UMCC: Uncoupling Multipath Congestion Control through Shared Bottleneck Detection in Path-Aware Networks

There has been a lot of effort in improving coupled congestion control in multipath scenarios by locating shared bottlenecks. However, without transparency and control in the network, these approaches come with high complexity potentially impacting performance in uncongested conditions. At the same time, Path-Aware Networking provides new opportunities to applications and protocols to identify shared bottlenecks more effectively. In this work, we propose UMCC, an uncoupled multipath congestion control algorithm based on SCION that identifies and locates shared bottlenecks. We demonstrate the fairness of UMCC by comparing it with MPTCP at a shared bottleneck. Our results show that UMCC can precisely locate the exact bottleneck up to 70% of the time and increases throughput by 35% by avoiding shared bottlenecks.

Authors

Institutions

Publication Details

Published
2024-09-09
DOI
https://doi.org/10.1109/lcn60385.2024.10639760
Primary Topic
Network Traffic and Congestion Control
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

UMCC: Uncoupling Multipath Congestion Control through Shared Bottleneck Detection in Path-Aware Networks

David Hausheer, Marten Gartner
Network Traffic and Congestion Control
article

UMCC: Uncoupling Multipath Congestion Control through Shared Bottleneck Detection in Path-Aware Networks

David Hausheer, Marten Gartner
article en

Abstract

There has been a lot of effort in improving coupled congestion control in multipath scenarios by locating shared bottlenecks. However, without transparency and control in the network, these approaches come with high complexity potentially impacting performance in uncongested conditions. At the same time, Path-Aware Networking provides new opportunities to applications and protocols to identify shared bottlenecks more effectively. In this work, we propose UMCC, an uncoupled multipath congestion control algorithm based on SCION that identifies and locates shared bottlenecks. We demonstrate the fairness of UMCC by comparing it with MPTCP at a shared bottleneck. Our results show that UMCC can precisely locate the exact bottleneck up to 70% of the time and increases throughput by 35% by avoiding shared bottlenecks.

Otto-von-Guericke-Universität Magdeburg (DE)
Openalex Percentile: Top 84%
Network Traffic and Congestion Control
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.