Dynamic NB-IoT Configuration: A Machine Learning-Driven Optimization Framework
Uložené v:
| Názov: | Dynamic NB-IoT Configuration: A Machine Learning-Driven Optimization Framework |
|---|---|
| Autori: | Abbas, Muhammad Tahir, Li, Yurong, Grinnemo, Karl-Johan, 1968, Brunstrom, Anna, 1967, Eklund, Johan, 1966, Rajiullah, Mohammad, 1981 |
| Zdroj: | DRIVE (Datadrivna latenskänsliga mobila tjänster för ett digitaliserat samhälle) IEEE Internet of Things Journal. 12(19):40098-40114 |
| Predmety: | CIoT, NB-IoT, energy efficiency, machine learn- ing, gradient boost, particle swarm optimization, Computer Science, Datavetenskap |
| Popis: | The deployment of Cellular Internet of Things (CIoT)is expected to reach over six billion devices by 2030. Many ofthese devices will be located in remote areas where replacingor recharging their batteries would be difficult and expensive.Therefore, it is crucial to configure these devices for efficientenergy use to avoid frequent battery replacements or recharging.However, optimizing the energy consumption of CIoT devices, con-sidering their applications and operating environmental conditions,presents a complex challenge. In response to this challenge, wepropose the Gradient-Boosted Learning Optimization for BatteryEfficiency (GLOBE) framework for dynamic configuration ofNarrowband Internet of Things (NB-IoT) devices. GLOBE adjuststhe radio layer of NB-IoT devices based on data transmissionpatterns and network conditions, enabling swift and automatedreconfiguration. Our results demonstrate that GLOBE reducesenergy consumption by 30% to 75% compared to baselineconfigurations, offering significant benefits for both networkoperators and end devices by improving energy efficiency. |
| Popis súboru: | electronic |
| Prístupová URL adresa: | https://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-106358 https://doi.org/10.1109/jiot.2025.3588596 |
| Databáza: | SwePub |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | The deployment of Cellular Internet of Things (CIoT)is expected to reach over six billion devices by 2030. Many ofthese devices will be located in remote areas where replacingor recharging their batteries would be difficult and expensive.Therefore, it is crucial to configure these devices for efficientenergy use to avoid frequent battery replacements or recharging.However, optimizing the energy consumption of CIoT devices, con-sidering their applications and operating environmental conditions,presents a complex challenge. In response to this challenge, wepropose the Gradient-Boosted Learning Optimization for BatteryEfficiency (GLOBE) framework for dynamic configuration ofNarrowband Internet of Things (NB-IoT) devices. GLOBE adjuststhe radio layer of NB-IoT devices based on data transmissionpatterns and network conditions, enabling swift and automatedreconfiguration. Our results demonstrate that GLOBE reducesenergy consumption by 30% to 75% compared to baselineconfigurations, offering significant benefits for both networkoperators and end devices by improving energy efficiency. |
|---|---|
| ISSN: | 23274662 |
| DOI: | 10.1109/jiot.2025.3588596 |