Dynamic Task Scheduling with Load Balancing using Genetic Algorithm
Chouhan Kumar Rath, Prasanti Biswal, Shashank Sekhar Suar · 2018
Parallel computing is better suitable for modeling, simulating complex problems. Simultaneous use of multiple tasks to compute a particular problem defines Parallel Computing. There are various techniques available to build a powerful parallel computing processor. An efficient task scheduling problem improves the performance of the multiprocessing system. So, distribution of tasks in a multiprocessing environment is the most critical issue today. This paper presents an approach to dynamic task scheduling with load balancing. Load distribution is a major issue for parallel processing now a days. In order to minimize the average make-span and solve the load balancing problem, the Genetic algorithm is used. New kind of fitness function is evaluated using standard deviation. The system is modeled by taking a standard task graph with communication cost and computation cost. Task graph consists of nodes (tasks) allocated to the processors with dependency. The experimental results depict the efficiency of the proposed method.