RESOURCE ALLOCATION IN CLOUD ENVIRONMENTS WHILE PERFORMING FLOW OF RANDOMLY INCOMING TASKS

RESOURCE ALLOCATION IN CLOUD ENVIRONMENTS WHILE PERFORMING FLOW OF RANDOMLY INCOMING TASKS

A.I. Kalyaev
PhD in Technical Sciences, Southern Federal University, Senior Programmer, 2, Chekhova ul., GSP-284, Taganrog, Rostov Region, 347928, Russia, tel.: +7(8634)360-757, This email address is being protected from spambots. You need JavaScript enabled to view it.

I.A. Kalyaev
Doctor of Technical Science, Southern Federal University, Professor, Corresponding Member of the Russian Academy of Sciences, Discipline Head, 2, Chekhova ul., GSP-284, Taganrog, Rostov Region, 347928, Russia, tel.: +7(8634)360-757, This email address is being protected from spambots. You need JavaScript enabled to view it.

Ya.S. Korovin
PhD in Technical Sciences, Southern Federal University, Director, 2, Chekhova ul., GSP-284, Taganrog, Rostov Region, 347928, Russia, tel.: +7(8634)360-757, This email address is being protected from spambots. You need JavaScript enabled to view it.


Abstract
The work is devoted to solving the fundamental problem of the adaptive allocation of resources in a cloud computing environment (CCE), which consists of heterogeneous computing resources for solving incoming flow of large-scale scientific tasks coming at random moments and consisting of interconnected subtasks. Problem of allocation is formulated for a variety of original task types. The proposed principles and methods of multi-agent allocating of heterogeneous resources for solving incoming flow of large-scale tasks provide adaptive distribution of all available at the current time computing resources taking into account their actual performance on various subtasks. Authors describe the algorithms of software agent for a variety of options of CCE. In addition, there is research on the effectiveness of the developed algorithms using multi-agent programming model of heterogeneous CCE. This research is supported by the Russian Foundation for Basic Research (grant 15-29-07928).

Key words
Cloud computing environment, decentralized controller, multi-agent dispatching, flow of large-scale tasks, adaptive resource allocation.

Year 2016 Issue number 1 Consecutive issue number 10 Pages 18-26
UDC identifier: 004.75

 

Editorial office address: 21, Tikhoretsky pr., Saint-Petersburg, Russia, 194064, tel.: +7(812) 552-13-25 e-mail: zheleznyakov@rtc.ru