Minimizing SLA Violation and Power Consumption in Cloud Data Centers Using Host State 3-Order Markov Chain Model

Li, Lianpeng; Dong, Jian; Zuo, Decheng; Zhao, Yao

doi:10.1109/hpcc/smartcity/dss.2019.00305

Cited by 3 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The power consumption of the two types of servers at different load levels are listed in Table 1. For details of the configuration of the two types of servers, and the four kinds of VM types, readers can refer to our previous work [7] .…”

Section: Methodsmentioning

confidence: 99%

“…We use two types of load to evaluate our model: a random workload and the PlanetLab [18] workload. For details of the load characteristics used in our experiment, readers can refer to our previous work [7] .…”

Section: Methodsmentioning

confidence: 99%

“…However, inaccurate predictions may lead to unnecessary VM migration, resulting in performance degradation. Therefore, we proposed an HS3MC prediction model in our previous research [7] . There, we proposed a 3rd-order Markov chain model to predict the host state, because we found that the higherorder Markov chain model can more accurately reflect the load characteristics.…”

Section: Related Workmentioning

confidence: 99%

“…Algorithm 2 first sorts vmList in descending order according to the CPU utilization, and then it finds the target host for every VM in vmList (lines 1-4). For a host, we first use our HSD algorithm to detect whether any of them returns true, which means that the host will be overloaded or underloaded at the next moment, then we exclude the host from the target list (lines [5][6][7][8][9][10][11]. After that, if the host has enough resources for the VM, we set the host as an alternative target host, and we iterate the whole host set to find the host with the smallest energy increase as the target host (lines 12-23).…”

Section: Vm Selectionmentioning

confidence: 99%

“…Some studies [5,6] have found that the energy consumption of a host is linearly related to its CPU utilization. Therefore, we propose a prediction model to forecast the future host state based on the host CPU utilization, called the Host state 3rd-order Markov chain (HS3MC) prediction model in our previous research [7] . We have improved and expanded the HS3MC model comprehensively, and compared with the old version, we have made at least five improvements in this paper.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

SLA‐Aware and Energy‐Efficient VM Consolidation in Cloud Data Centers Using Host State 3rd‐Order Markov Chain Model

Dong

Zuo

et al. 2020

Chin. j. electron.

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Vm Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

SLA‐Aware and Energy‐Efficient VM Consolidation in Cloud Data Centers Using Host State 3rd‐Order Markov Chain Model

Dong

Zuo

et al. 2020

Chin. j. electron.

Self Cite

View full text Add to dashboard Cite

Virtual Machine Consolidation Based on Load Distribution and Realtime Scheduler With Multi-objective Optimization

Brahmam

Rajasekaran

2023

Preprint

View full text Add to dashboard Cite

Optimal resource utilization and reduced energy consumption have been the primary objectives of cloud data centers as the dependency on cloud platforms is increasing day by day. Consolidating the virtual machines is a standard procedure for addressing the common issues and meeting the objectives. Though the approach seems viable for effective functionality, it is observed that consolidation performed over the permissible limit may result in violating the service level agreements in cloud service providers. When energy conservation is concentrated in the cloud platforms, multiple other factors are neglected or compromised. The supposed strategy for effective virtual machine consolidation must contemplate the parameters such as quality of service, service level agreements, reducing violations, resource distribution, load management, migration overheads, network resource management and other communication protocols. The proposed approach focusses on determining the dynamic load and resource management based on multiple objectives in order to reduce the power consumption. The dynamic load is derived based on a time-series analysis over the distributed load in different time zones. Increment in load distribution owing to virtual machine consolidation and selection is observed for improving the efficiency of consolidations. The load prediction approach along with current load detection has included multiple objectives as desired. The proposed approach, from the experimental analysis, has delivered a promising solution for load prediction, distribution and energy conservation in cloud service providers and optimized the functionalities of users. The energy efficiency was observed to be higher than existing virtual machine consolidation approaches along with effective load sequencing and maintaining the service level agreements.

show abstract

I-Neat: An intelligent framework for adaptive virtual machine consolidation

Liu

Zhao

Dong

et al. 2022

Tsinghua Sci. Technol.

Self Cite

View full text Add to dashboard Cite

With the increasing use of cloud computing, high energy consumption has become one of the major challenges in cloud data centers. Virtual Machine (VM) consolidation has been proven to be an efficient way to optimize energy consumption in data centers, and many research works have proposed to optimize VM consolidation.However, the performance of different algorithms is related with the characteristics of the workload and system status; some algorithms are suitable for Central Processing Unit (CPU)-intensive workload and some for web application workload. Therefore, an adaptive VM consolidation framework is necessary to fully explore the potential of these algorithms. Neat is an open-source dynamic VM consolidation framework, which is well integrated into OpenStack.However, it cannot conduct dynamic algorithm scheduling, and VM consolidation algorithms in Neat are few and basic, which results in low performance for energy saving and Service-Level Agreement (SLA) avoidance. In this paper, an Intelligent Neat framework (I-Neat) is proposed, which adds an intelligent scheduler using reinforcement learning and a framework manager to improve the usability of the system. The scheduler can select appropriate algorithms for the local manager from an algorithm library with many load detection algorithms. The algorithm library is designed based on a template, and in addition to the algorithms of Neat, I-Neat adds six new algorithms to the algorithm library. Furthermore, the framework manager helps users add self-defined algorithms to I-Neat without modifying the source code. Our experimental results indicate that the intelligent scheduler and these novel algorithms can effectively reduce energy consumption with SLA assurance.

show abstract

Minimizing SLA Violation and Power Consumption in Cloud Data Centers Using Host State 3-Order Markov Chain Model

Cited by 3 publications

References 15 publications

SLA‐Aware and Energy‐Efficient VM Consolidation in Cloud Data Centers Using Host State 3rd‐Order Markov Chain Model

SLA‐Aware and Energy‐Efficient VM Consolidation in Cloud Data Centers Using Host State 3rd‐Order Markov Chain Model

Virtual Machine Consolidation Based on Load Distribution and Realtime Scheduler With Multi-objective Optimization

I-Neat: An intelligent framework for adaptive virtual machine consolidation

Contact Info

Product

Resources

About