Simulation model of load balancing in distributed computing systems

International Conference on Mechanical Engineering, Automation and Control Systems 2016

机械制造;无线电电子学;计算机科学

Botygin, I.A.^1 ; Popov, V.N.^1 ; Frolov, S.G.^1

Tomsk Polytechnic University, Lenina ave., 30, Tomsk

634050, Russia^1

关键词: Analytical problems;    Complex computer systems;    Distributed computing systems;    Engineering companies;    Heterogeneous computer systems;    High performance computing;    High-speed data transfer;    Industrial enterprise;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/177/1/012017/pdf
DOI  :  10.1088/1757-899X/177/1/012017

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

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.