Hierarchical SLA-Driven Resource Management for Peak Power-Aware and Energy-Efficient Operation of a Cloud Datacenter

• Published in: IEEE transactions on cloud computing Vol. 4; no. 2; pp. 222 - 236
• Main Authors: Goudarzi, Hadi, Pedram, Massoud
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE Computer Society 01.04.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cloud computing; Clouds; Containers; Cooling; Cost engineering; Data centers; Mathematical models; Power demand; Resource management; Resources management; Servers; Service level agreements; resource management; Data center; service-level agreement; energy efficiency
• ISSN: 2168-7161; 2168-7161; 2372-0018
• DOI: 10.1109/TCC.2015.2474369

In this work, a hierarchical, service level agreement (SLA) based resource management solution for cloud datacenters is presented, which considers the energy non-proportionality of existing servers, peak power constraints, and cooling power consumption. The goal of this resource manager is to minimize the operational cost of the data center. The hierarchical structure of the proposed solution makes the resource management scalable. The proposed resource management solution simultaneously considers server and cooling power consumption, guarantee-based SLA and complexity of the decision making in the resource management of the cloud computing systems. Considering SLA and state of the datacenter in determining the amount of resource that needs to be allocated to applications results in significant reduction of the operational cost in datacenter. The effectiveness of the proposed management scheme compared to previous work is demonstrated using a comprehensive cloud computing simulation tool. The proposed resource management algorithms reduce the operational cost of a datacenter by about 40 percent while satisfying SLA constraints and decrease the run-time of the management algorithms by up to 86 percent with respect to the state of the art centralized management solution.