Research Article
Biobjective VoIP Service Management in Cloud Infrastructure
Jorge M. Cortés-Mendoza,
1
Andrei Tchernykh,
1
Fermin A. Armenta-Cano,
1
Pascal Bouvry,
2
Alexander Yu. Drozdov,
3
and Loic Didelot
4
1
CICESE Research Center, Ensenada, BC, Mexico
2
University of Luxembourg, Luxembourg City, Luxembourg
3
Moscow Institute of Physics and Technology, Moscow, Russia
4
MIXvoip S.A., Steinsel, Luxembourg
Correspondence should be addressed to Andrei Tchernykh; chernykh@cicese.mx
Received 22 January 2016; Revised 3 July 2016; Accepted 16 August 2016
Academic Editor: Ligang He
Copyright © 2016 Jorge M. Cort´ es-Mendoza et al. Tis is an open access article distributed under the Creative Commons
Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
Voice over Internet Protocol (VoIP) allows communication of voice and/or data over the internet in less expensive and reliable
manner than traditional ISDN systems. Tis solution typically allows fexible interconnection between organization and companies
on any domains. Cloud VoIP solutions can ofer even cheaper and scalable service when virtualized telephone infrastructure is used
in the most efcient way. Scheduling and load balancing algorithms are fundamental parts of this approach. Unfortunately, VoIP
scheduling techniques do not take into account uncertainty in dynamic and unpredictable cloud environments. In this paper, we
formulate the problem of scheduling of VoIP services in distributed cloud environments and propose a new model for biobjective
optimization. We consider the special case of the on-line nonclairvoyant dynamic bin-packing problem and discuss solutions for
provider cost and quality of service optimization. We propose twenty call allocation strategies and evaluate their performance by
comprehensive simulation analysis on real workload considering six months of the MIXvoip company service.
1. Introduction
Voice over Internet Protocol (VoIP) has now become the most
popular technology to communicate for long distance calling
and is adopted all over the world. Together with general
aspects of quality of service (QoS) of the Internet and other
networks, like transmission rates, error rates, and other char-
acteristics, VoIP adds new requirements: voice quality, service
response time, throughput, loss, interrupts, jitter, latency,
resource utilization, and so on. Hypervisor-level scheduling,
trafc control, dynamic resource provisioning, and so forth
are issues to address for the VoIP providers to ensure QoS
and successful end-to-end business solution.
Efective VoIP scheduling involves many important
issues: load estimation and prediction, performance analysis,
system stability, call resource requirements estimation, rout-
ing, bandwidth limitation, resource selection for call alloca-
tion, and so forth [1–3].
Businesses provided VoIP systems are always looking for
a way to cut down costs. Beloglazov et al. 2012 [4] consider
efciency of resource management deployed on the infra-
structure and applications running on the system. One of
the ways to reduce a cost is to avoid provisioning of more
resources than required by users and QoS.
Cloud VoIP (CVoIP) solutions can ofer even cheaper and
scalable service by using virtualized telephone infrastructure
in the efcient way. However, Tchernykh et al., 2015 [5], show
that virtualization in cloud computing adds other complexity
dimensions to the problem in terms of parameter variation,
system uncertainty, dynamic consolidation of the virtual
machines (VMs), and their migrations.
In this paper, we continue study presented by Cort´ es-
Mendoza et al., 2015 [3], where we introduce a VoIP opti-
mization model and study fve call allocation strategies. We
describe and analyze a model for cloud VoIP services focusing
on two important aspects: QoS and VM utilization. We
Hindawi Publishing Corporation
Scientific Programming
Volume 2016, Article ID 5706790, 14 pages
http://dx.doi.org/10.1155/2016/5706790