MaxFlowSDN: SDN-Based Maximum Flow Routing for High-Throughput Data Center Networks

Large data centers continuously move data from one server to another due to up-or downscaling virtual server specifications to meet user requirements.Most data center topologies allow multipath routing between any pair of nodes within their network to increase throughput, as well as resilience against link failures.Several approaches have been proposed and developed to utilize these routes to improve network performance.Existing methods often face challenges in achieving maximum throughput across diverse topologies without requiring kernel modifications, leaving room for improvement in practicality and scalability.In this paper, we propose a novel system, MaxFlowSDN, which uses the maximum flow algorithm along with traditional SDN and TCP to deliver higher throughput in data centers.MaxFlowSDN yielded 80% higher throughput in the Fat-Tree topology compared to StandardTCP, ParallelTCP, and MPTCP.In DCell and BCube topologies, it achieved approximately 190% higher throughput than StandardTCP and nearly 50% improvement over ParallelTCP and MPTCP.For evaluation, we deployed our system in different data center topologies and compared our results against existing methods.These results demonstrate that MaxFlowSDN provides maximum flow throughput in the data center environment while addressing the limitations of current approaches.

Authors

Institutions

Publication Details

Journal
Ingénierie des systèmes d information
Published
2025-06-30
DOI
https://doi.org/10.18280/isi.300611
Primary Topic
Software-Defined Networks and 5G
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

MaxFlowSDN: SDN-Based Maximum Flow Routing for High-Throughput Data Center Networks

Norah S. Bin Saeed, Maazen Alsabaan, Mohammed J. F. Alenazi, Abdulrahman Almutari
Ingénierie des systèmes d information
Software-Defined Networks and 5G
article

MaxFlowSDN: SDN-Based Maximum Flow Routing for High-Throughput Data Center Networks

Norah S. Bin Saeed, Maazen Alsabaan, Mohammed J. F. Alenazi, Abdulrahman Almutari
article en

Abstract

Large data centers continuously move data from one server to another due to up-or downscaling virtual server specifications to meet user requirements.Most data center topologies allow multipath routing between any pair of nodes within their network to increase throughput, as well as resilience against link failures.Several approaches have been proposed and developed to utilize these routes to improve network performance.Existing methods often face challenges in achieving maximum throughput across diverse topologies without requiring kernel modifications, leaving room for improvement in practicality and scalability.In this paper, we propose a novel system, MaxFlowSDN, which uses the maximum flow algorithm along with traditional SDN and TCP to deliver higher throughput in data centers.MaxFlowSDN yielded 80% higher throughput in the Fat-Tree topology compared to StandardTCP, ParallelTCP, and MPTCP.In DCell and BCube topologies, it achieved approximately 190% higher throughput than StandardTCP and nearly 50% improvement over ParallelTCP and MPTCP.For evaluation, we deployed our system in different data center topologies and compared our results against existing methods.These results demonstrate that MaxFlowSDN provides maximum flow throughput in the data center environment while addressing the limitations of current approaches.

Ingénierie des systèmes d informationVol. 30(06)
King Saud University (SA)
King Saud University
Openalex Percentile: Top 77%
Software-Defined Networks and 5G
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.