Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
DeepGANTT: A Scalable Deep Learning Scheduler for Backscatter Networks
RISE Research Institutes of Sweden, Digital Systems, Data Science. KTH Royal Institute of Technology, Sweden. (RISE Computer Science)ORCID iD: 0000-0002-1322-4367
RISE Research Institutes of Sweden, Digital Systems, Data Science. (RISE Computer Science)ORCID iD: 0000-0002-1903-4679
RISE Research Institutes of Sweden, Digital Systems, Data Science. (RISE Computer Science)ORCID iD: 0000-0003-3139-2564
RISE Research Institutes of Sweden, Digital Systems, Data Science. Uppsala University, Sweden. (RISE Computer Science)ORCID iD: 0000-0002-2586-8573
Show others and affiliations
2023 (English)In: IPSN '23: Proceedings of the 22nd International Conference on Information Processing in Sensor Networks / [ed] Association for Computing Machinery, New York, NY, United States, 2023, p. 163-Conference paper, Published paper (Refereed)
Abstract [en]

Novel backscatter communication techniques enable battery-free sensor tags to interoperate with unmodified standard IoT devices, extending a sensor network’s capabilities in a scalable manner. Without requiring additional dedicated infrastructure, the battery-free tags harvest energy from the environment, while the IoT devices provide them with the unmodulated carrier they need to communicate. A schedule coordinates the provision of carriers for the communications of battery-free devices with IoT nodes. Optimal carrier scheduling is an NP-hard problem that limits the scalability of network deployments. Thus, existing solutions waste energy and other valuable resources by scheduling the carriers suboptimally. We present DeepGANTT, a deep learning scheduler that leverages graph neural networks to efficiently provide near-optimal carrier scheduling. We train our scheduler with optimal schedules of relatively small networks obtained from a constraint optimization solver, achieving a performance within 3% of the optimum. Without the need to retrain, our scheduler generalizes to networks 6 × larger in the number of nodes and 10 × larger in the number of tags than those used for training. DeepGANTT breaks the scalability limitations of the optimal scheduler and reduces carrier utilization by up to compared to the state-of-the-art heuristic. As a consequence, our scheduler efficiently reduces energy and spectrum utilization in backscatter networks.

Place, publisher, year, edition, pages
New York, NY, United States, 2023. p. 163-
Keywords [en]
scheduling, machine learning, wireless backscatter communications, combinatorial optimization
National Category
Communication Systems Computer Sciences Information Systems
Identifiers
URN: urn:nbn:se:ri:diva-64865DOI: 10.1145/3583120.3586957ISBN: 979-8-4007-0118-4 (electronic)OAI: oai:DiVA.org:ri-64865DiVA, id: diva2:1758762
Conference
IPSN '23: The 22nd International Conference on Information Processing in Sensor Networks
Projects
SSF Instant Cloud ElasticityHorizon 2020 AI@Edge
Funder
Swedish Foundation for Strategic ResearchEU, Horizon 2020, 101015922Swedish Research Council, 2017-045989
Note

This work was financially supported by the Swedish Foundationfor Strategic Research (SSF), by the European Union’s Horizon 2020AI@EDGE project (Grant 101015922), and by the Swedish ResearchCouncil (Grant 2017-045989). 

Available from: 2023-05-23 Created: 2023-05-23 Last updated: 2023-06-08Bibliographically approved

Open Access in DiVA

fulltext(12634 kB)48 downloads
File information
File name FULLTEXT01.pdfFile size 12634 kBChecksum SHA-512
4d1dfd0bb77cab07cd4ea6bfbcf01f96eaca3bc6e24be1c485effe262e93c0eb09e6cb4b3eda9c1cead45bd6b0ee8cabe025f183065c893baae0d6e2f05c51df
Type fulltextMimetype application/pdf

Other links

Publisher's full textFull text

Authority records

Perez-Ramirez, Daniel F.Tsiftes, NicolasVoigt, ThiemoKostic, Dejan

Search in DiVA

By author/editor
Perez-Ramirez, Daniel F.Pérez-Penichet, CarlosTsiftes, NicolasVoigt, ThiemoKostic, DejanBoman, Magnus
By organisation
Data Science
Communication SystemsComputer SciencesInformation Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 48 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 207 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf