy Informatics ReviewVol. 4(5)
Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
Openalex Percentile: Top 21%
Parallel Computing and Optimization Techniques
0.98
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.