The flexibility and programmability provided by the Software-Defined Networking (SDN) paradigm allow network operators to upgrade their legacy IP network infrastructures with the aim of improving their control over the network. However, the full migration from IP to SDN is not straightforward, at least, in the short term. Thus, transitory network infrastructures combining IP and SDN nodes (named hybrid IP/SDN networks) are required to coexist, while the correct coordination between paradigms is crucial to maintain the required Quality of Service. In this paper, two optimization problems that are normally solved separately due to their opposite nature: i) traffic load balancing and ii) the reduction of network power consumption, are jointly considered. In particular, an heuristic named Hybrid Spreading Load Algorithm (HSLA), is proposed to jointly minimize the Maximum Link Utilization (MLU) and the network power consumption during the transition from IP to SDN networks. Simulations over topologies of different size considering diverse selection methods for the replacement of the nodes reveal that HSLA outperforms other state-of-the-art approaches that specifically tackle only one objective, either the traffic load balancing or the reduction of the network power consumption.

On the tradeoff between load balancing and energy-efficiency in hybrid IP/SDN networks / Galan-Jimenez, J.; Polverini, M.; Lavacca, F. G.; Herrera, J. L.; Berrocal, J.. - (2021), pp. 1-9. (Intervento presentato al convegno 12th International Conference on Network of the Future, NoF 2021 tenutosi a Coimbra; Portugal) [10.1109/NoF52522.2021.9609876].

On the tradeoff between load balancing and energy-efficiency in hybrid IP/SDN networks

Polverini M.;Lavacca F. G.;Berrocal J.
2021

Abstract

The flexibility and programmability provided by the Software-Defined Networking (SDN) paradigm allow network operators to upgrade their legacy IP network infrastructures with the aim of improving their control over the network. However, the full migration from IP to SDN is not straightforward, at least, in the short term. Thus, transitory network infrastructures combining IP and SDN nodes (named hybrid IP/SDN networks) are required to coexist, while the correct coordination between paradigms is crucial to maintain the required Quality of Service. In this paper, two optimization problems that are normally solved separately due to their opposite nature: i) traffic load balancing and ii) the reduction of network power consumption, are jointly considered. In particular, an heuristic named Hybrid Spreading Load Algorithm (HSLA), is proposed to jointly minimize the Maximum Link Utilization (MLU) and the network power consumption during the transition from IP to SDN networks. Simulations over topologies of different size considering diverse selection methods for the replacement of the nodes reveal that HSLA outperforms other state-of-the-art approaches that specifically tackle only one objective, either the traffic load balancing or the reduction of the network power consumption.
2021
12th International Conference on Network of the Future, NoF 2021
energy efficiency; heuristic; hybrid IP/SDN; load balancing; traffic engineering
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
On the tradeoff between load balancing and energy-efficiency in hybrid IP/SDN networks / Galan-Jimenez, J.; Polverini, M.; Lavacca, F. G.; Herrera, J. L.; Berrocal, J.. - (2021), pp. 1-9. (Intervento presentato al convegno 12th International Conference on Network of the Future, NoF 2021 tenutosi a Coimbra; Portugal) [10.1109/NoF52522.2021.9609876].
File allegati a questo prodotto
File Dimensione Formato  
Galan-Jimenez_On the tradeoff_2021.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 935.39 kB
Formato Adobe PDF
935.39 kB Adobe PDF   Contatta l'autore

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/11573/1695717
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
social impact