Advanced

Routing using Safe Reinforcement Learning

Nayak Seetanadi, Gautham LU and Årzén, Karl-Erik LU (2020) 2nd Workshop on Fog Computing and the Internet of Things
Abstract
The ever increasing number of connected devices has lead to a metoric rise in the amount data to be processed. This has caused computation to be moved to the edge of the cloud increasing the importance of efficiency in the whole of cloud. The use of this fog computing for time-critical control applications is on the rise and requires robust guarantees on transmission times of the packets in the network while reducing total transmission times of the various packets.

We consider networks in which the transmission times that may vary due to mobility of devices, congestion and similar artifacts. We assume knowledge of the worst case tranmssion times over each link and evaluate the typical tranmssion times through exploration. We... (More)
The ever increasing number of connected devices has lead to a metoric rise in the amount data to be processed. This has caused computation to be moved to the edge of the cloud increasing the importance of efficiency in the whole of cloud. The use of this fog computing for time-critical control applications is on the rise and requires robust guarantees on transmission times of the packets in the network while reducing total transmission times of the various packets.

We consider networks in which the transmission times that may vary due to mobility of devices, congestion and similar artifacts. We assume knowledge of the worst case tranmssion times over each link and evaluate the typical tranmssion times through exploration. We present the use of reinforcement learning to find optimal paths through the network while never violating preset deadlines. We show that with appropriate domain knowledge, using popular reinforcement learning techniques is a promising prospect even in time-critical applications. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
in press
subject
host publication
2nd Workshop on Fog Computing and the Internet of Things
conference name
2nd Workshop on Fog Computing and the Internet of Things
conference dates
2020-04-21
external identifiers
  • scopus:85083307498
ISBN
978-395977144-3
project
ELLIIT LU P02: Co-Design of Robust and Secure Networked Embedded Control Systems
language
English
LU publication?
yes
id
434a1bd3-8cfd-4875-88a1-028961a1c246
date added to LUP
2020-03-11 14:46:49
date last changed
2020-05-06 06:27:32
@inproceedings{434a1bd3-8cfd-4875-88a1-028961a1c246,
  abstract     = {The ever increasing number of connected devices has lead to a metoric rise in the amount data to be processed. This has caused computation to be moved to the edge of the cloud increasing the importance of efficiency in the whole of cloud. The use of this fog computing for time-critical control applications is on the rise and requires robust guarantees on transmission times of the packets in the network while reducing total transmission times of the various packets.<br/><br/>We consider networks in which the transmission times that may vary due to mobility of devices, congestion and similar artifacts. We assume knowledge of the worst case tranmssion times over each link and evaluate the typical tranmssion times through exploration. We present the use of reinforcement learning to find optimal paths through the network while never violating preset deadlines. We show that with appropriate domain knowledge, using popular reinforcement learning techniques is a promising prospect even in time-critical applications.},
  author       = {Nayak Seetanadi, Gautham and Årzén, Karl-Erik},
  booktitle    = {2nd Workshop on Fog Computing and the Internet of Things},
  isbn         = {978-395977144-3},
  language     = {eng},
  month        = {02},
  title        = {Routing using Safe Reinforcement Learning},
  url          = {https://lup.lub.lu.se/search/ws/files/77106676/main.pdf},
  year         = {2020},
}