More Like this

1. An In-Depth Study of Uplink Performance of 5G mmWave Networks

   https://doi.org/10.1145/3538394.3546042  

   Moinak Ghoshal, Z. Jonny ( August 2022 , Proceedings of The 2nd ACM SIGCOMM Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases (5G-MeMU))

   The highly anticipated 5G mmWave technology promises to enable many uplink-oriented, latency-critical applications (LCAs) such as Augmented Reality and Connected Autonomous Vehicles. Nonetheless, recent measurement studies have largely focused on its downlink performance. In thiswork,we perform a systematic study of the uplink performance of commercial 5G mmWave networks across 3 major US cities and 2 mobile operators. Our study makes three contributions. (1) It reveals that 5G mmWave uplink performance is geographically diverse, substantially higher over LTE in terms of bandwidth and latency, but often erratic and suboptimal, which can degrade LCA performance. (2) Our analysis of control messages and PHY-level KPIs shows that the root causes for the suboptimal performance are fundamental to 5G mmWave and cannot be easily fixed via simple tuning of network configurations. (3) We identify various design and deployment optimizations that 5G operators can explore to bring 5G mmWave performance to the level needed to ultimately support the LCAs. 

   more » « less
2. An In-Depth Measurement Analysis of 5G mmWave PHY Latency and Its Impact on End-to-End Delay

   https://doi.org/10.1007/978-3-031-28486-1_28  

   Fez, Rostand ; Ramadan, Eman ; Ye, Wei ; Minneci, Benjamin ; Xie, Jack ; Narayanan, Arvind ; Hassan, Ahmad ; Qian, Feng ; Zhang, Zhi-Li ; Chandrashekar, Jaideep ; et al ( January 2023 , In Passive and Active Measurement Conference (PAM) 2023.)

   5G aims to offer not only significantly higher throughput than previous generations of cellular networks, but also promises millisecond (ms) and sub-millisecond (ultra-)low latency support at the 5G physical (PHY) layer for future applications. While prior measurement studies have confirmed that commercial 5G deployments can achieve up to several Gigabits per second (Gbps) throughput (especially with the mmWave 5G radio), are they able to deliver on the (sub) millisecond latency promise? With this question in mind, we conducted to our knowledge the first in-depth measurement study of commercial 5G mmWave PHY latency using detailed physical channel events and messages. Through carefully designed experiments and data analytics, we dissect various factors that influence 5G PHY latency of both downlink and uplink data transmissions, and explore their impacts on end-to-end delay. We find that while in the best cases, the 5G (mmWave) PHY-layer is capable of delivering ms/sub-ms latency (with a minimum of 0.09 ms for downlink and 0.76 ms for uplink), these happen rarely. A variety of factors such as channel conditions, re-transmissions, physical layer control and scheduling mechanisms, mobility, and application (edge) server placement can all contribute to increased 5G PHY latency (and thus end-to-end (E2E) delay). Our study provides insights to 5G vendors, carriers as well as application developers/content providers on how to better optimize or mitigate these factors for improved 5G latency performance. 

   more » « less
3. Virtual Function Placement and Traffic Steering over 5G Multi-Technology Networks

   https://doi.org/10.1109/NETSOFT.2018.8460097  

   Akhtar, Nabeel ; Matta, Ibrahim ; Raza, Ali ; Goratti, Leonardo ; Braun, Torsten ; Esposito, Flavio ( June 2018 , 2018 4th IEEE Conference on Network Softwarization and Workshops (NetSoft))

   Next-generation mobile networks (5G and beyond) are expected to provide higher data rates and ultra-low latency in support of demanding applications, such as virtual and augmented reality, robots and drones, etc. To meet these stringent requirements, edge computing constitutes a central piece of the solution architecture wherein functional components of an application can be deployed over the edge network so as to reduce bandwidth demand over the core network while providing ultra-low latency communication to users. In this paper, we investigate the joint optimal placement of virtual service chains consisting of virtual application functions (components) and the steering of traffic through them, over a 5G multi-technology edge network model consisting of both Ethernet and mmWave links. This problem is NP-hard. We provide a comprehensive “microscopic" binary integer program to model the system, along with a heuristic that is one order of magnitude faster than solving the corresponding binary integer program. Extensive evaluations demonstrate the benefits of managing virtual service chains (by distributing them over the edge network) compared to a baseline “middlebox" approach in terms of overall admissible virtual capacity. We observe significant gains when deploying mmWave links that complement the Ethernet physical infrastructure. Moreover, most of the gains are attributed to only 30% of these mmWave links. 

   more » « less
4. Do Larger (More Accurate) Deep Neural Network Models Help in Edge-assisted Augmented Reality?

   https://doi.org/10.1145/3472727.3472807  

   Meng, Jiayi ; Kong, Zhaoning ; Xu, Qiang ; Hu, Y. Charlie ( August 2021 , NAI'21: Proceedings of the ACM SIGCOMM 2021 Workshop on Network-Application Integration)

   Edge-assisted Augmented Reality (AR) which offloads computeintensive Deep Neural Network (DNN)-based AR tasks to edge servers faces an important design challenge: how to pick the DNN model out of many choices proposed for each AR task for offloading. For each AR task, e.g., depth estimation, many DNN-based models have been proposed over time that vary in accuracy and complexity. In general, more accurate models are also more complex; they are larger and have longer inference time. Thus choosing a larger model in offloading can provide higher accuracy for the offloaded frames but also incur longer turnaround time, during which the AR app has to reuse the estimation result from the last offloaded frame, which can lead to lower average accuracy. In this paper, we experimentally study this design tradeoff using depth estimation as a case study. We design optimal offloading schedule and further consider the impact of numerous factors such as on-device fast tracking, frame downsizing and available network bandwidth. Our results show that for edge-assisted monocular depth estimation, with proper frame downsizing and fast tracking, compared to small models, the improved accuracy of large models can offset its longer turnaround time to provide higher average estimation accuracy across frames under both LTE and 5G mmWave. 

   more » « less
5. MIA: A Transport-Layer Plugin for Immersive Applications in Millimeter Wave Access Networks

   https://doi.org/10.1109/INFOCOM53939.2023.10228878  

   Wu, Zongshen ; Huang, Chin-Ya ; Ramanathan, Parameswaran ( May 2023 , IEEE)

   The highly directional nature of the millimeter wave (mmWave) beams pose several challenges in using that spectrum for meeting the communication needs of immersive applications. In particular, the mmWave beams are susceptible to misalignments and blockages caused by user movements. As a result, mmWave channels are vulnerable to large fluctuations in quality, which in turn, cause disproportionate degradation in end-to-end performance of Transmission Control Protocol (TCP) based applications. In this paper, we propose a reinforcement learning (RL) integrated transport-layer plugin, Millimeter wave based Immersive Agent (MIA), for immersive content delivery over the mmWave link. MIA uses the RL model to predict mmWave link bandwidth based on the real-time measurement. Then, MIA cooperates with TCP’s congestion control scheme to adapt the sending rate in accordance with the predictions of the mmWave bandwidth. To evaluate the effectiveness of the proposed MIA, we conduct experiments using a mmWave augmented immersive testbed and network simulations. The evaluation results show that MIA improves end-to-end immersive performance significantly on both throughput and latency. 

   more » « less