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 language | English |
|---|---|
| Article number | 012017 |
| Journal | IOP Conference Series: Materials Science and Engineering |
| Volume | 177 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 1 Mar 2017 |
Fingerprint
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 journal › Article
}
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 -