Simulation model of load balancing in distributed computing systems

I. A. Botygin, V. N. Popov, S. G. Frolov

Research output: Contribution to journalArticle

Abstract

The availability of high-performance computing, high speed data transfer over the network and widespread of software for the design and pre-production in mechanical engineering have led to the fact that at the present time the large industrial enterprises and small engineering companies implement complex computer systems for efficient solutions of production and management tasks. Such computer systems are generally built on the basis of distributed heterogeneous computer systems. The analytical problems solved by such systems are the key models of research, but the system-wide problems of efficient distribution (balancing) of the computational load and accommodation input, intermediate and output databases are no less important. The main tasks of this balancing system are load and condition monitoring of compute nodes, and the selection of a node for transition of the user's request in accordance with a predetermined algorithm. The load balancing is one of the most used methods of increasing productivity of distributed computing systems through the optimal allocation of tasks between the computer system nodes. Therefore, the development of methods and algorithms for computing optimal scheduling in a distributed system, dynamically changing its infrastructure, is an important task.

Original languageEnglish
Article number012017
JournalIOP Conference Series: Materials Science and Engineering
Volume177
Issue number1
DOIs
Publication statusPublished - 1 Mar 2017

Fingerprint

Distributed computer systems
Resource allocation
Computer systems
Condition monitoring
Mechanical engineering
Data transfer
Industry
Productivity
Scheduling
Availability

ASJC Scopus subject areas

  • Materials Science(all)
  • Engineering(all)

Cite this

Simulation model of load balancing in distributed computing systems. / Botygin, I. A.; Popov, V. N.; Frolov, S. G.

In: IOP Conference Series: Materials Science and Engineering, Vol. 177, No. 1, 012017, 01.03.2017.

Research output: Contribution to journalArticle

@article{9be8db4ad55e473d8ec6732deeb74309,
title = "Simulation model of load balancing in distributed computing systems",
abstract = "The availability of high-performance computing, high speed data transfer over the network and widespread of software for the design and pre-production in mechanical engineering have led to the fact that at the present time the large industrial enterprises and small engineering companies implement complex computer systems for efficient solutions of production and management tasks. Such computer systems are generally built on the basis of distributed heterogeneous computer systems. The analytical problems solved by such systems are the key models of research, but the system-wide problems of efficient distribution (balancing) of the computational load and accommodation input, intermediate and output databases are no less important. The main tasks of this balancing system are load and condition monitoring of compute nodes, and the selection of a node for transition of the user's request in accordance with a predetermined algorithm. The load balancing is one of the most used methods of increasing productivity of distributed computing systems through the optimal allocation of tasks between the computer system nodes. Therefore, the development of methods and algorithms for computing optimal scheduling in a distributed system, dynamically changing its infrastructure, is an important task.",
author = "Botygin, {I. A.} and Popov, {V. N.} and Frolov, {S. G.}",
year = "2017",
month = "3",
day = "1",
doi = "10.1088/1757-899X/177/1/012017",
language = "English",
volume = "177",
journal = "IOP Conference Series: Materials Science and Engineering",
issn = "1757-8981",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - Simulation model of load balancing in distributed computing systems

AU - Botygin, I. A.

AU - Popov, V. N.

AU - Frolov, S. G.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - The availability of high-performance computing, high speed data transfer over the network and widespread of software for the design and pre-production in mechanical engineering have led to the fact that at the present time the large industrial enterprises and small engineering companies implement complex computer systems for efficient solutions of production and management tasks. Such computer systems are generally built on the basis of distributed heterogeneous computer systems. The analytical problems solved by such systems are the key models of research, but the system-wide problems of efficient distribution (balancing) of the computational load and accommodation input, intermediate and output databases are no less important. The main tasks of this balancing system are load and condition monitoring of compute nodes, and the selection of a node for transition of the user's request in accordance with a predetermined algorithm. The load balancing is one of the most used methods of increasing productivity of distributed computing systems through the optimal allocation of tasks between the computer system nodes. Therefore, the development of methods and algorithms for computing optimal scheduling in a distributed system, dynamically changing its infrastructure, is an important task.

AB - The availability of high-performance computing, high speed data transfer over the network and widespread of software for the design and pre-production in mechanical engineering have led to the fact that at the present time the large industrial enterprises and small engineering companies implement complex computer systems for efficient solutions of production and management tasks. Such computer systems are generally built on the basis of distributed heterogeneous computer systems. The analytical problems solved by such systems are the key models of research, but the system-wide problems of efficient distribution (balancing) of the computational load and accommodation input, intermediate and output databases are no less important. The main tasks of this balancing system are load and condition monitoring of compute nodes, and the selection of a node for transition of the user's request in accordance with a predetermined algorithm. The load balancing is one of the most used methods of increasing productivity of distributed computing systems through the optimal allocation of tasks between the computer system nodes. Therefore, the development of methods and algorithms for computing optimal scheduling in a distributed system, dynamically changing its infrastructure, is an important task.

UR - http://www.scopus.com/inward/record.url?scp=85016175780&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016175780&partnerID=8YFLogxK

U2 - 10.1088/1757-899X/177/1/012017

DO - 10.1088/1757-899X/177/1/012017

M3 - Article

AN - SCOPUS:85016175780

VL - 177

JO - IOP Conference Series: Materials Science and Engineering

JF - IOP Conference Series: Materials Science and Engineering

SN - 1757-8981

IS - 1

M1 - 012017

ER -