Summary
International Conference on Emerging Technologies for Communications
2022
Session Number:S8
Session:
Number:S8-7
A Study on the Performance Improvement of a Routing Mechanism using Reinforcement Learning for IoT Networks
Shotaro Takahashi, Shota Inoue, Keita Goto, Hiroyuki Ohsaki,
pp.-
Publication Date:2022/11/29
Online ISSN:2188-5079
DOI:10.34385/proc.72.S8-7
PDF download (536.6KB)
Summary:
Low-power and lossy networks (LLNs) have been gaining attention as wireless networks for IoT applications. Recently, Farag et al. proposed a routing protocol for LLNs using reinforcement learning. heir method determines the next hop by performing Q-learning, in which each neighbor node is rewarded with the number of hops to the sink node, message loss rate along the path to the sink node, and queue occupancy. We believe that the performance of their method can be improved by performing Q-learning cooperatively rather than independently.