Energy-aware Cost Prediction and Pricing of Virtual Machines in Cloud Computing Environments

With the increasing cost of electricity, Cloud providers consider energy consumption as one of the major cost factors to be maintained within their infrastructure. Consequently, various proactive and reactive management mechanisms are used to efficiently manage the cloud resources and reduce the energy consumption and cost. These mechanisms support energy-awareness at the level of Physical Machines (PM) as well as Virtual Machines (VM) to make corrective decisions. This paper introduces a novel Cloud system architecture that facilitates an energy aware and efficient cloud operation methodology and presents a cost prediction framework to estimate the total cost of VMs based on their resource usage and power consumption. The evaluation on a Cloud testbed show that the proposed energy-aware cost prediction framework is capable of predicting the workload, power consumption and estimating total cost of the VMs with good prediction accuracy for various Cloud application workload patterns. Furthermore, a set of energy-based pricing schemes are defined, intending to provide the necessary incentives to create an energy-efficient and economically sustainable ecosystem. Further evaluation results show that the adoption of energy-based pricing by cloud and application providers creates additional economic value to both under different market conditions.

You can find the article here: 

Journal: Future Generation Computer Systems, Elsevier 

Karim Djemame, Mohammed Aldossary et al
Thursday, November 15, 2018