Smooth Handovers via Smoothed Online Learning

TL;DR

This paper introduces a novel approach to optimizing cellular handovers using Smoothed Online Learning, leveraging extensive real-world data to improve seamless connectivity by accounting for network heterogeneity and device features.

Contribution

It presents the first countrywide study of handover optimization via SOL, modeling UE-cell associations dynamically and extending existing methods with realistic assumptions and robust guarantees.

Findings

Identified correlation between handover failures and network heterogeneity

Proposed a new HO optimization model incorporating device and cell features

Demonstrated superior performance of the algorithm in real-world scenarios

Abstract

With users demanding seamless connectivity, handovers (HOs) have become a fundamental element of cellular networks. However, optimizing HOs is a challenging problem, further exacerbated by the growing complexity of mobile networks. This paper presents the first countrywide study of HO optimization, through the prism of Smoothed Online Learning (SOL). We first analyze an extensive dataset from a commercial mobile network operator (MNO) in Europe with more than 40M users, to understand and reveal important features and performance impacts on HOs. Our findings highlight a correlation between HO failures/delays, and the characteristics of radio cells and end-user devices, showcasing the impact of heterogeneity in mobile networks nowadays. We subsequently model UE-cell associations as dynamic decisions and propose a realistic system model for smooth and accurate HOs that extends existing approaches by (i) incorporating device and cell features on HO optimization, and (ii) eliminating (prior) strong assumptions about requiring future signal measurements and knowledge of end-user mobility. Our algorithm, aligned with the O-RAN paradigm, provides robust dynamic regret guarantees, even in challenging environments, and shows superior performance in multiple scenarios with real-world and synthetic data.