SLA-Aware Energy Efficient Resource Management for Cloud Environments

Cloud computing provides online services to customers using pay as you go model. The Cloud computing enables customers to outsource the large and complex tasks to the cloud data centers for the execution and result generations. Cloud data centers host the incoming tasks by providing resources, such...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2018-01, Vol.6, p.15004-15020
Main Authors: Mustafa, Saad, Bilal, Kashif, Malik, Saif Ur Rehman, Madani, Sajjad A.
Format: Article
Language:English
Subjects:
Cloud computing
Computer centers
Consolidation
Customers
Data centers
Energy consumption
Energy efficiency
Energy management
Optimization
Performance evaluation
Petri nets
resource allocation
Resource management
Resource utilization
Servers
SLA awareness
Task analysis
Task complexity
Workload
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cloud computing provides online services to customers using pay as you go model. The Cloud computing enables customers to outsource the large and complex tasks to the cloud data centers for the execution and result generations. Cloud data centers host the incoming tasks by providing resources, such as CPU, RAM, storage, and bandwidth. As the large data centers provide the basic resources to hosted tasks, they also consume a huge amount of energy, which leads to higher operating cost and CO 2 traces. Therefore, research community felt the need to provide energy-efficient solutions that reduce the impact of the aforementioned issues. Consequently, researchers proposed many solutions, and majority of them are based upon the concept of consolidation. Consolidation techniques place the incoming tasks on minimum possible servers, thus increasing the resource utilization and decreasing energy consumption. In this paper, we use the same workload consolidation concept and present two techniques that reduce energy consumption while ensuring the negotiated quality-of-service. Moreover, we enhanced two existing techniques by improving the energy efficiency and introducing service level agreement (SLA) awareness to minimize the overall SLA violations. Performance evaluation of the proposed techniques is done based on fluctuating workloads, and results show that our techniques outperform existing techniques in terms of energy efficiency, SLA compliance, and performance assurance at the network level. Moreover, correctness of the proposed techniques is demonstrated by modeling and verifying them with the help of high-level Petri Nets, SMT-Lib, and Z3 solver.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2018.2808320