Cargando…

Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach

Small-to-medium scale smart buildings are an important part of the Internet of Things (IoT). Wireless Sensor Networks (WSNs) are the major enabler for smart control in such environments. Reliability is among the key performance requirements for many loss-sensitive IoT and WSN applications, while Ene...

Descripción completa

Detalles Bibliográficos
Autores principales: Ateeq, Muhammad, Ishmanov, Farruh, Afzal, Muhammad Khalil, Naeem, Muhammad
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6359337/
https://www.ncbi.nlm.nih.gov/pubmed/30646555
http://dx.doi.org/10.3390/s19020309
_version_ 1783392219666841600
author Ateeq, Muhammad
Ishmanov, Farruh
Afzal, Muhammad Khalil
Naeem, Muhammad
author_facet Ateeq, Muhammad
Ishmanov, Farruh
Afzal, Muhammad Khalil
Naeem, Muhammad
author_sort Ateeq, Muhammad
collection PubMed
description Small-to-medium scale smart buildings are an important part of the Internet of Things (IoT). Wireless Sensor Networks (WSNs) are the major enabler for smart control in such environments. Reliability is among the key performance requirements for many loss-sensitive IoT and WSN applications, while Energy Consumption (EC) remains a primary concern in WSN design. Error-prone links, traffic intense applications, and limited physical resources make it challenging to meet these service goals—not only that these performance metrics often conflict with one another, but also require solving optimization problems, which are intrinsically NP-hard. Correctly forecasting Packet Delivery Ratio (PDR) and EC can play a significant role in different loss-sensitive application environments. With the ever-increasing availability of performance data, data-driven techniques are becoming popular in such settings. It is observed that a number of communication parameters like transmission power, packet size, etc., influence metrics like PDR and EC in diverse ways. In this work, different regression models including linear, gradient boosting, random forest, and deep learning are used for the purpose of predicting both PDR and EC based on such communication parameters. To evaluate the performance, a public dataset of the IEEE 802.15.4 network, containing measurements against more than 48,000 combinations of parameter configurations, is used. Results are evaluated using root mean square error and it turns out that deep learning achieves up to 98% accuracy for both PDR and EC predictions. These prediction results can help configure communication parameters taking into account the performance goals.
format Online
Article
Text
id pubmed-6359337
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-63593372019-02-06 Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach Ateeq, Muhammad Ishmanov, Farruh Afzal, Muhammad Khalil Naeem, Muhammad Sensors (Basel) Article Small-to-medium scale smart buildings are an important part of the Internet of Things (IoT). Wireless Sensor Networks (WSNs) are the major enabler for smart control in such environments. Reliability is among the key performance requirements for many loss-sensitive IoT and WSN applications, while Energy Consumption (EC) remains a primary concern in WSN design. Error-prone links, traffic intense applications, and limited physical resources make it challenging to meet these service goals—not only that these performance metrics often conflict with one another, but also require solving optimization problems, which are intrinsically NP-hard. Correctly forecasting Packet Delivery Ratio (PDR) and EC can play a significant role in different loss-sensitive application environments. With the ever-increasing availability of performance data, data-driven techniques are becoming popular in such settings. It is observed that a number of communication parameters like transmission power, packet size, etc., influence metrics like PDR and EC in diverse ways. In this work, different regression models including linear, gradient boosting, random forest, and deep learning are used for the purpose of predicting both PDR and EC based on such communication parameters. To evaluate the performance, a public dataset of the IEEE 802.15.4 network, containing measurements against more than 48,000 combinations of parameter configurations, is used. Results are evaluated using root mean square error and it turns out that deep learning achieves up to 98% accuracy for both PDR and EC predictions. These prediction results can help configure communication parameters taking into account the performance goals. MDPI 2019-01-14 /pmc/articles/PMC6359337/ /pubmed/30646555 http://dx.doi.org/10.3390/s19020309 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ateeq, Muhammad
Ishmanov, Farruh
Afzal, Muhammad Khalil
Naeem, Muhammad
Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach
title Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach
title_full Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach
title_fullStr Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach
title_full_unstemmed Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach
title_short Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach
title_sort multi-parametric analysis of reliability and energy consumption in iot: a deep learning approach
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6359337/
https://www.ncbi.nlm.nih.gov/pubmed/30646555
http://dx.doi.org/10.3390/s19020309
work_keys_str_mv AT ateeqmuhammad multiparametricanalysisofreliabilityandenergyconsumptioniniotadeeplearningapproach
AT ishmanovfarruh multiparametricanalysisofreliabilityandenergyconsumptioniniotadeeplearningapproach
AT afzalmuhammadkhalil multiparametricanalysisofreliabilityandenergyconsumptioniniotadeeplearningapproach
AT naeemmuhammad multiparametricanalysisofreliabilityandenergyconsumptioniniotadeeplearningapproach