Development of Simulation Models of Cloud Computing Infrastructures with Automatic Scaling Based on Thresholds

Bibliographic Details
Parent link:Lecture Notes in Networks and Systems.— .— Cham: Springer
Vol. 722 : Software Engineering Research in System Science.— 2023.— P. 295-304
Other Authors: Botygin I. A. Igor Aleksandrovich, Sherstneva A. I. Anna Igorevna, Sherstnev V. S. Vladislav Stanislavovich, Tartakovsky V. Valery
Summary:Title screen
In this paper, the open access toolkit CloudSim Plus was used to evaluate the impact of computing power scaling on service level and cost of using cloud resources. Focusing on automatic scaling policy based on thresholds, static power-aware distribution scenarios, horizontal scaling scenarios based on thresholds, horizontal scaling scenarios based on power-aware thresholds, vertical scaling scenarios based on thresholds, vertical scaling scenarios based on power-aware thresholds were simulated. The experiments monitored the average job waiting time, the amount of energy consumed by the data center, the number of hosts that participate in workload processing, the average CPU load, the number of virtual machines created to process the workload, the number of local processing clusters created. It is found that setting the thresholds requires a deep understanding of the workload patterns. Incorrect setting of CPU load, response time, and threshold latency leads to fluctuations in the number of virtual machines and, as a consequence, performance degradation. #CSOC1120
Текстовый файл
AM_Agreement
Published: 2023
Subjects:
Online Access:https://doi.org/10.1007/978-3-031-35311-6_30
Format: Electronic Book Chapter
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=680006