Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters

Evagoras Makridis; Kyriakos M. Deliparaschos; Evangelia Kalyvianaki; Themistoklis Charalambous

doi:10.1109/ETFA.2017.8247677

Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters

Evagoras Makridis, Kyriakos M. Deliparaschos, Evangelia Kalyvianaki, Themistoklis Charalambous

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

Virtualized servers have been the key for the efficient deployment of cloud applications. As the application demand increases, it is important to dynamically adjust the CPU allocation of each component in order to save resources for other applications and keep performance high, e.g., the client mean response time (mRT) should be kept below a Quality of Service (QoS) target. In this work, a new form of Kalman filter, called the Maximum Correntropy Criterion Kalman Filter (MCC-KF), has been used in order to predict, and hence, adjust the CPU allocations of each component while the RUBiS auction site workload changes randomly as the number of clients varies. MCC-KF has shown high performance when the noise is non-Gaussian, as it is the case in the CPU usage. Numerical evaluations compare our designed framework with other current state-of-the-art using real-data via the RUBiS benchmark website deployed on a prototype Xen-virtualized cluster.

Original language	English
Title of host publication	Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	978-1-5090-6505-9
DOIs	https://doi.org/10.1109/ETFA.2017.8247677
Publication status	Published - 8 Jan 2018
MoE publication type	A4 Article in a conference publication
Event	IEEE International Conference on Emerging Technologies and Factory Automation - Limassol, Cyprus Duration: 12 Sep 2017 → 15 Sep 2017 Conference number: 22

Publication series

Name	Proceedings IEEE International Conference on Emerging Technologies and Factory Automation
Publisher	IEEE
ISSN (Print)	1946-0740
ISSN (Electronic)	2379-9560

Conference

Conference	IEEE International Conference on Emerging Technologies and Factory Automation
Abbreviated title	ETFA
Country	Cyprus
City	Limassol
Period	12/09/2017 → 15/09/2017

Keywords

resource provisioning
virtualized servers
CPU
allocation
CPU usage
RUBiS
Kalman filters

Access to Document

10.1109/ETFA.2017.8247677

Fingerprint Dive into the research topics of 'Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters'. Together they form a unique fingerprint.

Cite this

Makridis, E., Deliparaschos, K. M., Kalyvianaki, E., & Charalambous, T. (2018). Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters. In Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017 (Proceedings IEEE International Conference on Emerging Technologies and Factory Automation). IEEE. https://doi.org/10.1109/ETFA.2017.8247677

Makridis, Evagoras ; Deliparaschos, Kyriakos M. ; Kalyvianaki, Evangelia ; Charalambous, Themistoklis. / Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters. Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017. IEEE, 2018. (Proceedings IEEE International Conference on Emerging Technologies and Factory Automation).

@inproceedings{96bd3addbf5a4b21afdff22988644a5e,

title = "Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters",

abstract = "Virtualized servers have been the key for the efficient deployment of cloud applications. As the application demand increases, it is important to dynamically adjust the CPU allocation of each component in order to save resources for other applications and keep performance high, e.g., the client mean response time (mRT) should be kept below a Quality of Service (QoS) target. In this work, a new form of Kalman filter, called the Maximum Correntropy Criterion Kalman Filter (MCC-KF), has been used in order to predict, and hence, adjust the CPU allocations of each component while the RUBiS auction site workload changes randomly as the number of clients varies. MCC-KF has shown high performance when the noise is non-Gaussian, as it is the case in the CPU usage. Numerical evaluations compare our designed framework with other current state-of-the-art using real-data via the RUBiS benchmark website deployed on a prototype Xen-virtualized cluster.",

keywords = "resource provisioning, virtualized servers, CPU, allocation, CPU usage, RUBiS, Kalman filters",

author = "Evagoras Makridis and Deliparaschos, {Kyriakos M.} and Evangelia Kalyvianaki and Themistoklis Charalambous",

year = "2018",

month = jan,

day = "8",

doi = "10.1109/ETFA.2017.8247677",

language = "English",

series = "Proceedings IEEE International Conference on Emerging Technologies and Factory Automation",

publisher = "IEEE",

booktitle = "Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017",

address = "United States",

note = "IEEE International Conference on Emerging Technologies and Factory Automation, ETFA ; Conference date: 12-09-2017 Through 15-09-2017",

}

Makridis, E, Deliparaschos, KM, Kalyvianaki, E & Charalambous, T 2018, Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters. in Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017. Proceedings IEEE International Conference on Emerging Technologies and Factory Automation, IEEE, IEEE International Conference on Emerging Technologies and Factory Automation, Limassol, Cyprus, 12/09/2017. https://doi.org/10.1109/ETFA.2017.8247677

Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters. / Makridis, Evagoras; Deliparaschos, Kyriakos M.; Kalyvianaki, Evangelia; Charalambous, Themistoklis.

Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017. IEEE, 2018. (Proceedings IEEE International Conference on Emerging Technologies and Factory Automation).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters

AU - Makridis, Evagoras

AU - Deliparaschos, Kyriakos M.

AU - Kalyvianaki, Evangelia

AU - Charalambous, Themistoklis

N1 - Conference code: 22

PY - 2018/1/8

Y1 - 2018/1/8

N2 - Virtualized servers have been the key for the efficient deployment of cloud applications. As the application demand increases, it is important to dynamically adjust the CPU allocation of each component in order to save resources for other applications and keep performance high, e.g., the client mean response time (mRT) should be kept below a Quality of Service (QoS) target. In this work, a new form of Kalman filter, called the Maximum Correntropy Criterion Kalman Filter (MCC-KF), has been used in order to predict, and hence, adjust the CPU allocations of each component while the RUBiS auction site workload changes randomly as the number of clients varies. MCC-KF has shown high performance when the noise is non-Gaussian, as it is the case in the CPU usage. Numerical evaluations compare our designed framework with other current state-of-the-art using real-data via the RUBiS benchmark website deployed on a prototype Xen-virtualized cluster.

AB - Virtualized servers have been the key for the efficient deployment of cloud applications. As the application demand increases, it is important to dynamically adjust the CPU allocation of each component in order to save resources for other applications and keep performance high, e.g., the client mean response time (mRT) should be kept below a Quality of Service (QoS) target. In this work, a new form of Kalman filter, called the Maximum Correntropy Criterion Kalman Filter (MCC-KF), has been used in order to predict, and hence, adjust the CPU allocations of each component while the RUBiS auction site workload changes randomly as the number of clients varies. MCC-KF has shown high performance when the noise is non-Gaussian, as it is the case in the CPU usage. Numerical evaluations compare our designed framework with other current state-of-the-art using real-data via the RUBiS benchmark website deployed on a prototype Xen-virtualized cluster.

KW - resource provisioning

KW - virtualized servers

KW - CPU

KW - allocation

KW - CPU usage

KW - RUBiS

KW - Kalman filters

U2 - 10.1109/ETFA.2017.8247677

DO - 10.1109/ETFA.2017.8247677

M3 - Conference contribution

T3 - Proceedings IEEE International Conference on Emerging Technologies and Factory Automation

BT - Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017

PB - IEEE

T2 - IEEE International Conference on Emerging Technologies and Factory Automation

Y2 - 12 September 2017 through 15 September 2017

ER -

Makridis E, Deliparaschos KM, Kalyvianaki E, Charalambous T. Dynamic CPU resource provisioning in virtualized servers using maximum correntropy criterion Kalman filters. In Proceedings of the 22nd IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2017. IEEE. 2018. (Proceedings IEEE International Conference on Emerging Technologies and Factory Automation). https://doi.org/10.1109/ETFA.2017.8247677