Controlling Interferences in Smart Building IoT Networks using Machine Learning

Per Lynggaard

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

The coexistence of many internet of things (IoT) networks in smart buildings poses a major challenge because they interfere mutually. In most settings this results in a greedy approach where each IoT node optimises its own performance parameters like increasing transmit-power, etc. However, this means that interference levels are increased, battery powers are wasted, and spectrum resources are exhausted in high dense settings. To control interference levels, share spectrum resources, and lower the overall power-consumptions this paper proposes a centralised control scheme which is based on a nonlinear cost function. This cost function is optimised by using machine learning in the form of a binary particle swarm optimisation (BPSO) algorithm. It has been found that this approach shares the spectrum in a fair way, it saves power and lowers the interference levels, and it dynamically adapts to network changes.

Original languageEnglish
JournalInternational Journal of Sensor Networks
Volume30
Issue number1
Pages (from-to)46-55
Number of pages10
ISSN1748-1279
DOIs
Publication statusPublished - 2019

Fingerprint

Intelligent buildings
Cost functions
Learning systems
Particle swarm optimization (PSO)
Electric power utilization
Internet of things

Keywords

  • BPSO
  • Centralised control scheme
  • Fading
  • Interferences
  • IoT networks
  • Machine learning
  • Smart buildings
  • Transmit-power regulation

Cite this

@article{6e9ff94be7184ba0adfac15a740cffa6,
title = "Controlling Interferences in Smart Building IoT Networks using Machine Learning",
abstract = "The coexistence of many internet of things (IoT) networks in smart buildings poses a major challenge because they interfere mutually. In most settings this results in a greedy approach where each IoT node optimises its own performance parameters like increasing transmit-power, etc. However, this means that interference levels are increased, battery powers are wasted, and spectrum resources are exhausted in high dense settings. To control interference levels, share spectrum resources, and lower the overall power-consumptions this paper proposes a centralised control scheme which is based on a nonlinear cost function. This cost function is optimised by using machine learning in the form of a binary particle swarm optimisation (BPSO) algorithm. It has been found that this approach shares the spectrum in a fair way, it saves power and lowers the interference levels, and it dynamically adapts to network changes.",
keywords = "BPSO, Centralised control scheme, Fading, Interferences, IoT networks, Machine learning, Smart buildings, Transmit-power regulation",
author = "Per Lynggaard",
year = "2019",
doi = "10.1504/IJSNET.2019.099233",
language = "English",
volume = "30",
pages = "46--55",
journal = "International Journal of Sensor Networks",
issn = "1748-1279",
publisher = "Inderscience Publishers",
number = "1",

}

Controlling Interferences in Smart Building IoT Networks using Machine Learning. / Lynggaard, Per.

In: International Journal of Sensor Networks, Vol. 30, No. 1, 2019, p. 46-55.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Controlling Interferences in Smart Building IoT Networks using Machine Learning

AU - Lynggaard, Per

PY - 2019

Y1 - 2019

N2 - The coexistence of many internet of things (IoT) networks in smart buildings poses a major challenge because they interfere mutually. In most settings this results in a greedy approach where each IoT node optimises its own performance parameters like increasing transmit-power, etc. However, this means that interference levels are increased, battery powers are wasted, and spectrum resources are exhausted in high dense settings. To control interference levels, share spectrum resources, and lower the overall power-consumptions this paper proposes a centralised control scheme which is based on a nonlinear cost function. This cost function is optimised by using machine learning in the form of a binary particle swarm optimisation (BPSO) algorithm. It has been found that this approach shares the spectrum in a fair way, it saves power and lowers the interference levels, and it dynamically adapts to network changes.

AB - The coexistence of many internet of things (IoT) networks in smart buildings poses a major challenge because they interfere mutually. In most settings this results in a greedy approach where each IoT node optimises its own performance parameters like increasing transmit-power, etc. However, this means that interference levels are increased, battery powers are wasted, and spectrum resources are exhausted in high dense settings. To control interference levels, share spectrum resources, and lower the overall power-consumptions this paper proposes a centralised control scheme which is based on a nonlinear cost function. This cost function is optimised by using machine learning in the form of a binary particle swarm optimisation (BPSO) algorithm. It has been found that this approach shares the spectrum in a fair way, it saves power and lowers the interference levels, and it dynamically adapts to network changes.

KW - BPSO

KW - Centralised control scheme

KW - Fading

KW - Interferences

KW - IoT networks

KW - Machine learning

KW - Smart buildings

KW - Transmit-power regulation

UR - http://www.scopus.com/inward/record.url?scp=85065095024&partnerID=8YFLogxK

U2 - 10.1504/IJSNET.2019.099233

DO - 10.1504/IJSNET.2019.099233

M3 - Journal article

VL - 30

SP - 46

EP - 55

JO - International Journal of Sensor Networks

JF - International Journal of Sensor Networks

SN - 1748-1279

IS - 1

ER -