Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation

Colin Brown, Mohamad Alkadamani, Halim Yanikomeroglu

TL;DR

The proposed ML models are tested and validated across five major Canadian cities, demonstrating their generalizability and robustness and assist spectrum regulators in dynamic spectrum planning, enabling better resource allocation and policy adjustments to meet future network demands.

Abstract

Accurately forecasting spectrum demand is a key component for efficient spectrum resource allocation and management. With the rapid growth in demand for wireless services, mobile network operators and regulators face increasing challenges in ensuring adequate spectrum availability. This paper presents a data-driven approach leveraging artificial intelligence (AI) and machine learning (ML) to estimate and manage spectrum demand. The approach uses multiple proxies of spectrum demand, drawing from site license data and derived from crowdsourced data. These proxies are validated against real-world mobile network traffic data to ensure reliability, achieving an R$^2$ value of 0.89 for an enhanced proxy. The proposed ML models are tested and validated across five major Canadian cities, demonstrating their generalizability and robustness. These contributions assist spectrum regulators in dynamic spectrum planning, enabling better resource allocation and policy adjustments to meet future network demands.

AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation

TL;DR

The proposed ML models are tested and validated across five major Canadian cities, demonstrating their generalizability and robustness and assist spectrum regulators in dynamic spectrum planning, enabling better resource allocation and policy adjustments to meet future network demands.

Abstract

Accurately forecasting spectrum demand is a key component for efficient spectrum resource allocation and management. With the rapid growth in demand for wireless services, mobile network operators and regulators face increasing challenges in ensuring adequate spectrum availability. This paper presents a data-driven approach leveraging artificial intelligence (AI) and machine learning (ML) to estimate and manage spectrum demand. The approach uses multiple proxies of spectrum demand, drawing from site license data and derived from crowdsourced data. These proxies are validated against real-world mobile network traffic data to ensure reliability, achieving an R value of 0.89 for an enhanced proxy. The proposed ML models are tested and validated across five major Canadian cities, demonstrating their generalizability and robustness. These contributions assist spectrum regulators in dynamic spectrum planning, enabling better resource allocation and policy adjustments to meet future network demands.
Paper Structure (20 sections, 1 equation, 5 figures, 2 tables)

This paper contains 20 sections, 1 equation, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Proposed Methodology
  3. Proxy Development and Validation
  4. Feature Integration
  5. Predictive Modeling Framework
  6. Experimental Setup
  7. Proxy Validation Setup
  8. Traffic Data
  9. Proxy Computation
  10. $P_{\text{BW}}$
  11. $P_{\text{Users}}$
  12. $P_{\text{Combined}}$
  13. ML Modeling Setup
  14. Data Preparation
  15. Spatial Processing
  16. ...and 5 more sections

Figures (5)

  • Figure 1: Integration of AI-enabled spectrum demand modeling within the broader spectrum planning and resource allocation framework.
  • Figure 2: Counts for the number of active user for a single MNO in Toronto taken from crowdsourced data and aggregated at grid tile level.
  • Figure 3: Geospatial distribution of proxy discrepancies in Montreal.
  • Figure 4: Scatter plot of actual vs. predicted spectrum demand values for the Combined Proxy using the best-performing XGBoost model.
  • Figure 5: Feature importance heatmap for XGBoost models trained with different proxies.