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

TL;DR

This paper introduces an AI-driven, multi-granularity spectrum management framework within O-RAN that dynamically forecasts and trades spectrum, enhancing adaptability and efficiency through a marketplace model and advanced AI techniques.

Contribution

It presents a novel, flexible spectrum-sharing framework combining AI forecasting and a marketplace for dynamic trading within O-RAN architecture.

Findings

GenAI improves spectrum prediction accuracy.

Marketplace enables real-time spectrum trading.

Framework increases spectrum utilization efficiency.

Abstract

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.