Optimal allocation of virtual machines in multi-cloud environments with reserved and on-demand pricing

Abstract

In the Cloud Computing market, a significant number of cloud providers offer Infrastructure as a Service (IaaS), including the capability of deploying virtual machines of many different types. The deployment of a service in a public provider generates a cost derived from the rental of the allocated virtual machines. In this paper we present LLOOVIA (Load Level based OpimizatiOn for VIrtual machine Allocation), an optimization technique designed for the optimal allocation of the virtual machines required by a service, in order to minimize its cost, while guaranteeing the required level of performance. LLOOVIA considers virtual machine types, different kinds of limits imposed by providers, and two price schemas for virtual machines: reserved and on-demand. LLOOVIA, which can be used with multi-cloud environments, provides two types of solutions: (1) the optimal solution and (2) the approximated solution based on a novel approach that uses binning applied on histograms of load levels. An extensive set of experiments has shown that when the size of the problem is huge, the approximated solution is calculated in a much shorter time and is very close to the optimal one. The technique presented has been applied to a set of case studies, based on the Wikipedia workload. These cases demonstrate that LLOOVIA can handle problems in which hundreds of virtual machines of many different types, multiple providers, and different kinds of limits are used.

Cost Minimization of Virtual Machine Allocation in Public Clouds Considering Multiple Applications

“…Finally, the most related work is [6]. This work covers all the characteristics considered here, except that it only deals with a single application.…”

“…This work covers all the characteristics considered here, except that it only deals with a single application. The objective of our paper is to extend [6] to solve the cost optimization problem when several applications have to be allocated on the same cloud resources.…”

“…The model presented in this paper is very similar to the one in [6], but extended to allow multiple applications to be deployed in the same (shared) cloud infrastructure. Most of the concepts and notation in [6] are still relevant, being the main differences: a) the workload is not longer a single number per timeslot, but a set of numbers, one per application, and b) the performance of any given instance class (defined later) is not a single number, but also a set of numbers.…”

“…Hiring too much means a waste of money; on the other hand, hiring too little may reduce profits or, even worse, incur economic penalties if SLAs are not met. Therefore, there is a broad research in order to answer this question and to find the most cost-effective allocation, such as [1], [4,5,6], [9,10], [14,15] or [18].…”

“…A previous VM allocation approach, referred to as LLOOVIA (Load Level based OptimizatiOn for VIrtual machine Allocation) [6], combined a long-term and a short-term strategy, organized in two phases, to take advantage of both reserved and on demand VMs. LLOOVIA is designed to minimize allocation costs, while guaranteeing the fulfillment of a determined level of performance.…”