Machine Learning for Modeling Wireless Radio Metrics with Crowdsourced Data and Local Environment Features

2025-01-02

AI Summary

To address insufficient prediction accuracy of radio signal strength (RSRP/RSRQ/RSSI) in indoor/outdoor 4G networks—including vertical dimension—this paper proposes a hybrid machine learning model integrating crowdsourced measurements with multi-source urban environmental features. We systematically incorporate 12 categories of geospatial features—including geographic coordinates, building density, and road topology—and design a collaborative architecture combining gradient-boosted trees and neural networks. Evaluated on over 300,000 real-world measurement points across Toronto, Montreal, and Vancouver, the model achieves RMSEs of 9.76–11.69 dB for RSRP, 2.90–3.23 dB for RSRQ, and 9.50–10.36 dB for RSSI—outperforming state-of-the-art baseline models. The approach significantly enhances cross-scenario generalization capability in complex urban environments and improves the precision of network quality-of-service assessment.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations

Abstract

This paper presents a suite of machine learning models, CRC-ML-Radio Metrics, designed for modeling RSRP, RSRQ, and RSSI wireless radio metrics in 4G environments. These models utilize crowdsourced data with local environmental features to enhance prediction accuracy across both indoor at elevation and outdoor urban settings. They achieve RMSE performance of 9.76 to 11.69 dB for RSRP, 2.90 to 3.23 dB for RSRQ, and 9.50 to 10.36 dB for RSSI, evaluated on over 300,000 data points in the Toronto, Montreal, and Vancouver areas. These results demonstrate the robustness and adaptability of the models, supporting precise network planning and quality of service optimization in complex Canadian urban environments.

Problem

• Machine Learning
• 4G Network
• Signal Strength Prediction

Innovation

• CRC-ML-Radio Metrics
• 4G Network Signal Prediction
• Machine Learning for Network Optimization