Authors:
Soha Rawas
;
Ahmed Zekri
and
Ali El Zaart
Affiliation:
Beirut Arab University, Lebanon
Keyword(s):
Carbon Footprint, Energy-efficient, Latency, Geo-distributed Data Centres.
Abstract:
The proliferation of cloud computing due to its attracting on-demand services leads to the establishment of
geo-distributed data centers (DCs) with thousands of computing and storage nodes. Consequently, many
challenges exist for cloud providers to run such an environment. One important challenge is to minimize
cloud users’ network latency while accessing services from the DCs. The other is to decrease the DCs’
energy consumption that contributes to high operational cost rates, low profits for cloud providers, and high
carbon non-environment friendly emissions. In this paper, we studied the problem of virtual machine
placement that results in less energy consumption, less CO2 emission, and less access latency towards largescale
cloud providers operational cost minimization. The problem was formulated as multi-objective
function and an intelligent machine-learning model constructed to improve the performance of the proposed
model. To evaluate the proposed model, extensive sim
ulation is conducted using the CloudSim simulator.
The simulation results reveal the effectiveness of PCVM model compared to other competing virtual
machine placement methods in terms of network latency, energy consumption, CO2 emission and
operational cost minimization.
(More)