Deliverable D3.2 - Final Report on Transport Protocol Enhancements

This deliverable provides a final report on the work on transport protocol enhancements done inWork Package 3. First, we report on the extensions made to the SCTP protocol that turn it into a viable alternative to TCP and allow to deliver a lower-latency transport service. Next, we describe our work...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:A New, Evolutive API and Transport-Layer Architecture for the Internet (NEAT) Evolutive API and Transport-Layer Architecture for the Internet (NEAT), 2017
Hauptverfasser: Grinnemo, Karl-Johan, Brunström, Anna, Fairhurst, Gorry, Hayes, David, Hurtig, Per, Khademi, Naeem, Ros, David, Rüngeler, Irene, Tüxen, Michael, Weinrank, Felix, Welzl, Michael
Format: Report
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This deliverable provides a final report on the work on transport protocol enhancements done inWork Package 3. First, we report on the extensions made to the SCTP protocol that turn it into a viable alternative to TCP and allow to deliver a lower-latency transport service. Next, we describe our work to develop a framework for providing a deadline-aware, less-than-best-effort transport service, targeting background traffic and thus addressing requirements on NEAT from the EMC use case. We also present our efforts to design and implement a latency-aware scheduler for MPTCP, which enables NEAT to offer a transport service that meets the needs of latency-sensitive applications, and that efficiently utilises available network resources. Lastly, this document informs on our work on coupled congestion control for TCP, a mechanism that treats a bundle of parallel TCP flows between the same pair of hosts as a single unit. By efficiently multiplexing concurrent TCP flows, our coupled congestion control alleviates the effects of queueing, and tends to result in a more efficient usage of available bandwidth, where the flows’ aggregate capacity share can be apportioned based on application preferences.