MS4PAN: Measurement System for Path-Aware Networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Path-Aware Networks (PANs) allow applications to choose the network paths their data traverses. However, they require application developers to translate their performance requirements (e.g., in terms of latency, throughput and data loss) to a set of paths available through a PAN, which can be a cumbersome process especially when dealing with multiple PANs at the same time. In this paper, we propose MS4PAN, a tool for app developers to select the best paths based on app-specific requirements in Path-Aware Networks. We investigate several network requirements for different use cases as well as the difficulties for app developers to interact with different network architectures. We provide a tool that automatically finds the best paths that fulfill a set of requirements. We evaluate MS4PAN in SCIONLab, an experimental testbed and implementation of a SCION network. Our software helps developers by providing a simple abstraction while dealing with different network archi-tectures.

Original languageEnglish
Title of host publication2024 IEEE 13th International Conference on Cloud Networking, CloudNet 2024
EditorsDiogo Menezes Ferrazani Mattos, Igor Monteiro Moraes, Thi Mai Trang Nguyen, Rodrigo de Souza Couto, Marcelo Goncalves Rubinstein
PublisherIEEE
ISBN (Electronic)9798350376562
DOIs
Publication statusPublished - 31 Dec 2024
Event13th IEEE International Conference on Cloud Networking, CloudNet 2024 - Rio de Janeiro, Brazil
Duration: 27 Nov 202429 Nov 2024
Conference number: 13

Conference

Conference13th IEEE International Conference on Cloud Networking, CloudNet 2024
Abbreviated titleCloudNet 2024
Country/TerritoryBrazil
CityRio de Janeiro
Period27/11/2429/11/24

Keywords

  • n/a OA procedure

Fingerprint

Dive into the research topics of 'MS4PAN: Measurement System for Path-Aware Networks'. Together they form a unique fingerprint.

Cite this