Contextual Combinatorial Beam Management via Online Probing for Multiple Access mmWave Wireless Networks

TL;DR

This work addresses beam management in dense mmWave networks by formulating joint transceiver pairing and beam selection as a contextual combinatorial MAB problem. It couples online probing with a contextual knowledge map built from long-term LoS/NLoS predictions (grid-based) and short-term spatial-temporal predictions (GCN+LSTM) to guide arm selection. A novel CCBM algorithm using attention-based exploration and an early stopping criterion achieves a sublinear regret bound of $O(T^{3/4}\log T)$ and optimizes load balancing via a beam-level penalty, demonstrated through realistic 3D indoor simulations where it outperforms UCB and CC-MAB baselines in throughput and robustness under localization noise. The results suggest CCBM as a scalable, low-overhead approach for next-generation access networks, enabling efficient, load-balanced multi-access beam management in challenging mmWave environments.

Abstract

Due to the exponential increase in wireless devices and a diversification of network services, unprecedented challenges, such as managing heterogeneous data traffic and massive access demands, have arisen in next-generation wireless networks. To address these challenges, there is a pressing need for the evolution of multiple access schemes with advanced transceivers. Millimeter-wave (mmWave) communication emerges as a promising solution by offering substantial bandwidth and accommodating massive connectivities. Nevertheless, the inherent signaling directionality and susceptibility to blockages pose significant challenges for deploying multiple transceivers with narrow antenna beams. Consequently, beam management becomes imperative for practical network implementations to identify and track the optimal transceiver beam pairs, ensuring maximum received power and maintaining high-quality access service. In this context, we propose a Contextual Combinatorial Beam Management (CCBM) framework tailored for mmWave wireless networks. By leveraging advanced online probing techniques and integrating predicted contextual information, such as dynamic link qualities in spatial-temporal domain, CCBM aims to jointly optimize transceiver pairing and beam selection while balancing the network load. This approach not only facilitates multiple access effectively but also enhances bandwidth utilization and reduces computational overheads for real-time applications. Theoretical analysis establishes the asymptotically optimality of the proposed approach, complemented by extensive evaluation results showcasing the superiority of our framework over other state-of-the-art schemes in multiple dimensions.

Figures (7)

• Figure 1: Overview of the short-term prediction model framework.
• Figure 2: Workflow of CCBM procedure.
• Figure 3: Comparison of regret among different schemes.
• Figure 4: Reward under different beam probing budgets.
• Figure 5: Comparison of average user throughput among different schemes.

Theorems & Definitions (5)

• Theorem 1
• proof
• Theorem 2
• proof
• Lemma 1