Probabilistic Mobility Load Balancing for Multi-band 5G and Beyond Networks
Saria Al Lahham, Di Wu, Ekram Hossain, Xue Liu, Gregory Dudek
TL;DR
The paper addresses load balancing across multiple bands in beyond-5G networks by formulating a multi-objective stochastic UE-to-band assignment problem. It introduces Probabilistic Mobility Load Balancing (PMLB), which uses an epigraph-based linear programming transformation and relaxes integrality to derive probabilistic UE-band allocations; UEs are assigned by sampling from these distributions, with an event-driven trigger (LBI) controlling when re-optimization occurs. The approach balances band loads via $f_1(\mathbf{X})$ and minimizes inter-frequency handovers via $f_2(\mathbf{X})$, combined with a weight $w$. Simulation results show PMLB outperforms rule-based MLB and 3GPP MLB baselines in throughput and handover interruption time while maintaining high load balance across bands.
Abstract
The ever-increasing demand for data services and the proliferation of user equipment (UE) have resulted in a significant rise in the volume of mobile traffic. Moreover, in multi-band networks, non-uniform traffic distribution among different operational bands can lead to congestion, which can adversely impact the user's quality of experience. Load balancing is a critical aspect of network optimization, where it ensures that the traffic is evenly distributed among different bands, avoiding congestion and ensuring better user experience. Traditional load balancing approaches rely only on the band channel quality as a load indicator and to move UEs between bands, which disregards the UE's demands and the band resource, and hence, leading to a suboptimal balancing and utilization of resources. To address this challenge, we propose an event-based algorithm, in which we model the load balancing problem as a multi-objective stochastic optimization, and assign UEs to bands in a probabilistic manner. The goal is to evenly distribute traffic across available bands according to their resources, while maintaining minimal number of inter-frequency handovers to avoid the signaling overhead and the interruption time. Simulation results show that the proposed algorithm enhances the network's performance and outperforms traditional load balancing approaches in terms of throughput and interruption time.