Environmental Monitoring Stations Data Transmission Using Reinforcement Learning Wavelet Compression Method

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F22%3A10250220" target="_blank" >RIV/61989100:27240/22:10250220 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S2405896322003366" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2405896322003366</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.ifacol.2022.06.021" target="_blank" >10.1016/j.ifacol.2022.06.021</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Environmental Monitoring Stations Data Transmission Using Reinforcement Learning Wavelet Compression Method

Popis výsledku v původním jazyce

The connection between environmental monitoring and the Internet of Things (IoT) raises new possibilities for data transmission from environmental wireless sensors networks (EWSN) and transferring parameters of interest to a cloud. EWSN uses a low-power wide-area networks (LPWAN) which allow only very limited data throughput and are subject to regional restriction. The paper investigates a self-learning wavelet compression algorithm driven by a strategy based on Q-learning (QL). This approach allows optimiation of the total amount of transmitted data by applying lossy wavelet transform compression. The aim of this research is to achieve optimal use of the available communication channel width and minimize loss of information using compression. The paper presents a simulation-based study with design methodology for a QL controller. The results showed that the loss of information due to lossy compression causes a relative error in range of 0.3-1.7 % for most of the environmental parameters. The results also revealed that lossy compression causes small errors in parameters which experience slow and infrequent changes. Copyright (C) 2022 The Authors.

Název v anglickém jazyce

Environmental Monitoring Stations Data Transmission Using Reinforcement Learning Wavelet Compression Method

Popis výsledku anglicky

The connection between environmental monitoring and the Internet of Things (IoT) raises new possibilities for data transmission from environmental wireless sensors networks (EWSN) and transferring parameters of interest to a cloud. EWSN uses a low-power wide-area networks (LPWAN) which allow only very limited data throughput and are subject to regional restriction. The paper investigates a self-learning wavelet compression algorithm driven by a strategy based on Q-learning (QL). This approach allows optimiation of the total amount of transmitted data by applying lossy wavelet transform compression. The aim of this research is to achieve optimal use of the available communication channel width and minimize loss of information using compression. The paper presents a simulation-based study with design methodology for a QL controller. The results showed that the loss of information due to lossy compression causes a relative error in range of 0.3-1.7 % for most of the environmental parameters. The results also revealed that lossy compression causes small errors in parameters which experience slow and infrequent changes. Copyright (C) 2022 The Authors.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

<a href="/cs/project/EF16_019%2F0000867" target="_blank" >EF16_019/0000867: Centrum výzkumu pokročilých mechatronických systémů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IFAC PapersOnLine. Volume 55

ISBN

—

ISSN

2405-8963

e-ISSN

—

Počet stran výsledku

6

Strana od-do

127-132

Název nakladatele

Elsevier

Místo vydání

Amsterdam

Místo konání akce

Sarajevo

Datum konání akce

17. 5. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000836230600021