Cloud Flat Rates Enabled via Fair Multi-resource Consumption - Management and Security in the Age of Hyperconnectivity Access content directly
Conference Papers Year : 2016

Cloud Flat Rates Enabled via Fair Multi-resource Consumption

Abstract

Many companies rent Virtual Machines (VM) from cloud providers to meet their computational needs. While this option is also available to end-users, they do not always take advantage of this option. One reason may be that it is common to pay on a per-VM-basis, whereas the telecommunications sector has shown that customers prefer flat rates. A flat rate for cloud services needs to define utilization thresholds, to cap the usage of heavy customers and thereby limit their impact on the flat rate price and the cloud performance. Unfortunately, customers consume multiple heterogenous resources in clouds, e.g., CPU, RAM, disk I/O and space, or network access. This makes the definition of a customer’s fair “cloud share” and according utilization thresholds complex.Backed by a questionnaire among more than 600 individuals, this paper designs the new Greediness Metric (GM) that formalizes an intuitive understanding of multi-resource fairness without access to consumers’ utility functions. This GM enables the introduction of attractive cloud flat rates and fair sharing policies for private/commodity clouds and provides incentive to customers to wisely determine VM configurations.
Fichier principal
Vignette du fichier
385745_1_En_3_Chapter.pdf (624.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01632743 , version 1 (10-11-2017)

Licence

Attribution

Identifiers

Cite

Patrick Poullie, Burkhard Stiller. Cloud Flat Rates Enabled via Fair Multi-resource Consumption. 10th IFIP International Conference on Autonomous Infrastructure, Management and Security (AIMS), Jun 2016, Munich, Germany. pp.30-44, ⟨10.1007/978-3-319-39814-3_3⟩. ⟨hal-01632743⟩
117 View
90 Download

Altmetric

Share

Gmail Facebook X LinkedIn More