Power-aware admission control and virtual machine allocation for cloud applications

Different service providers in the cloud computing environment assume different responsibilities. Software as a Service (SaaS) providers have to respond to users' requests within an acceptable deadline determined in their Service Level Agreement (SLA) contracts, while Infrastructure as a Service (IaaS) providers mostly care about the infrastructural resources. Power and cooling management and pricing of available resources are concerns of IaaS providers. The goal of an SaaS provider is to maximize the revenue from SLAs and minimize the cost of using IaaS resources. An IaaS provider wants to maximize the prices of its own resources that it charges its clients, and at the same time minimize the total power consumption of infrastructural resources. Each provider's decision may affect the other providers' strategies. In this paper, we propose a power-aware algorithm for both IaaS and SaaS providers to jointly and optimally control the admission rate and allocate the resources. We simulate different scenarios to substantiate the viability of our proposed scheme.

[1]  Rajkumar Buyya,et al.  Power‐aware provisioning of virtual machines for real‐time Cloud services , 2011, Concurr. Comput. Pract. Exp..

[2]  Yan Zhang,et al.  Heterogeneity aware dominant resource assistant heuristics for virtual machine consolidation , 2013, 2013 IEEE Global Communications Conference (GLOBECOM).

[3]  Barbara Panicucci,et al.  Energy-Aware Autonomic Resource Allocation in Multitier Virtualized Environments , 2012, IEEE Transactions on Services Computing.

[4]  Feng Zhao,et al.  Virtual machine power metering and provisioning , 2010, SoCC '10.

[5]  Rajarshi Das,et al.  Coordinating Multiple Autonomic Managers to Achieve Specified Power-Performance Tradeoffs , 2007, Fourth International Conference on Autonomic Computing (ICAC'07).

[6]  Xiaoyun Zhu,et al.  1000 islands: an integrated approach to resource management for virtualized data centers , 2009, Cluster Computing.

[7]  Yan Zhang,et al.  On Architecture Design, Congestion Notification, TCP Incast and Power Consumption in Data Centers , 2013, IEEE Communications Surveys & Tutorials.

[8]  Federico Etro,et al.  Stackelberg Competition with Endogenous Entry , 2008 .

[9]  G. Magklis,et al.  Dynamic Frequency and Voltage Scaling for a Multiple-Clock-Domain Microprocessor , 2003, IEEE Micro.

[10]  Danilo Ardagna,et al.  SLA based profit optimization in autonomic computing systems , 2004, ICSOC '04.

[11]  Yan Zhang,et al.  HERO: Hierarchical Energy Optimization for Data Center Networks , 2015, IEEE Systems Journal.

[12]  Ítalo S. Cunha,et al.  Joint admission control and resource allocation in virtualized servers , 2010, J. Parallel Distributed Comput..

[13]  Nagarajan Kandasamy,et al.  Power and performance management of virtualized computing environments via lookahead control , 2008, 2008 International Conference on Autonomic Computing.

[14]  Barbara Panicucci,et al.  A game theoretic formulation of the service provisioning problem in cloud systems , 2011, WWW.

[15]  Yan Zhang,et al.  Fair Quantized Congestion Notification in Data Center Networks , 2013, IEEE Transactions on Communications.

[16]  Nirwan Ansari,et al.  A feasible solution to provide cloud computing over optical networks , 2013, IEEE Network.

[17]  Yan Zhang,et al.  HERO: Hierarchical energy optimization for data center networks , 2012, 2012 IEEE International Conference on Communications (ICC).