An Active-Passive Measurement Study of TCP Performance over LTE on High-speed Rails MobiCom'19

Jing Wang, Yufan Zheng, Yunzhe Ni, Chenren Xu, Feng Qian, Wangyang Li, Wantong Jiang, Yihua Cheng, Zhuo Cheng, Yuanjie Li, Xiufeng Xie, Yi Sun, Zhongfeng Wang.

High-speed rail (HSR) systems potentially provide a more efficient way of door-to-door transportation than airplane. However, they also pose unprecedented challenges in delivering seamless Internet service for on-board passengers. In this paper, we conduct a large-scale active-passive measurement study of TCP performance over LTE on HSR. Our measurement targets the HSR routes in China operating at above 300 km/h. We performed extensive data collection through both controlled setting and passive monitoring, obtaining 1732.9 GB data collected over 135719 km of trips. Leveraging such a unique dataset, we measure important performance metrics such as TCP goodput, latency, loss rate, as well as key characteristics of TCP flows, application breakdown, and users' behaviors. We further quantitatively study the impact of frequent cellular handover on HSR networking performance, and conduct in-depth examination of the performance of two widely deployed transport-layer protocols: TCP CUBIC and TCP BBR. Our findings reveal the performance of today's commercial HSR networks "in the wild", as well as identify several performance inefficiencies, which motivate us to design a simple yet effective congestion control algorithm based on BBR to further boost the throughput by up to 36.5%. They together highlight the need to develop dedicated protocol mechanisms that are friendly to extreme mobility.

SOFTSTAGE: Content Staging for Vehicular Content Delivery in Xpressive Internet Architecture ICDCS'19

Jing Wang, Chenren Xu, Wangyang Li, Zhenyi Li, Shuang Jiang and Peter Steenkiste.

Client mobility is a fundamental challenge when accessing the current Internet, especially in the context of vehicular networking because of its intermittent connectivity nature. Meanwhile, today's network applications are evolving from host-to-host communication to content retrieval, and fostering new designs of Information-centric networking (ICN) protocol and system optimized towards this end. In this paper, we present SOFTSTAGE, a client instructed ICN-based network layer function that effectively manages the edge caching to perform reactive content staging to improve vehicular content delivery without any assumption about the client mobility pattern. Experimental results based on an implementation in eXpressive Internet Architecture (XIA) shows that SOFTSTAGE achieves up to 10x throughput gain in vehicular networking environments.
A Multipath QUIC Scheduler for Mobile HTTP/2 APNET'19

Jing Wang, Yunfeng Gao, Chenren Xu

In recent years, QUIC protocol has shown great advantages for HTTPS over TCP in terms of improving handshake delay and head-of-line blocking. Multipath QUIC (MPQUIC) further opens up the opportunity to leverage path diversity for realizing various optimization goals, especially for mobile access. In this paper, we present a context-aware MPQUIC packet scheduler dedicated to mobile HTTP/2. Specifically, the scheduler takes into account the stream priority (from HTTP/2 dependency tree) for stream-aware downlink packet scheduling by exclusively transferring each stream at a time while maintaining the relative stream completing order. Additionally, ACK packets are scheduled by choosing the path with the lowest one-way delay to reduce overall RTT and expedite loss recovery. Real-world experiments show that our scheduler reduces page load time by up to 8.5\% and stream average completion time by up to 12.9\% over the status-quo.
@inproceedings{yu2013scalable, title={Scalable opportunistic vanet content routing with encounter information}, author={Yu, Yu-Ting and Li, Yuanjie and Ma, Xingyu and Shang, Wentao and Sanadidi, MY and Gerla, Mario}, booktitle={Network Protocols (ICNP), 2013 21st IEEE International Conference on}, pages={1--6}, year={2013}, organization={IEEE} }

Selected Honors & Awards

President Scholarship @ Peking University (Top 7.5%).