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

2025-02-19

AI Summary

Existing spectrum sharing frameworks suffer from static configurations, insufficient coupling across temporal, spatial, and spectral dimensions, and poor adaptability to the dynamic requirements of Open Radio Access Networks (O-RAN). Method: This paper proposes an AI-driven spatio-temporal-spectral joint dynamic spectrum management framework. It pioneers the deep integration of generative AI into spectrum management—unifying discriminative and generative models—and synergizes multi-scale time-series forecasting, spatial graph neural networks, and smart-contract-enabled multi-granularity spectrum markets to enable coordinated optimization from macro-level planning to micro-level real-time trading. Contribution/Results: We introduce the first adjustable-granularity, three-dimensional (spatio-temporal-spectral) dynamic sharing paradigm, overcoming traditional time-domain-centric, static, or coarse-grained allocation limitations. Simulation results demonstrate a 32% improvement in average throughput, a 41% reduction in end-to-end latency, and significant gains in spectrum utilization efficiency and heterogeneous network collaboration performance.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Algorithm Configuration
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• AI-driven spectrum-sharing in O-RAN
• Multi-granularity marketplace for spectrum trading
• Enhancing spatio-temporal spectrum management with GenAI

Innovation

• AI-driven spectrum-sharing framework
• Multi-granularity marketplace model
• Generative AI enhances traffic prediction