Combined load balancing algorithm in distributed computing environment
Load balancing algorithms and task scheduling are one of the most important tasks in parallel application design and implementation. Proper task assignment to processor cores can minimize execution time and increase the performance of a parallel application. In this paper, we analyzed the domain decomposition and master-slave load balancing algorithms and proposed a combined version. The combined algorithm is based on a combination of standard, existing and well known, domain decomposition and master-slave algorithms. They minimize communication between independent tasks and improve performance of a parallel application. Simulation results confirmed that proposed algorithm decrease the execution time and reduce the load imbalance.