2021/09/09 by Benjamin Sliwa, Sliwa, Benjamin, Hendrik Schippers +3 · 1 citation
Engineering · #Advanced MIMO Systems Optimization #FOS: Computer and information sciences #FOS: Electrical engineering #Green IT and Sustainability #Networking and Internet Architecture (cs.NI) #Signal Processing (eess.SP) #Telecommunications and Broadcasting Technologies #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2109.04117
openalex publication_date 2021/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In order to satisfy the ever-growing Quality of Service (QoS) requirements of\ninnovative services, cellular communication networks are constantly evolving.\nRecently, the 5G NonStandalone (NSA) mode has been deployed as an intermediate\nstrategy to deliver high-speed connectivity to early adopters of 5G by\nincorporating Long Term Evolution (LTE) network infrastructure. In addition to\nthe technological advancements, novel communication paradigms such as\nanticipatory mobile networking aim to achieve a more intelligent usage of the\navailable network resources through exploitation of context knowledge. For this\npurpose, novel methods for proactive prediction of the end-to-end behavior are\nseen as key enablers. In this paper, we present a first empirical analysis of\nclient-based end-to-end data rate prediction for 5G NSA vehicle-to-cloud\ncommunications. Although this operation mode is characterized by massive\nfluctuations of the observed data rate, the results show that conventional\nmachine learning methods can utilize locally acquirable measurements for\nachieving comparably accurate estimations of the end-to-end behavior.\n