Sökning: onr:"swepub:oai:research.chalmers.se:4a31924a-1132-495b-b7b5-216be986a837" >
Poster: Learning to...
Poster: Learning to Shine - Optimizing Glossy at Runtime with Reinforcement Learning
-
- Poirot, Valentin, 1994 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Landsiedel, Olaf, 1979 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology,Christian-Albrechts-Universität zu Kiel,University of Kiel
-
(creator_code:org_t)
- 2019
- 2019
- Engelska.
-
Ingår i: International Conference on Embedded Wireless Systems and Networks. - 2562-2331. ; 2019, s. 226-227
- Relaterad länk:
-
https://research.cha... (primary) (free)
-
visa fler...
-
https://research.cha...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Telekommunikation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Telecommunications (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Kommunikationssystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Communication Systems (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- wireless sensor networks
- network flooding
- artificial intelligence
- Glossy
- reinforcement learning
- IoT
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas