Energy Aware Scheduling for Green Cloud Computing
Advisor Information
Hesham Ali
Location
Dr. C.C. and Mabel L. Criss Library
Presentation Type
Poster
Start Date
2-3-2018 12:30 PM
End Date
2-3-2018 1:45 PM
Abstract
Energy Aware Scheduling for Green Cloud Computing
Graduate Student: Anusha Kothapally
Supervisor: Hesham Ali
Abstract — Cloud computing is an emerging technology that many IT companies are utilizing since it offers potential benefits to both cloud consumer and cloud owner. It is a new class of network-based computing that takes place over the Internet. While there are many efforts to increase the performance of cloud services, limited reported research has been developed with a focus on energy dissipation. The contemporary single data center would own thousands of servers, which would cause huge power devour. It is reported in one of the surveys that data centers are consuming around 3.5% of the total world’s energy. Energy consumption has become a significant concern for cloud service providers in terms of financial and environmental factors. In this study, we develop a new mechanism that employs the concept of task consolidation to reduce energy consumption in cloud environments. We use multi-layer graphs to model the key factors that need to be considered for task consolidation such as processor speed, process availability, memory requirements, and communication cost among relate tasks. The proposed model can be extended to include other parameters as needed for each computational environment which allows cloud providers to customize their task schedulers according to their own workload profiles. Early results show that the proposed approach leads to significant energy saving for various scenarios of cloud services.
Energy Aware Scheduling for Green Cloud Computing
Dr. C.C. and Mabel L. Criss Library
Energy Aware Scheduling for Green Cloud Computing
Graduate Student: Anusha Kothapally
Supervisor: Hesham Ali
Abstract — Cloud computing is an emerging technology that many IT companies are utilizing since it offers potential benefits to both cloud consumer and cloud owner. It is a new class of network-based computing that takes place over the Internet. While there are many efforts to increase the performance of cloud services, limited reported research has been developed with a focus on energy dissipation. The contemporary single data center would own thousands of servers, which would cause huge power devour. It is reported in one of the surveys that data centers are consuming around 3.5% of the total world’s energy. Energy consumption has become a significant concern for cloud service providers in terms of financial and environmental factors. In this study, we develop a new mechanism that employs the concept of task consolidation to reduce energy consumption in cloud environments. We use multi-layer graphs to model the key factors that need to be considered for task consolidation such as processor speed, process availability, memory requirements, and communication cost among relate tasks. The proposed model can be extended to include other parameters as needed for each computational environment which allows cloud providers to customize their task schedulers according to their own workload profiles. Early results show that the proposed approach leads to significant energy saving for various scenarios of cloud services.