Optimizing the trade-off between power saving and Quality of Service in the current Internet is a challenging research objective, whose difficulty stems also from the dominant presence of Transmission Control Protocol (TCP) traffic, and its elastic nature. More specifically, recent works support the possibility of improving energy efficiency of network devices by modulating switching and transmission capacity according to traffic load, whereas TCP traffic is in turn adaptive to the available resources. In a previous work, we have shown that an intertwining exists between capacity scaling approaches and TCP congestion control. In this paper, we investigate the reasons of such intertwining, and we evaluate how and how much the dynamics of the two algorithms affect each other’s performance. More specifically, we will show that such an interaction is essentially due to the relative speed of the two algorithms, which determines the conditions for the successful or unsuccessful coexistence of the two mechanisms.

Network interface power management and TCP congestion control: a troubled marriage

LOMBARDO, Alfio;SCHEMBRA, Giovanni
2016-01-01

Abstract

Optimizing the trade-off between power saving and Quality of Service in the current Internet is a challenging research objective, whose difficulty stems also from the dominant presence of Transmission Control Protocol (TCP) traffic, and its elastic nature. More specifically, recent works support the possibility of improving energy efficiency of network devices by modulating switching and transmission capacity according to traffic load, whereas TCP traffic is in turn adaptive to the available resources. In a previous work, we have shown that an intertwining exists between capacity scaling approaches and TCP congestion control. In this paper, we investigate the reasons of such intertwining, and we evaluate how and how much the dynamics of the two algorithms affect each other’s performance. More specifically, we will show that such an interaction is essentially due to the relative speed of the two algorithms, which determines the conditions for the successful or unsuccessful coexistence of the two mechanisms.
File in questo prodotto:
File Dimensione Formato  
R50.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Non specificato
Dimensione 1.65 MB
Formato Adobe PDF
1.65 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/18782
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact