UDC 004.7
ALGORITHM FOR CONFIGURING CLOUD COMPUTING SCHEDULE PARAMETERS BASED ON PARTICLE SWARM OPTIMIZATION
A. A. Spitsyn, Associate Professor, Military Training and Research Center of the Air Force «Professor N. E. Zhukovsky and Yu. A. Gagarin Air Force Academy», Voronezh, Russian Federation;
orcid.org/0000-0002-8650-6736, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
Infrastructure as a service (IaaS) clouds offer huge opportunities for solving large-scale tasks. Running workflows in such environments can be time-consuming if they are not properly scheduled. Although workflow planning in industry is widely studied, most approaches are focused on two user requirements for the quality of service, namely, execution time and cost. It is also necessary to take into account other important features of cloud computing, heterogeneous cloud data centers. The aim is to optimize data transfer time while minimizing execution time and improving reliability. Based on the simulation, the results show significant improvement in terms of execution time, transmitted data, and reliability compared to the proven HEFT (Heterogeneous Earliest Execution Time) method for reference workflows.
Key words: IaaS cloud, workflow, scheduling, quality of service, data transfer time, reliability, heterogeneous centers, execution time.