Summary
International Conference on Emerging Technologies for Communications
2020
Session Number:P1
Session:
Number:P1-1
Implementation and Experimental Evaluation of A Reinforcement- Learning-Based Channel Selection on A Mobile IoT System
Honami Furukawa, Aohan Li, Yozo Shoji, Yoshito Watanabe, Song-Ju Kim, Koya Sato, Yusuke Ito, Yiannis Andreopoulos, Mikio Hasegawa,
pp.-
Publication Date:2020/12/2
Online ISSN:2188-5079
DOI:10.34385/proc.63.P1-1
PDF download
Summary:
Achieving high-quality communications in massive Internet of Things (IoT) systems requires to develop an efficient channel selection method with low power consumption. To this end, Ma et al. [1] proposed an autonomous distributed channel selection method based on the Tug-of-War (ToW) dynamics [2]. The ToW-based method can achieve equivalent performance to UCB1-tuned [3]; which is recognized as a best practice technique for solving multi-armed bandit (MAB) problems. However, reference [1] only considered fixed IoT devices with simplex communication. We have extended the ToW-based channel selection to duplex communications in a distributed Massive IoT system: which is called ToW-based channel selection algorithm (ToWCS) [4]. In this paper, we evaluate the practical performance of the ToWCS via an experiment using multiple wireless modules based on IEEE 802.15.4g/4e.