Jiawei Huang

ORCID: 0000-0003-4819-2585
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Software-Defined Networks and 5G
  • Network Traffic and Congestion Control
  • Cloud Computing and Resource Management
  • Wireless Networks and Protocols
  • Mobile Ad Hoc Networks
  • Caching and Content Delivery
  • Interconnection Networks and Systems
  • Advanced Wireless Network Optimization
  • Opportunistic and Delay-Tolerant Networks
  • Advanced Optical Network Technologies
  • Image and Video Quality Assessment
  • Video Coding and Compression Technologies
  • Peer-to-Peer Network Technologies
  • Vehicular Ad Hoc Networks (VANETs)
  • Network Time Synchronization Technologies
  • Flow Experience in Various Fields
  • Age of Information Optimization
  • Wireless Communication Networks Research
  • UAV Applications and Optimization
  • Face and Expression Recognition
  • Machine Learning in Healthcare
  • Green IT and Sustainability
  • Wireless Communication Security Techniques
  • Wireless Sensor Networks and IoT
  • Advanced Clustering Algorithms Research

Central South University
2016-2025

Institute of Automation
2025

Chinese Academy of Sciences
2025

Jilin University
2023-2024

Guangzhou Huali College
2024

Southern University of Science and Technology
2023-2024

China Southern Power Grid (China)
2024

Nanjing University of Posts and Telecommunications
2021

University of Minnesota
2015

Guangdong University of Technology
2015

Multipath transmission control protocol (MPTCP) allows a TCP connection to operate across multiple paths simultaneously and becomes highly attractive support the emerging mobile devices with various radio interfaces improve resource utilization as well robustness. The existing multipath congestion algorithms, however, are mainly loss-based prefer lower drop rates, leading severe performance degradation in wireless communication systems, where random packet losses occur frequently. To address...

10.1109/tcomm.2016.2584615 article EN IEEE Transactions on Communications 2016-06-23

In data center networks, a large number of concurrent TCP connections suffer the Incast throughput collapse due to packet drops in shallow-buffered Ethernet switches. this work, we first reveal theoretically and empirically that controlling IP size is much more effective avoiding than cutting congestion window under severe congestion. We further design general supporting scheme Packet Slicing, which adjusts on widely used commodity The uses standard ICMP signaling, makes no modification...

10.1109/tcc.2018.2810870 article EN IEEE Transactions on Cloud Computing 2018-03-01

10.1109/icassp49660.2025.10887625 article EN ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025-03-12

In data center networks, many network-intensive applications typically suffer TCP incast throughput collapse when bursty concurrent flows share a single bottleneck link. To address the problem, we first reveal theoretically and empirically that controlling number of is much more effective in reducing probability than congestion window. We further propose novel cross-layer design called Adaptive Request Schedule (ARS), which dynamically adjusts by batching application requests according to...

10.1109/infocom.2016.7524533 article EN 2016-04-01

Many Carrier Sense Multiple Access (CSMA) and Time Division (TDMA) based medium access control (MAC) protocols for vehicular ad hoc networks (VANETs) have been proposed recently. Contrary to the common perception that they are competitors, we argue underlying strategies used in these MAC complementary. Based on this insight, design CTMAC, a protocol synthesizes existing strategies; namely, random accessing channel (used CSMA-style protocols) arbitral reserving TDMA-based protocols). CTMAC...

10.3390/s17020338 article EN cc-by Sensors 2017-02-10

Providing deadline-sensitive services is a challenge in data centers. Because of the conservativeness additive increase congestion avoidance, current transmission control protocols are inefficient utilizing super high bandwidth This may cause many flows to miss their deadlines before achieving available bandwidths. We propose an Adaptive-Acceleration Data Center TCP, A <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> DTCP, which takes...

10.1109/tc.2014.2345393 article EN IEEE Transactions on Computers 2014-01-01

In vehicular ad hoc networks (VANETs), the medium access control (MAC) protocol is of great importance to provide time-critical safety applications. Contemporary multihop broadcast protocols in VANETs usually choose farthest node range as forwarder reduce number forwarding hops. However, this paper, we demonstrate that may experience large contention delay case high vehicle density. We propose an IEEE 802.11-based VDF address issue emergency message dissemination. To achieve tradeoff between...

10.1155/2014/584164 article EN cc-by The Scientific World JOURNAL 2014-01-01

Modern data-center applications generate a diverse mix of short and long flows with different performance requirements weaknesses. The are typically delay-sensitive but to suffer the head-of-line blocking out-of-order problems. Recent solutions prioritize meet their latency requirements, while damaging throughput-sensitive flows. To solve these problems, we design Coding-based Adaptive Packet Spraying (CAPS) that effectively mitigates negative impact on each other. exploit availability...

10.1109/infocom.2018.8486354 article EN IEEE INFOCOM 2022 - IEEE Conference on Computer Communications 2018-04-01

Modern data center topologies often take the form of a multi-rooted tree with rich parallel paths to provide high bandwidth. However, various path diversities caused by traffic dynamics, link failures and heterogeneous switching equipments widely exist in production datacenter network. Therefore, multi-path load balancer should be robust these diversities. Although prior fine-grained schemes such as RPS Presto make full use available paths, they are prone experience packet reordering problem...

10.1109/icnp.2019.8888076 article EN 2019-10-01

Abstract In the data center networks, multipath transmission control protocol(MPTCP) uses multiple subflows to balance traffic over parallel paths and achieve high throughput. Despite much recent progress in improving MPTCP performance center, how adjust number of according network status has remained elusive. this paper, we reveal theoretically empirically that controlling concurrent is very important reducing flow completion time (FCT) under dynamic. We further propose a novel design...

10.1186/s13677-020-00160-3 article EN cc-by Journal of Cloud Computing Advances Systems and Applications 2020-02-24

In Priority Flow Control (PFC) enabled datacenter networks (DCNs), PFC is inevitably triggered due to bursty traffic even with end-to-end congestion control. Load balancing as a complementary mechanism transport protocols can make rerouting decisions in time alleviate PFC's head-of-line (HoL) blocking problem. However, prior solutions designed for lossy DCNs do not work well PFC-enabled networks, because the unreliable signals such separate local queue length, round-trip (RTT), explicit...

10.1145/3542637.3542641 article EN 2022-07-01

Modern datacenter topologies typically are multi-rooted trees consisting of multiple paths between any given pair hosts. Recent load balancing designs focus on making full use available parallel to provide high bisection bandwidth. However, they agnostic the mixed traffic generated by diverse applications in data centers and respectively same granularity rerouting flows regardless flow type. Therefore, short suffer long-tailed queueing delay reordering problems, while throughputs long also...

10.1145/3337821.3337866 article EN 2019-07-25

Modern data center nowadays leverages highly concurrent TCP connections between thousands of computer servers to achieve high system performance and service reliability. However, recent works have shown that, in the many-to-one barrier-synchronized communication pattern, a large number suffer Incast problem due packet drops shallow-buffered Ethernet switches. This unavoidably leads severe under-utilization link capacity. In this work, we first reveal theoretically empirically that...

10.1109/icnp.2015.39 article EN 2015-11-01

SUMMARY The fair allocation of the resources is an important issue in wireless local area network (WLAN) because all nodes compete for same radio channel. When uplink and downlink transmission congestion protocol (TCP) flows coexist WLAN, service biased toward TCP flows, tend to starve. In this article, we investigate special up/down unfairness problem point out that direct cause acknowledgement (ACK) packets occupy most buffer space access point. We thus propose a management algorithm...

10.1002/dac.2469 article EN International Journal of Communication Systems 2012-11-06

Modern data center networks are usually constructed in multi-rooted tree topologies, which require the highly efficient multi-path load balancing to achieve high link utilization. Recent packet-level balancer obtains throughput by spraying packets all paths, but it easily leads packet reordering under network asymmetry. The flow-level or flowlet-level avoids reordering, while reducing utilization due their inflexibility. To solve these problems, we design a Queueing Delay Aware Packet...

10.1109/icnp.2018.00017 article EN 2018-09-01
Coming Soon ...