EUVIMEDEUVIMED entdecken
Crossref

Multi‐Objective Resource Optimization in UAV ‐Enabled Heterogeneous Cellular Networks Using Serverless Federated Learning and Power‐Domain NOMA

Qinghua Song, Junru Yang, Amin Mohajer

Transactions on Emerging Telecommunications Technologies · 2025-08 · 36 (8)

DOI: 10.1002/ett.70210 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions on Emerging Telecommunications Technologies, online erschienen am 20.07.2025. Verfasst von Qinghua Song und 2 weiteren Autor:innen. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 51 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The integration of unmanned aerial vehicles ( UAVs ) into cellular networks has emerged as a promising solution to enhance connectivity and service quality in both urban and remote areas. In this paper, we propose a comprehensive framework that combines multi‐agent deep learning with backhaul traffic optimization to effectively manage resources in UAV ‐enabled communication networks. By leveraging the capabilities of intelligent reflecting surfaces ( IRS ) and cell‐free communication strategies, our approach aims to optimize backhaul traffic, ensuring seamless data transmission and improved network throughput. Our methodology involves a dynamic resource allocation mechanism that utilizes multi‐agent deep learning to accurately predict network demands and adaptively allocate resources. The process begins with the collection of real‐time network data, including user demand, traffic patterns, and UAV positions. This data is then fed into a deep learning model, where multiple agents collaboratively analyze and predict future network requirements. Based on the predictions, the resource allocation mechanism dynamically adjusts the distribution of resources, such as bandwidth and power, to meet the anticipated demand. This adaptive strategy enables the network to efficiently handle varying traffic loads, reducing congestion and latency. Furthermore, our backhaul traffic optimization technique focuses on minimizing the energy consumption of UAVs while maximizing their coverage and connectivity. By optimizing the flight paths and altitudes of UAVs , we ensure that they provide optimal coverage with minimal energy expenditure. Additionally, the IRS ‐assisted communication further enhances signal quality, reducing the need for high‐power transmissions and thus conserving energy. Our simulations show that our framework improves network throughput, energy efficiency, and reliability. It offers a promising way to manage resources in future UAV ‐enabled communication networks.

Zitieren

APA

Song, Q., Yang, J., & Mohajer, A. (2025). Multi‐Objective Resource Optimization in UAV ‐Enabled Heterogeneous Cellular Networks Using Serverless Federated Learning and Power‐Domain NOMA. Transactions on Emerging Telecommunications Technologies, 36(8). https://doi.org/10.1002/ett.70210

Vancouver

Song Q, Yang J, Mohajer A. Multi‐Objective Resource Optimization in UAV ‐Enabled Heterogeneous Cellular Networks Using Serverless Federated Learning and Power‐Domain NOMA. Transactions on Emerging Telecommunications Technologies. 2025;36(8). doi:10.1002/ett.70210

BibTeX
@article{Song2025,
  author = {Song, Qinghua and Yang, Junru and Mohajer, Amin},
  title = {Multi‐Objective Resource Optimization in UAV ‐Enabled Heterogeneous Cellular Networks Using Serverless Federated Learning and Power‐Domain NOMA},
  journal = {Transactions on Emerging Telecommunications Technologies},
  year = {2025},
  volume = {36},
  number = {8},
  doi = {10.1002/ett.70210}
}
Kostenlos starten →