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

TL;DR

This paper introduces machine learning models that leverage crowdsourced data and environmental features to accurately predict wireless radio metrics in diverse urban and indoor settings, aiding network planning.

Contribution

The paper presents CRC-ML-Radio Metrics, a novel suite of models that improve wireless metric predictions using crowdsourced data combined with local environmental features.

Findings

Achieved RMSE of 9.76-11.69 dB for RSRP

Achieved RMSE of 2.90-3.23 dB for RSRQ

Validated on over 300,000 data points across Canadian cities

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.