SIMPLE HEURISTIC ALGORITHM FOR DYNAMIC VM REALLOCATION IN IAAS CLOUDS
Journal Title: Современные информационные технологии и ИТ-образование - Year 2018, Vol 14, Issue 1
Abstract
The rapid development of cloud technologies and its high prevalence in both commercial and academic areas have stimulated active research in the domain of optimal cloud resource management. One of the most active research directions is dynamic virtual machine (VM) placement optimization in clouds build on Infrastructure-as-a-Service model. This kind of research may pursue different goals with energy-aware optimization being the most common goal as it aims at a urgent problem of green cloud computing - reducing energy consumption by data centers. In this paper we present a new heuristic algorithm of dynamic reallocation of VMs based on an approach presented in one of our previous works. In the algorithm we apply a 2-rank strategy to classify VMs and servers corresponding to the highly and lowly active VMs and solve four tasks: VM classification, host classification, forming a VM migration map and VMs migration. Dividing all of the VMs and servers into two classes we attempt to implement the possibility of risk reduction in case of hardware overloads under overcommitment conditions and to reduce the influence of the occurring overloads on the performance of the cloud VMs. Presented algorithm was developed based on the workload profile of the JINR cloud (a scientific private cloud) with the goal of maximizing its usage, but it can also be applied in both public and private commercial clouds to organize the simultaneous use of different SLA and QoS levels in the same cloud environment by giving each VM rank its own level of overcommitment.
Authors and Affiliations
Nikita Balashov, Alexandr Baranov, Ivan Kadochnikov, Vladimir Korenkov, Nikolay Kutovskiy, Igor Pelevanyuk
Keywords
Related Articles
- EP ID EP507303
- DOI 10.25559/SITITO.14.201801.101-110
- Views 115
- Downloads 0
EDUCATIONAL PROGRAM ON HPC TECHNOLOGIES BASED ON THE HETEROGENEOUS CLUSTER HYBRILIT (LIT JINR)
The article highlights the issues of training personnel for work with high-performance computing systems (HPC), as well as of support of the software and information environment which is necessary for the efficient use o...
FEATURES OF PROGRAMMING IN DSSP FOR THE TERNARY MACHINE
In article characteristic properties of the Dialogue System for Structured Programming (DSSP) in which it significantly differs from the traditional languages (Pascal, C) which are usually used for development of a basic...
GAMIFICATION TECHNOLOGIES FOR THE EARLY EDUCATION OF OBJECT-ORIENTED PROGRAMMING
The article describes the issues of teaching programming in the school at computer science (Computing) lessons. The authors have analyzed how the school computer science (computing) course has changed in recent years. In...
TABULAR ARTIFICIAL NEURAL NETWORK IMPLEMENTATION OF RADIAL BASIS FUNCTIONS FOR THE SAMPLES CLASSIFICATION
The development and study of a new constructive algorithm for constructing models for sample classification using an artificial neural network with radial basis functions in a Microsoft Excel spreadsheet environment with...
APPLIED PROBLEMS OF OPTIMIZING THE PROTECTION OF INTELLECTUAL PROPERTY IN THE EEU AND THE RUSSIAN FEDERATION
In the present article, the authors have carried out a comparative analysis of the lists of protected results of intellectual activity in the Russian Federation, in the countries of the EAEU, as well as in bilateral agre...