Identification and Analysis of a Unique Cell Selection Phenomenon in Public Unlicensed Cellular Networks Through Machine Learning

Abstract

Cellular operators deploy 4G License Assisted Access (LAA) and 5G NR-U base stations in the unlicensed spectrum, to enhance the overall network capacity. This work highlights a unique Physical Cell Id (PCI) related phenomenon observed in the public LAA operator deployments. Notably, the licensed and unlicensed carriers of a device may have the same PCI or different PCIs. The phenomenon is triggered by the combined effect of unlicensed deployment architectures and cell selection mechanisms. Consequently, the phenomenon will intensify manifold in 5G NR-U whose public deployment will soon commence. Unfortunately, the impact of this phenomenon on coexistence network performance is unexplored. It is also desirable to accurately identify the PCI scenarios at the device for improved cell selection and network performance. However, the data imbalance makes the classification problem challenging. This work addresses these problems through the following approach. Operator data from three LAA cellular providers is gathered and analyzed using machine learning algorithms. The impact of the phenomenon on LTE, LAA, and Wi-Fi components is demonstrated in three steps: First, the variation in network performance prediction accuracy in the PCI scenarios is examined. Second, the efficacy of numerosity reduction techniques used in data-driven cell selection is evaluated in both PCI scenarios. The third step entails a comparison of operator data analysis with network measurements. On-site experiments are conducted at the same PCI and different PCI sites to study the differences in real-time network performance. A controlled LTE-WiFi coexistence environment is created and multiple traffic categories are considered. Finally, a class-weight-based solution is proposed for PCI scenario identification. F-score of 0.75 and AUC-ROC of 0.84 is achieved for LAA, with a minimalist feature-set of SINR and Throughput.

Distributed Reinforcement Learning–based Seamless Multi-Connectivity Solution for Heterogeneous 5GNR and Wi-Fi Networks

“…Nevertheless, the study does not thoroughly explore the influence of coexistence on quality of service (QoS) metrics i.e., the impact of coexistence on parameters such as latency, packet loss, and other QoS factors that would enhance a comprehensive understanding of LTE-LAA coexistence with WiFi systems. The impact of a unique phenomenon related to Physical Cell Id (PCI) on integrated system including LTE, LAA, and Wi-Fi is demonstrated in [23] using machine learning algorithms. Although [23] contributes significantly to enhance LTE-LAA coexistence with WiFi systems, the study does not explicitly examine the impact of varying user densities on the observed PCI scenarios.…”

“…The impact of a unique phenomenon related to Physical Cell Id (PCI) on integrated system including LTE, LAA, and Wi-Fi is demonstrated in [23] using machine learning algorithms. Although [23] contributes significantly to enhance LTE-LAA coexistence with WiFi systems, the study does not explicitly examine the impact of varying user densities on the observed PCI scenarios. Particularly in scenarios marked by high traffic density, fluctuations in the dynamics of coexistence and PCI-related effects may vary, which may potentially affect the robustness of identified solutions.…”

Cellular Operator Data Meets Counterfactual Machine Learning

“…ML algorithms derive insights from raw data gathered through measurements and are better suited for comparing cellular network scenarios and contexts [6]. For example, two cell selection scenarios were identified in current unlicensed networks, which was not evident from the measurement-based analysis [7]. Network performance optimization can also benefit from datadriven inputs.…”