Highly Dynamic and Flexible Spatio-Temporal Spectrum Management with AI-Driven O-RAN: A Multi-Granularity Marketplace Framework

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rasti, Mehdi, Ataeebojd, Elaheh, Taskooh, Shiva Kazemi, Monemi, Mehdi, Razmi, Siavash, Latva-aho, Matti
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913699022766080
author Rasti, Mehdi
Ataeebojd, Elaheh
Taskooh, Shiva Kazemi
Monemi, Mehdi
Razmi, Siavash
Latva-aho, Matti
author_facet Rasti, Mehdi
Ataeebojd, Elaheh
Taskooh, Shiva Kazemi
Monemi, Mehdi
Razmi, Siavash
Latva-aho, Matti
contents Current spectrum-sharing frameworks struggle with adaptability, often being either static or insufficiently dynamic. They primarily emphasize temporal sharing while overlooking spatial and spectral dimensions. We propose an adaptive, AI-driven spectrum-sharing framework within the O-RAN architecture, integrating discriminative and generative AI (GenAI) to forecast spectrum needs across multiple timescales and spatial granularities. A marketplace model, managed by an authorized spectrum broker, enables operators to trade spectrum dynamically, balancing static assignments with real-time trading. GenAI enhances traffic prediction, spectrum estimation, and allocation, optimizing utilization while reducing costs. This modular, flexible approach fosters operator collaboration, maximizing efficiency and revenue. A key research challenge is refining allocation granularity and spatio-temporal dynamics beyond existing models.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13891
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Highly Dynamic and Flexible Spatio-Temporal Spectrum Management with AI-Driven O-RAN: A Multi-Granularity Marketplace Framework
Rasti, Mehdi
Ataeebojd, Elaheh
Taskooh, Shiva Kazemi
Monemi, Mehdi
Razmi, Siavash
Latva-aho, Matti
Systems and Control
Machine Learning
Current spectrum-sharing frameworks struggle with adaptability, often being either static or insufficiently dynamic. They primarily emphasize temporal sharing while overlooking spatial and spectral dimensions. We propose an adaptive, AI-driven spectrum-sharing framework within the O-RAN architecture, integrating discriminative and generative AI (GenAI) to forecast spectrum needs across multiple timescales and spatial granularities. A marketplace model, managed by an authorized spectrum broker, enables operators to trade spectrum dynamically, balancing static assignments with real-time trading. GenAI enhances traffic prediction, spectrum estimation, and allocation, optimizing utilization while reducing costs. This modular, flexible approach fosters operator collaboration, maximizing efficiency and revenue. A key research challenge is refining allocation granularity and spatio-temporal dynamics beyond existing models.
title Highly Dynamic and Flexible Spatio-Temporal Spectrum Management with AI-Driven O-RAN: A Multi-Granularity Marketplace Framework
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2502.13891