RoC prediction for Bi-objective cost-QoS optimization of cloud VoIP call allocations

J.M. Cortes-Mendoza; A. Tchernykh; G. Radchenko; A.Y. Drozdov; Suroegina Z.; Pavlyukova E.; Uzhinskaya L.

doi:10.1109/ICEnT.2017.32

RoC prediction for Bi-objective cost-QoS optimization of cloud VoIP call allocations

J.M. Cortes-Mendoza, A. Tchernykh, G. Radchenko, A.Y. Drozdov, Suroegina Z., Pavlyukova E., Uzhinskaya L.

Publikation: Konferenzbeitrag › Papier › Begutachtung

Abstract

In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective problem is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of sixty four strategies with dynamic prediction of the load. We show that our prediction rule that consider the number of Virtual Machines (VMs) running in the system improves the efficiency of traditional rate of change algorithm. It provides suitable quality of service and lower cost. Variations of VM startup time delays permit to evaluate the prediction rules under different scenarios and assess the robustness of all strategies. © 2017 IEEE.

Originalsprache	Englisch
Seiten	119-123
Seitenumfang	5
DOIs	https://doi.org/10.1109/ICEnT.2017.32
Publikationsstatus	Veröffentlicht - 2017
Veranstaltung	4th International Conference on Engineering and Telecommunication - Moscow, Russland Dauer: 25 Nov. 2020 → …

Konferenz

Konferenz	4th International Conference on Engineering and Telecommunication
Kurztitel	En and T 2017
Land/Gebiet	Russland
Ort	Moscow
Zeitraum	25/11/20 → …

Zugriff auf Dokument

10.1109/ICEnT.2017.32

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85049257255&doi=10.1109%2fICEnT.2017.32&partnerID=40&md5=b0c792f450e31785d1b4b473a20770b2

Dieses zitieren

@conference{25b26189536b4109ba5e443af8b0de97,

title = "RoC prediction for Bi-objective cost-QoS optimization of cloud VoIP call allocations",

abstract = "In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective problem is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of sixty four strategies with dynamic prediction of the load. We show that our prediction rule that consider the number of Virtual Machines (VMs) running in the system improves the efficiency of traditional rate of change algorithm. It provides suitable quality of service and lower cost. Variations of VM startup time delays permit to evaluate the prediction rules under different scenarios and assess the robustness of all strategies. {\textcopyright} 2017 IEEE.",

keywords = "bin packing, call allocation, cloud voice over IP, load prediction, quality of service, Costs, Forecasting, Internet telephony, Voice/data communication systems, Bin packing, Dynamic prediction, Load predictions, Prediction rules, QoS optimization, Scheduling strategies, Voice over IP, Quality of service",

author = "J.M. Cortes-Mendoza and A. Tchernykh and G. Radchenko and A.Y. Drozdov and Suroegina Z. and Pavlyukova E. and Uzhinskaya L.",

note = "Conference code: 134065 Export Date: 27 August 2021 Correspondence Address: Tchernykh, A.; CICESE Research CenterMexico; email: chernykh@cicese.mx; 4th International Conference on Engineering and Telecommunication, En and T 2017 ; Conference date: 25-11-2020",

year = "2017",

doi = "10.1109/ICEnT.2017.32",

language = "English",

pages = "119--123",

}

TY - CONF

T1 - RoC prediction for Bi-objective cost-QoS optimization of cloud VoIP call allocations

AU - Cortes-Mendoza, J.M.

AU - Tchernykh, A.

AU - Radchenko, G.

AU - Drozdov, A.Y.

AU - Z., Suroegina

AU - E., Pavlyukova

AU - L., Uzhinskaya

N1 - Conference code: 134065 Export Date: 27 August 2021 Correspondence Address: Tchernykh, A.; CICESE Research CenterMexico; email: chernykh@cicese.mx

PY - 2017

Y1 - 2017

N2 - In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective problem is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of sixty four strategies with dynamic prediction of the load. We show that our prediction rule that consider the number of Virtual Machines (VMs) running in the system improves the efficiency of traditional rate of change algorithm. It provides suitable quality of service and lower cost. Variations of VM startup time delays permit to evaluate the prediction rules under different scenarios and assess the robustness of all strategies. © 2017 IEEE.

AB - In this paper, we present cloud VoIP scheduling strategies to provide appropriate levels of quality of service to users, and cost to VoIP service providers. This bi-objective problem is reasonable and representative for real installations and applications. We conduct comprehensive simulation on real data of sixty four strategies with dynamic prediction of the load. We show that our prediction rule that consider the number of Virtual Machines (VMs) running in the system improves the efficiency of traditional rate of change algorithm. It provides suitable quality of service and lower cost. Variations of VM startup time delays permit to evaluate the prediction rules under different scenarios and assess the robustness of all strategies. © 2017 IEEE.

KW - bin packing

KW - call allocation

KW - cloud voice over IP

KW - load prediction

KW - quality of service

KW - Costs

KW - Forecasting

KW - Internet telephony

KW - Voice/data communication systems

KW - Bin packing

KW - Dynamic prediction

KW - Load predictions

KW - Prediction rules

KW - QoS optimization

KW - Scheduling strategies

KW - Voice over IP

KW - Quality of service

U2 - 10.1109/ICEnT.2017.32

DO - 10.1109/ICEnT.2017.32

M3 - Paper

SP - 119

EP - 123

T2 - 4th International Conference on Engineering and Telecommunication

Y2 - 25 November 2020

ER -

RoC prediction for Bi-objective cost-QoS optimization of cloud VoIP call allocations

Abstract

Konferenz

Zugriff auf Dokument

Fingerprint

Dieses zitieren