Multi-Armed Bandit Channel Access Scheme With Cognitive Radio Technology in Wireless Sensor Networks for the Internet of Things

The wireless sensor network (WSN) is one of the key enablers for the Internet of Things (IoT), where WSNs will play an important role in future internet by several application scenarios, such as healthcare, agriculture, environment monitoring, and smart metering. However, today's radio spectrum...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2016, Vol.4, p.4609-4617
Main Authors: Zhu, Jiang, Song, Yonghui, Jiang, Dingde, Song, Houbing
Format: Article
Language:English
Subjects:
Agriculture
Algorithms
channel-grouping
Channels
Cognitive radio
Environmental monitoring
fairness access scheme
I.I.D. multi-armed bandit
Internet of Things
Machine learning
Medical services
modified UCB-tuned
Multi-armed bandit problems
Radio spectra
Spectrum allocation
Unknown environments
Wireless networks
Wireless sensor networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The wireless sensor network (WSN) is one of the key enablers for the Internet of Things (IoT), where WSNs will play an important role in future internet by several application scenarios, such as healthcare, agriculture, environment monitoring, and smart metering. However, today's radio spectrum is very crowded for the rapid increasing popularities of various wireless applications. Hence, WSN utilizing the advantages of cognitive radio technology, namely, cognitive radio-based WSN (CR-WSN), is a promising solution for spectrum scarcity problem of IoT applications. A major challenge in CR-WSN is utilizing spectrum more efficiently. Therefore, a novel channel access scheme is proposed for the problem that how to access the multiple channels with the unknown environment information for cognitive users, so as to maximize system throughput. The problem is modeled as I.I.D. multi-armed bandit model with M cognitive users and N arms (M
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2016.2600633