JLJinhao Liu

Jinhao Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jinhao Liu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    UniProxy: Breaking the Per-Flow Barrier in Multipath Proxy Design

    by Jinhao Liu, Jiangping Han, Kaiping Xue

    The widespread deployment of multi-homed Local Area Networks (LANs) has made it increasingly feasible to leverage multiple Internet paths via Performance Enhancing Proxies (PEPs). However, most existing designs treat each proxied flow as an independent transport session, applying full-fledged multipath transmission on a per-flow basis. This approach limits resource sharing and restricts scheduling flexibility across flows. Our analysis further reveals that isolated flow management leads to excessive per-flow window usage regardless of intra-flow scheduling, resulting in a fundamental throughput bottleneck. In this paper, we present UniProxy, a proxy framework that unifies both the management and scheduling of proxied flows over a cohesive multipath transport architecture. Unlike conventional designs that treat each flow as an independent transport session, UniProxy multiplexes all proxied flows over a single MPQUIC connection, assigning each to a distinct QUIC stream. This design enables unified flow management and flexible, coordinated scheduling across heterogeneous paths. At its core, UniProxy introduces two tightly integrated algorithms: (i) a stream-to-path assignment that favors path consistency per stream to minimize reordering overhead, while balancing load globally; (ii) a Token-based Round-Robin (TRR) packet scheduling that dynamically regulates stream transmission on preferred paths while opportunistically utilizing alternate paths to exploit residual bandwidth and preserve inter-flow fairness. Extensive evaluation shows that this joint design avoids throughput degradation under receive buffer constraints and sustains fairness across concurrent flows, while maintaining robust performance under diverse network conditions. For example, in real-network tests, it achieves 12.9%–17.5% higher throughput compared to existing multipath proxies.

  • Open Access

    Collaborative Multi-Flow Congestion Control via Deep Reinforcement Learning

    by Qiangqiang Wei, Jiangping Han, Kaiping Xue, Jinhao Liu, Naiqiang Qiao, Hao Chen


  • From an In-Depth Understanding of Multipath TCP Enhancement Schemes to an Adaptive Control Framework in Wireless Networks

    by Jiangping Han, Yitao Xing, Jinhao Liu, Kaiping Xue, Jian Li, David S. L. Wei, Qibin Sun, Jun Lu

    Multipath TCP (MPTCP) has gained popularity to enhance data transmission. From the last decade, proposed MPTCP enhancement schemes for congestion control, path management, and packet scheduling, have been used to benefit transmission performance. However, despite their efforts, they are exigent with a comprehensive understanding of real-world performance to guide the implementation of MPTCP to a more complex wireless network. To that end, we conduct a measurement-driven study of MPTCP enhancement schemes, providing insights and in-depth demonstrations of their performance with a comprehensive real-world platform. Our finding indicates that the enhancement schemes struggle to consistently maintain high performance at all times. One can achieve optimal efficiency in its specific scenarios, but suffers extreme degradation at times. To eliminate this transmission uncertainty in wireless networks, we further propose an adaptive control framework OLSch to integrate different schemes, emphasizing their strengths to provide consistently high performance. To be specific, OLSch is implemented with different scheduling schemes and leverages an online-learning-driven approach to choose one that best fits the current network conditions. Evaluations show that OLSch obviously improves the stability of transmission in harsh network scenarios, eliminates performance degradation, and increases the 95% tail throughput by 1.45×-2.39×.


  • Toward High-Quality Real-Time Video Streaming: An Efficient Multi-Stream and Multi-Path Scheduling Framework

    by Jiangping Han, Jinhao Liu, Kaiping Xue, Qibin Sun, Jun Lu

    Real-time video streaming requires high throughput and low delivery time for enhanced user’s Quality of Experience (QoE). This motivates the use of multi-path transmission to improve performance. However, ensuring target performance within specified deadlines and priorities for video frames is particularly crucial for real-time communication and video quality, especially in scenarios with limited resources. To address this challenge, we propose a novel framework, vStreamPth, to guarantee high-quality real-time video streaming through multi-path transmission. For essential quality assurance, vStreamPth incorporates key requirement indicators that guide the transmission decisions of video frames across predefined multiple paths. In this framework, lightweight and robust decision-making is achieved through the collaboration of application-oriented and network-oriented data scheduling. Specifically, it employs robustness estimation to maintain the non-blocking delivery of frames, and further applies online fine-tuning to correct variations caused by changes in end-to-end transmission and multi-path network conditions. We implement a prototype of vStreamPth in Linux user space and conduct a thorough evaluation. Experimental results demonstrate the absolute improvement of vStreamPth in achieving high QoE and deadline satisfaction ratio compared to existing multi-path solutions.