RETRACTED ARTICLE: Optimizing radio access in 5G vehicle networks using novel machine learning-driven resource management

Modern wireless technologies and vehicular networks are unable to handle the enormous crossover of vehicle network requirements. In order to achieve objectives in a vehicle environment, managing resource has become a challenging endeavor. The 5G wireless protocol claims it provides exceptionally fas...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Optical and quantum electronics 2023-12, Vol.55 (14), Article 1270
Hauptverfasser: Natarajan, Rajesh, Mahadev, Natesh, Alfurhood, Badria Sulaiman, Ranjith, Christodoss Prasanna, Zaki, John, Manu, M. N.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Modern wireless technologies and vehicular networks are unable to handle the enormous crossover of vehicle network requirements. In order to achieve objectives in a vehicle environment, managing resource has become a challenging endeavor. The 5G wireless protocol claims it provides exceptionally fast, dependable, and delay-free connectivity. A crucial technology that will make 5G possible includes software-defined networking (SDN). It ensures improved performance everywhere. The major difficulties are limiting the expanding range of vehicles and ensuring uninterrupted changes inside the bases. Furthermore, very low latency and high reliability necessary for offering applications that require safety like autonomous driving. Effective resource allocation solutions are needed because of the small quantity of spectrum that's accessible and the fluid nature of vehicular communication. In order to keep the network functional effectively, interference and congestion in channels must be avoided, and priority approaches are needed to accommodate different users' demands. In the current piece, we suggested an energy allocation method for using a radio frequency in 5G networks for vehicles Boosting Ant Colony Optimization and Magnified Recurrent Neural Network (BACO–MRNN) based traffic classification. The BACO–MRNN algorithm imposed superior outcomes as measured by several parameters, combining precision of 97.23%, accuracy of 98.10%, F1-Score of 98.45%, recall of 98.15%, and RMSE of 30.10%. A highly complex aptitude for discrimination was also revealed by the BACO–MRNN classification. For connected vehicles to fulfill all of their potential and for smart modes of transportation to be noticed radio accessibility pertaining to 5G vehicle networks has to be effectively addressed. 5G vehicle networks are necessary for the widespread adoption of autonomous vehicles. In order to facilitate safe and efficient autonomous driving, 5G’s ultra-low latency and fast connectivity enable motor vehicles, amenities the cloud, and real-time communication.
ISSN:0306-8919
1572-817X
DOI:10.1007/s11082-023-05388-2