Networked Embedded Systems constitute a key enabling technology for Industry 4.0 and cutting-edge applications, such as smart cities, intelligent energy management, and transportation. Performance optimisation in Networked Embedded Systems involves carefully configuring several network parameters and tailoring the network to application requirements and to the environment it is deployed.
ELISE provides network reconfigurations at runtime responding to dynamic application requirements, such as energy-efficiency, latency and reliability. It is powered by a reinforcement learning framework that is trained to identify optimal network configurations.
In this video demo, ELISE dynamically reconfigures the slotframe size of a TSCH network in respond to an emergency event that switches the priorities from energy-efficiency to latency.
Research:
F. F. Jurado Lasso, M. Barzegaran, J. F. Jurado, and X. Fafoutis. ELISE: A Reinforcement Learning Framework to Optimize the Slotframe Size of the TSCH Protocol in IoT Networks. IEEE Systems Journal, 2024.
Publication:
DOI: doi.org/10.1109/JSYST.2024.3371429
Direct link to the paper: ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10473707
Source Code: github.com/fdojurado/SDWSN-controller
Contact:
For more information, reach out to the authors at DTU Compute:
- F. F. Jurado Lasso, fdojurado.github.io/
- X. Fafoutis, people.compute.dtu.dk/xefa/
Funding:
This work was supported in part by the DAIS project. DAIS has received funding from the ECSEL Joint Undertaking (JU) under Grant 101007273. The JU was supported in part by the European Union's Horizon 2020 research and innovation programme and Sweden, Spain, Portugal, Belgium, Germany, Slovenia, Czech Republic, Netherlands, Denmark, Norway, and Turkey. Danish participants were supported in part by the Innovation Fund Denmark under Grant 0228-00004A.
Researchers:
- F. Fernando Jurado-Lasso and Xenofon Fafoutis are with the Embedded Systems Engineering section, DTU Compute, Technical University of Denmark, 2800 Lyngby, Denmark.
- Mohammadreza Barzegaran is with the Center for Pervasive Communications and Computing, University of California, Irvine, CA 92697, USA.
- J. F. Jurado is with the Department of Basic Science, Faculty of Engineering and Administration, Universidad Nacional de Colombia Sede Palmira, Palmira 763531, Colombia.
Learn more:
- DAIS Website: dais-project.eu/
- DAIS @ CORDIS: cordis.europa.eu/project/id/101007273
- ESE @ DTU Compute:
www.compute.dtu.dk/english/research/research-sections/ese
DTU Compute: www.compute.dtu.dk/english/