A neural network propagation model for LoRaWAN and critical analysis with real-world measurements

Salaheddin Hosseinzadeh; Mahmood Almoathen; Hadi Larijani; Krystyna Curtis

doi:10.3390/bdcc1010007

A neural network propagation model for LoRaWAN and critical analysis with real-world measurements

Salaheddin Hosseinzadeh, Mahmood Almoathen, Hadi Larijani, Krystyna Curtis

Research output: Contribution to journal › Article › peer-review

142 Downloads (Pure)

Abstract

Among the many technologies competing for the Internet of Things (IoT), one of the most
promising and fast-growing technologies in this landscape is the Low-PowerWide-Area Network
(LPWAN). Coverage of LoRa, one of the main IoT LPWAN technologies, has previously been
studied for outdoor environments. However, this article focuses on end-to-end propagation in
an outdoor–indoor scenario. This article will investigate how the reported and documented outdoor
metrics are interpreted for an indoor environment. Furthermore, to facilitate network planning
and coverage prediction, a novel hybrid propagation estimation method has been developed and
examined. This hybrid model is comprised of an artificial neural network (ANN) and an optimized
Multi-Wall Model (MWM). Subsequently, real-world measurements were collected and compared
against different propagation models. For benchmarking, log-distance and COST231 models were
used due to their simplicity. It was observed and concluded that: (a) the propagation of the LoRa
Wide-Area Network (LoRaWAN) is limited to a much shorter range in this investigated environment
compared with outdoor reports; (b) log-distance and COST231 models do not yield an accurate
estimate of propagation characteristics for outdoor–indoor scenarios; (c) this lack of accuracy can be
addressed by adjusting the COST231 model, to account for the outdoor propagation; (d) a feedforward
neural network combined with a COST231 model improves the accuracy of the predictions. This
work demonstrates practical results and provides an insight into the LoRaWAN’s propagation in
similar scenarios. This could facilitate network planning for outdoor–indoor environments.

Original language	English
Number of pages	10
Journal	Big Data and Cognitive Computing
Volume	1
Issue number	1
DOIs	https://doi.org/10.3390/bdcc1010007
Publication status	Published - 14 Dec 2017

Keywords

LoRaWAN; LPWAN; propagation analysis and modeling; feedforward neural networks; COST231 multi-wall model

Documents and Links

10.3390/bdcc1010007

Hosseinzadeh, S. et al (2017) A neural network propagation model for LoRaWAN and critical analysis with real-world measurements
© 2017 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/).
Final published version, 1.63 MBLicence: CC BY

Fingerprint Dive into the research topics of 'A neural network propagation model for LoRaWAN and critical analysis with real-world measurements'. Together they form a unique fingerprint.

Cite this

@article{fdd789db7fd64abdbe1833194aa428b5,

title = "A neural network propagation model for LoRaWAN and critical analysis with real-world measurements",

abstract = "Among the many technologies competing for the Internet of Things (IoT), one of the mostpromising and fast-growing technologies in this landscape is the Low-PowerWide-Area Network(LPWAN). Coverage of LoRa, one of the main IoT LPWAN technologies, has previously beenstudied for outdoor environments. However, this article focuses on end-to-end propagation inan outdoor–indoor scenario. This article will investigate how the reported and documented outdoormetrics are interpreted for an indoor environment. Furthermore, to facilitate network planningand coverage prediction, a novel hybrid propagation estimation method has been developed andexamined. This hybrid model is comprised of an artificial neural network (ANN) and an optimizedMulti-Wall Model (MWM). Subsequently, real-world measurements were collected and comparedagainst different propagation models. For benchmarking, log-distance and COST231 models wereused due to their simplicity. It was observed and concluded that: (a) the propagation of the LoRaWide-Area Network (LoRaWAN) is limited to a much shorter range in this investigated environmentcompared with outdoor reports; (b) log-distance and COST231 models do not yield an accurateestimate of propagation characteristics for outdoor–indoor scenarios; (c) this lack of accuracy can beaddressed by adjusting the COST231 model, to account for the outdoor propagation; (d) a feedforwardneural network combined with a COST231 model improves the accuracy of the predictions. Thiswork demonstrates practical results and provides an insight into the LoRaWAN{\textquoteright}s propagation insimilar scenarios. This could facilitate network planning for outdoor–indoor environments.",

keywords = "LoRaWAN; LPWAN; propagation analysis and modeling; feedforward neural networks; COST231 multi-wall model",

author = "Salaheddin Hosseinzadeh and Mahmood Almoathen and Hadi Larijani and Krystyna Curtis",

note = "Changed template to article from paper Acceptance date from webpage OA; no funding note",

year = "2017",

month = dec,

day = "14",

doi = "10.3390/bdcc1010007",

language = "English",

volume = "1",

journal = "Big Data and Cognitive Computing",

issn = "2504-2289",

publisher = "MDPI",

number = "1",

}

TY - JOUR

T1 - A neural network propagation model for LoRaWAN and critical analysis with real-world measurements

AU - Hosseinzadeh, Salaheddin

AU - Almoathen, Mahmood

AU - Larijani, Hadi

AU - Curtis, Krystyna

N1 - Changed template to article from paper Acceptance date from webpage OA; no funding note

PY - 2017/12/14

Y1 - 2017/12/14

N2 - Among the many technologies competing for the Internet of Things (IoT), one of the mostpromising and fast-growing technologies in this landscape is the Low-PowerWide-Area Network(LPWAN). Coverage of LoRa, one of the main IoT LPWAN technologies, has previously beenstudied for outdoor environments. However, this article focuses on end-to-end propagation inan outdoor–indoor scenario. This article will investigate how the reported and documented outdoormetrics are interpreted for an indoor environment. Furthermore, to facilitate network planningand coverage prediction, a novel hybrid propagation estimation method has been developed andexamined. This hybrid model is comprised of an artificial neural network (ANN) and an optimizedMulti-Wall Model (MWM). Subsequently, real-world measurements were collected and comparedagainst different propagation models. For benchmarking, log-distance and COST231 models wereused due to their simplicity. It was observed and concluded that: (a) the propagation of the LoRaWide-Area Network (LoRaWAN) is limited to a much shorter range in this investigated environmentcompared with outdoor reports; (b) log-distance and COST231 models do not yield an accurateestimate of propagation characteristics for outdoor–indoor scenarios; (c) this lack of accuracy can beaddressed by adjusting the COST231 model, to account for the outdoor propagation; (d) a feedforwardneural network combined with a COST231 model improves the accuracy of the predictions. Thiswork demonstrates practical results and provides an insight into the LoRaWAN’s propagation insimilar scenarios. This could facilitate network planning for outdoor–indoor environments.

AB - Among the many technologies competing for the Internet of Things (IoT), one of the mostpromising and fast-growing technologies in this landscape is the Low-PowerWide-Area Network(LPWAN). Coverage of LoRa, one of the main IoT LPWAN technologies, has previously beenstudied for outdoor environments. However, this article focuses on end-to-end propagation inan outdoor–indoor scenario. This article will investigate how the reported and documented outdoormetrics are interpreted for an indoor environment. Furthermore, to facilitate network planningand coverage prediction, a novel hybrid propagation estimation method has been developed andexamined. This hybrid model is comprised of an artificial neural network (ANN) and an optimizedMulti-Wall Model (MWM). Subsequently, real-world measurements were collected and comparedagainst different propagation models. For benchmarking, log-distance and COST231 models wereused due to their simplicity. It was observed and concluded that: (a) the propagation of the LoRaWide-Area Network (LoRaWAN) is limited to a much shorter range in this investigated environmentcompared with outdoor reports; (b) log-distance and COST231 models do not yield an accurateestimate of propagation characteristics for outdoor–indoor scenarios; (c) this lack of accuracy can beaddressed by adjusting the COST231 model, to account for the outdoor propagation; (d) a feedforwardneural network combined with a COST231 model improves the accuracy of the predictions. Thiswork demonstrates practical results and provides an insight into the LoRaWAN’s propagation insimilar scenarios. This could facilitate network planning for outdoor–indoor environments.

KW - LoRaWAN; LPWAN; propagation analysis and modeling; feedforward neural networks; COST231 multi-wall model

U2 - 10.3390/bdcc1010007

DO - 10.3390/bdcc1010007

M3 - Article

VL - 1

JO - Big Data and Cognitive Computing

JF - Big Data and Cognitive Computing

SN - 2504-2289

IS - 1

ER -