In-node cognitive power control in Wireless Sensor Networks

Michele Chincoli, Antonio Liotta

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)
1 Downloads (Pure)

Abstract

Reliability, interoperability and efficiency are fundamental in Wireless Sensor Network deployment. Herein we look at how transmission power control may be used to reduce interference, which is particularly problematic in high-density conditions. We adopt a distributed approach where every node has the ability to learn which transmission power is most appropriate, given the network conditions and quality of service targets. The status of the network is represented by the combination of three parameters: number of retransmissions, clear channel assessment attempts and the quantized average latency. The target is to maintain packet loss at the lowest possible level, whilst striving for minimum transmission power. The learning phase is managed by an ϵ-greedy strategy, which directs the physical layer of each node to choose between either a random action (exploration) or the best action (exploitation). We demonstrate as our learning sensors automatically discover the best trade off between power and quality.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Communications Workshops, ICC Workshops 2017
PublisherInstitute of Electrical and Electronics Engineers
Pages1099-1104
Number of pages6
ISBN (Electronic)9781509015252
DOIs
Publication statusPublished - 29 Jun 2017
Event2017 IEEE International Conference on Communications (ICC 2017) - Palais des Congrès - Porte Maillot, Paris, France
Duration: 21 May 201725 May 2017

Conference

Conference2017 IEEE International Conference on Communications (ICC 2017)
Abbreviated titleIEEE ICC 2017
Country/TerritoryFrance
CityParis
Period21/05/1725/05/17
OtherBridging People, Communities, and Cultures

Fingerprint

Dive into the research topics of 'In-node cognitive power control in Wireless Sensor Networks'. Together they form a unique fingerprint.

Cite this