Bringing Carbon Awareness to Multi-Cloud Application Delivery

Data centers consume roughly 1--2% of the world's electricity, with the majority of it attributed to compute, making the computing industry a substantial source of greenhouse gas emissions. Resources in data centers typically focus on providing high performance and availability, but the questio...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy informatics review 2024-09, Vol.4 (3), p.26-31
Hauptverfasser: Maji, Diptyaroop, Pfaff, Ben, R, Vipin P, Sreenivasan, Rajagopal, Firoiu, Victor, Iyer, Sreeram, Josephson, Colleen, Pan, Zhelong, Sitaraman, Ramesh K.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Data centers consume roughly 1--2% of the world's electricity, with the majority of it attributed to compute, making the computing industry a substantial source of greenhouse gas emissions. Resources in data centers typically focus on providing high performance and availability, but the question of sustainability in managing these distributed resources often goes unnoticed over these other metrics. This problem will only exacerbate as the data center computing demand continues to increase. In this paper1, we address the sustainability aspect of load balancing in VMware's Avi Global Server Load Balancer (GSLB). Our GSLB deployment spans data centers across geographies and clouds and relies on geographical proximity to shift client application requests to the closest data center. In this work, we enhance the GSLB service to additionally consider the realtime carbon intensity at each data center as a factor in making a load-balancing choice. Our carbon-aware prototype shows an average of 21% and a maximum of 51% reduction in carbon emissions while operating with an acceptable latency.
ISSN:2770-5331
2770-5331
DOI:10.1145/3698365.3698370