AI-Driven Adaptive Communications for Energy-Efficient Underwater Acoustic Sensor Networks
Sensors · 2025-06-14 · 25 (12) · 3729
DOI: 10.3390/s25123729 ↗At a glance
Journal article in Sensors, published online on 2025-06-14. Written by A Ur Rehman and 2 co-authors. Institution: Dipartimento di Ingegneria Elettrica Elettronica e Informatica (DIEEI), University of Catania & CNIT, Viale A. Doria 6, 95125 Catania, Italy. Cited 21 times so far (Crossref); 21 references. The full text is freely available (open access, CC BY 4.0). Funded by: European Union under the Italian National Recovery and Resilience Plan (NRRP) of NextGenerationEU, partnership on “Telecommunications of the Future” (PE0000001….
Abstract (original language)
Underwater acoustic sensor networks, crucial for marine monitoring, face significant challenges, including limited bandwidth, high delay, and severe energy constraints. Addressing these limitations requires an energy-efficient design to ensure network survivability, reliability, and reduced operational costs. This paper proposes an artificial intelligence-driven framework aimed at enhancing energy efficiency and sustainability in applications of marine wildlife monitoring in underwater sensor networks, according to the vision of implementing an underwater acoustic sensor network. The framework integrates intelligent computing directly into underwater sensor nodes, employing lightweight AI models to locally classify marine species. Transmitting only classification results, instead of raw data, significantly reduces data volume, thus conserving energy. Additionally, a software-defined radio methodology dynamically adapts transmission parameters such as modulation schemes, packet length, and transmission power to further minimize energy consumption and environmental disruption. GNU Radio simulations evaluate the framework effectiveness using metrics like energy consumption, bit error rate, throughput, and delay. Adaptive transmission strategies implicitly ensure reduced energy usage as compared to non-adaptive transmission solutions employing fixed communication parameters. The results illustrate the framework ability to effectively balance energy efficiency, performance, and ecological impact. This research contributes directly to ongoing development in sustainable and energy-efficient underwater wireless sensor network design and deployment.
Subjects
Author keywords
Authors and institutions
- Dipartimento di Ingegneria Elettrica Elettronica e Informatica (DIEEI), University of Catania & CNIT, Viale A. Doria 6, 95125 Catania, Italy.
ORCID profiles: A Ur Rehman, Laura Galluccio
Funding
- European Union under the Italian National Recovery and Resilience Plan (NRRP) of NextGenerationEU, partnership on “Telecommunications of the Future” (PE0000001…
Cite
APA
Rehman, A. U., Galluccio, L., & Morabito, G. (2025). AI-Driven Adaptive Communications for Energy-Efficient Underwater Acoustic Sensor Networks. Sensors, 25(12), 3729. https://doi.org/10.3390/s25123729
Vancouver
Rehman AU, Galluccio L, Morabito G. AI-Driven Adaptive Communications for Energy-Efficient Underwater Acoustic Sensor Networks. Sensors. 2025;25(12):3729. doi:10.3390/s25123729
BibTeX
@article{Rehman2025,
author = {Rehman, A Ur and Galluccio, Laura and Morabito, Giacomo},
title = {AI-Driven Adaptive Communications for Energy-Efficient Underwater Acoustic Sensor Networks},
journal = {Sensors},
year = {2025},
volume = {25},
number = {12},
pages = {3729},
doi = {10.3390/s25123729}
}
EUVIMED