Decreasing Power Consuming in Cloud Computing Based On Enhanced Bin Packing Algorithm
No Thumbnail Available
Date
2021-04-05
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Cloud computing is an emerging computing technology that uses
the internet and central remote services to maintain data and application
which are provisioned on-demand and on pay-as-you-go basis. Wide
adaptation of Cloud concepts has increased number of data centers
worldwide resulting into significant amounts of power consumption by
data centers which affects environment and economical aspects.
Through virtualization, multiple virtual machines (VM) can be
deployed onto one physical machine (PM). These VMs hold and
execute the Cloud workload.
An existing problem is how to allocate Virtual Machines (VMs) to
Physical Machines (PMs) or hosts. This process is called VM
placement.
The decision on which physical machines (PM) to place each virtual
machine (VM) is very important for the efficient cloud operation. On
one hand, it is important that VMs obtain adequate resources (e.g.,
CPU, memory, and network) from the hosting PM so that its
performance is not impaired. On the other hand, the cloud operator
would like to consolidate VMs on as few PMs as possible to maximize
resource utilization and lower energy consumption. Efficient VM
placement is like the vector bin packing problem, which is known to be
NP-hard.
Effective physical machine allocation of VMs will lead to better
use of resources and energy savings. In this study, the main goal is to
provide an improved Policy on energy efficient VM placement to
minimize energy consumption in the cloud environment. Placing the
VMs in the addressed Bin-Packing mechanism and retaining the
Service Level Agreement (SLA) between the provider and the cloud
customer .Significant reduction in power consumption could even be
made if reduction are implemented at software level. Energy-aware
scheduling processes produces excellent performance by
implementing Bin-packing energy efficiency mechanisms.
The proposed algorithm has been enhanced for the two First Fit
Decreasing (FFD( and Best Fit Decreasing) BFD( algorithms, which
are considered the best among Bin packing algorithms. The enhanced
algorithm adopts server power as the basis for arranging servers in
the database, unlike the BFD, FFD algorithms that arrange servers
according to their CPU. The purpose is to minimize the number of
active servers without affecting the service level agreement
The proposed algorithm has been practically tried using
MATLAB 2020 programing language for samples of heterogeneous
servers and virtual machines (each server and virtual machine has its
own specifications for storage, processing unit, bandwidth, etc and
different from the others ), whose specifications were chosen
randomly. The proposed algorithm could decrease significantly
energy consumption and resources utilization in comparison with
the existing algorithms (FFD, BFD).