TY - JOUR
T1 - Configurable cost-quality optimization of cloud-based VoIP
AU - Tchernykh, A.
AU - Cortés-Mendoza, J.M.
AU - Bychkov, I.
AU - Feoktistov, A.
AU - Didelot, L.
AU - Bouvry, P.
AU - Radchenko, G.
AU - Borodulin, K.
N1 - Cited By :3
Export Date: 27 August 2021
CODEN: JPDCE
Correspondence Address: Tchernykh, A.; CICESE Research Center, Carretera Ensenada-Tijuana 3918, Mexico; email: chernykh@cicese.mx
Funding details: Russian Foundation for Basic Research, RFBR, 18-07-01224
Funding details: Consejo Nacional de Ciencia y Tecnología, CONACYT, 178415
Funding details: Government Council on Grants, Russian Federation, 02.A03.21.0011
Funding text 1: This work is partially supported by Russian Foundation for Basic Research (RFBR)18-07-01224 and Act 211, Government of the Russian Federation[contract number 02.A03.21.0011]; and CONACYT, M?xico [grant number 178415].
Funding text 2: This work is partially supported by Russian Foundation for Basic Research (RFBR)18-07-01224 and Act 211, Government of the Russian Federation[contract number 02.A03.21.0011]; and CONACYT, México [grant number 178415].
Funding text 3: This work is partially supported by Russian Foundation for Basic Research (RFBR) 18-07-01224 and Act 211, Government of the Russian Federation [contract number 02.A03.21.0011 ]; and CONACYT , México [grant number 178415 ].
PY - 2019
Y1 - 2019
N2 - In this paper, we formulate configurable cloud-based VoIP call allocation problem as a special case of dynamic multi-objective bin-packing. We consider voice quality influenced by CPU stress, cost contributed by the number of billing hours for Virtual Machines (VMs) provisioning, and calls placed on hold due to under-provisioning resources. We distinguish call allocation strategies by the type and amount of information used for allocation: knowledge-free, utilization-aware, rental-aware, and load-aware. We propose and study a variety of strategies with static and dynamic policies of VM provisioning. To study realistic scenarios, we consider startup delays for VM provisioning, and three configurable parameters: utilization threshold, rental threshold, and prediction interval. They can be configured and dynamically adapted to cope with different objective preferences, workloads, and cloud properties. We conduct comprehensive simulation on the real workload of the MIXvoip company and show that the proposed strategies outperform ones currently in-use. © 2018 Elsevier Inc.
AB - In this paper, we formulate configurable cloud-based VoIP call allocation problem as a special case of dynamic multi-objective bin-packing. We consider voice quality influenced by CPU stress, cost contributed by the number of billing hours for Virtual Machines (VMs) provisioning, and calls placed on hold due to under-provisioning resources. We distinguish call allocation strategies by the type and amount of information used for allocation: knowledge-free, utilization-aware, rental-aware, and load-aware. We propose and study a variety of strategies with static and dynamic policies of VM provisioning. To study realistic scenarios, we consider startup delays for VM provisioning, and three configurable parameters: utilization threshold, rental threshold, and prediction interval. They can be configured and dynamically adapted to cope with different objective preferences, workloads, and cloud properties. We conduct comprehensive simulation on the real workload of the MIXvoip company and show that the proposed strategies outperform ones currently in-use. © 2018 Elsevier Inc.
KW - Bin packing
KW - Call allocation
KW - Cloud computing
KW - Cloud voice over IP
KW - Quality of service
KW - Scheduling
KW - Virtual machine
KW - Voice/data communication systems
KW - Allocation problems
KW - Allocation strategy
KW - Amount of information
KW - Configurable parameter
KW - Quality optimization
KW - Voice over IP
KW - Internet telephony
U2 - 10.1016/j.jpdc.2018.07.001
DO - 10.1016/j.jpdc.2018.07.001
M3 - Article
SN - 0743-7315
VL - 133
SP - 319
EP - 336
JO - J. Parallel Distrib. Comput.
JF - J. Parallel Distrib. Comput.
ER -