AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation

Researchers developed an AI-driven approach to forecast spectrum demand for wireless networks, achieving 89% accuracy when tested across five Canadian cities. The machine learning models use multiple data sources including site licenses and crowdsourced data to help regulators optimize spectrum allocation and planning.

• →AI and ML models achieved 89% accuracy (R² = 0.89) in predicting wireless spectrum demand using multiple data proxies.
• →The approach was validated across five major Canadian cities, demonstrating scalability and robustness.
• →Models combine site license data with crowdsourced information to create reliable spectrum demand estimates.
• →The solution enables dynamic spectrum planning and better resource allocation for network operators.
• →Research addresses growing challenges in spectrum management due to rapidly increasing wireless service demand.