Multi-Connectivity and L4S in 5G Radio Access Networks: Throughput Enhancement and Low-Latency Delivery

Abstract

This thesis presents two complementary works addressing different aspects of 5G radio access networks: one focused on improving the received throughput through multi- connectivity, and the other on achieving low-latency delivery through L4S marking mechanisms. Multi-connectivity is anticipated to provide more reliable, higher data rate con- nections for cellular network users by leveraging all available radio resources across base stations within one or multiple radio access technology(ies) (RAT). It aims to improve user mobility through multi-RAT connections or mitigate quality of service (QoS) degradation when users connect to congested cells through load-balancing traffic among base stations and distributing the user’s flow across multiple links. Many studies have investigated the benefits of multi-connectivity across various network deployments using analytical models or simulated environments. In this work we critically assess these reported gains, particularly regarding system throughput. We argue that multi-connectivity’s advantages are primarily restricted to scenarios with a low user-to-base station ratio and that dense networks are less likely to benefit. We formulate the user-to-base station association and resource allocation within a Proportional Fair (PF) setting across varying user densities to examine this. Our findings show that multi-connectivity offers no superiority over the PF single-connectivity baseline in dense networks. Furthermore, in sparse networks, we show that while multi-connectivity can potentially enhance system throughput, it does not significantly improve individual users’ QoS, as the PF single-connectivity scheme can offer sufficient resources to every user. Complementing this throughput-oriented study, the second part of the thesis addresses low-latency delivery in evolving mobile networks, where many emerging services, such as cloud gaming, are highly latency-sensitive. In this context, the sender must react quickly to congestion, and its response must be adapted to the extent of the congestion. Otherwise, the link will be either underutilized or suffer from excessive latency. By integrating Low Loss Low Latency Scalable Throughput (L4S) into a disaggregated 5G Radio Access Network (RAN), we demonstrate its strong potential to simultaneously achieve low delay and high throughput for real-time mobile applications. We introduce a novel 3GPP-compliant marking scheme tailored for RAN, and compare it with the state-of-the-art RAN marking solution, L4Span. Our experiments suggest that our approach is superior in mitigating tail latency. We further examine the impact of our design on our L4S-compliant Web Real-Time Communication (WebRTC) stack using SCReAMv2, a congestion control algorithm designed for WebRTC media. Our results show substantial reductions in frame delays compared to non-L4S solutions, while also revealing practical limitations of SCReAMv2, including sender-side packet drops that can cause decoder stalls and video perceptual quality degradation.