Energy Consumption Optimization of
Container-Oriented Cloud Computing Center
Zhenjiang Li
()
and Zhenxiang He
College of Cyberspace Security, Gansu Political Science And Law Institute, Lanzhou, China
()
Corresponding author: lzj6843@gsli.edu.com
Abstract. [Objective] A container-based cloud computing center suffers from
higher energy consumption, so an improved virtual migration strategy has been
proposed to optimize energy consumption. [Methods] Firstly, we have studied
the dependency among physical machines, virtual machines and containers of a
cloud computing center in a container environment; secondly, analyzed the key
factors affecting the energy consumption of the data center under such a
dependency and established a mathematical model; finally, proposed an optimal
utilization priority algorithm according to the non-linear relationship between
utilization and energy consumption of different physical machines. [Result]
The simulation experiments made on the ContainerCloudSim platform show
that the method proposed in this paper can be used to effectively reduce the
energy consumption of the data center in the container environment compared
with traditional strategies such as random scheduling and maximum utilization.
[Conclusion] In this paper, starting from the differences between different
physical machines in the actual environment, the classical virtual migration
strategy has been improved in order to reduce the energy consumption of the
data center and moreover, the algorithm is simple, easy to implement and
worthy of popularization.
Keywords: Container, Data center, Energy consumption, Virtual migration
1 Introduction
In cloud computing centers, the energy consumption optimization has always been a
focus of attention. In recent years, in order to solve the problem that applications in
the PaaS (Platform as a Service) environment are restricted by platform
specifications, the concept of CaaS (Container as a Service) has been accepted by
more and more people. As the basis of implementing CaaS cloud models, this
technology has provided an isolated virtual environment without the need for
intermediate monitoring media, for example, virtual machine managers [1]. The cloud
computing service providers and consumers have been gradually changing the means
for managing and leasing the data center resource with the development of such new
technologies as containers, but improvement on resource utilization and reduction of
energy consumption in data centers are still two important issues that container cloud
service providers are most concerned about [2].