Poster: Learning to Shine - Optimizing Glossy at Runtime with Reinforcement Learning
Conference poster, 2019

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.

Glossy

IoT

wireless sensor networks

artificial intelligence

network flooding

reinforcement learning

Author

Valentin Poirot

Chalmers, Computer Science and Engineering (Chalmers), Networks and Systems (Chalmers)

Olaf Landsiedel

Chalmers, Computer Science and Engineering (Chalmers), Networks and Systems (Chalmers)

International Conference on Embedded Wireless Systems and Networks (EWSN)
Beijing, ,

Ultra Low-Latency, Low-Power Wireless Mesh Networks

Swedish Foundation for Strategic Research (SSF), 2017-01-01 -- 2021-12-31.

Areas of Advance

Information and Communication Technology

Subject Categories

Telecommunications

Communication Systems

Computer Science

More information

Latest update

3/5/2019 8