Poster: Learning to shine – optimizing glossy at runtime with reinforcement learning
Publikationstyp
Conference Paper
Date Issued
2019-02
Sprache
English
Author(s)
Start Page
226
End Page
227
Citation
16th International Conference on Embedded Wireless Systems and Networks, EWSN 2019
Contribution to Conference
Scopus ID
Publisher
Junction Publishing
ISBN of container
978-0-9949-8863-8
Glossy is a dissemination protocol that allows a node to propagate information to the entire network through constructive interference. We present GLOSSAI, a new artificial intelligence-based version of Glossy. We use reinforcement learning to determine and update Glossy’s parameters at runtime. Each node individually learns the best strategy to minimize energy consumption while maintaining high reliability. Furthermore, nodes can dynamically adapt their parameters to follow the dynamics of the medium.
Subjects
MLE@TUHH
DDC Class
600: Technology