An Analysis of Double Q-learning Based Energy Management Strategies for TEG-powered IoT Devices

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F23%3A10253446" target="_blank" >RIV/61989100:27240/23:10253446 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10145999" target="_blank" >https://ieeexplore.ieee.org/document/10145999</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/JIOT.2023.3283599" target="_blank" >10.1109/JIOT.2023.3283599</a>

Jazyk výsledku

angličtina

Název v původním jazyce

An Analysis of Double Q-learning Based Energy Management Strategies for TEG-powered IoT Devices

Popis výsledku v původním jazyce

The study presents a self-learning controller for managing the energy in an Internet-of-Things (IoT) device powered by energy harvested from a thermoelectric generator (TEG). The device&apos;s controller is based on a double Q-learning (DQL) method; the hardware incorporates a TEG energy harvesting subsystem with a DC/DC converter, a load module with a microcontroller, and a LoRaWAN communications interface. The model is controlled according to adaptive measurements and transmission periods. The controller&apos;s reward policy evaluates the level of charge available to the device. The controller applies and evaluates various learning parameters and reduces the learning rate over time. Using four years of historical soil temperature data in an experimental simulation of several controller configurations, the DQL controller demonstrated correct operation, a low learning rate and high cumulative rewards. The best energy management controller operated with a completed cycle and missed cycle ratio of 98.5 %. The novelty of the presented approach is discussed in relation to state-of-the-art methods in adaptive ability, learning processes and practical applications of the device. Author

Název v anglickém jazyce

An Analysis of Double Q-learning Based Energy Management Strategies for TEG-powered IoT Devices

Popis výsledku anglicky

The study presents a self-learning controller for managing the energy in an Internet-of-Things (IoT) device powered by energy harvested from a thermoelectric generator (TEG). The device&apos;s controller is based on a double Q-learning (DQL) method; the hardware incorporates a TEG energy harvesting subsystem with a DC/DC converter, a load module with a microcontroller, and a LoRaWAN communications interface. The model is controlled according to adaptive measurements and transmission periods. The controller&apos;s reward policy evaluates the level of charge available to the device. The controller applies and evaluates various learning parameters and reduces the learning rate over time. Using four years of historical soil temperature data in an experimental simulation of several controller configurations, the DQL controller demonstrated correct operation, a low learning rate and high cumulative rewards. The best energy management controller operated with a completed cycle and missed cycle ratio of 98.5 %. The novelty of the presented approach is discussed in relation to state-of-the-art methods in adaptive ability, learning processes and practical applications of the device. Author

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

<a href="/cs/project/FW03010194" target="_blank" >FW03010194: Vývoj systému pro monitoring a vyhodnocení vybraných rizikových faktorů fyzické zátěže pracovních operací v kontextu Průmyslu 4.0.</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

IEEE Internet of Things Journal

ISSN

2327-4662

e-ISSN

—

Svazek periodika

10

Číslo periodika v rámci svazku

23

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

10

Strana od-do

18919-18929

Kód UT WoS článku

001098109800046

EID výsledku v databázi Scopus

2-s2.0-85161612417