Contextual Bandits and Reconfigurable Intelligent Surfaces for Predictive LTM Handover Decisions

TL;DR

This paper proposes an integrated approach using predictive modeling, RIS, and contextual bandits to optimize handover decisions in next-generation wireless networks, reducing unnecessary handovers and improving link reliability.

Contribution

It introduces a novel combination of RIS, signal prediction, and a CMAB-based decision mechanism for proactive and efficient handover management.

Findings

CMAB reduces handover frequency and ping-pong rate.

RIS enhances link reliability and coverage.

Predictive models improve handover decision accuracy.

Abstract

This article addresses the challenge of optimizing handover (HO) in next-generation wireless networks by integrating Reconfigurable Intelligent Surfaces (RIS), predicting received signal power, and utilizing learning-based decision-making. A conventional reactive HO mechanism, such as lower-layer triggered mobility (LTM), is enhanced through linear prediction to anticipate link degradation. Additionally, the use of RIS helps to mitigate signal blockage and extend coverage. An online trained non-linear Contextual Multi-Armed Bandit (CMAB) agent selects target gNBs based on context features, which reduces unnecessary HO and signaling overhead. Extensive simulations evaluate eight combinations of these techniques under realistic mobility and channel conditions. Results show that CMAB and RSRP prediction consistently reduce the number of HO, ping-pong rate and cell preparations, while RIS improves link reliability.