A Monarch Butterfly Optimization Approach to Dynamic Task Scheduling
- 17 Downloads
Parallel processing has been employed many years in high-performance computing. Parallel processing is mostly used because it provides concurrency, maximizes load balancing, and minimizes system idle time and execution time which depend on various computer architecture. Task scheduling is a parallel processing technique which allocates the tasks to various processors. Mapping of heterogeneous tasks to a heterogeneous processor or core dynamically in a distributed environment is one of the active area of research in the field of parallel computing system. Here in this paper, monarch butterfly optimization (MBO) , a nature-inspired metaheuristic algorithm is implemented for a task scheduling problem. A monarch, a North American butterfly is best known for its migratory behavior in the summer season. There are mainly two processes to get the best solution. First, using a migration operator, a new generation is created. Second, they update their position by using a butterfly adjusting operator. The fitness value is evaluated and updated the population with a higher fitness value to satisfy the objective of the problem. Minimizing the cost and time of the scheduling strategy is the main objective of the proposed work.
KeywordsTask scheduling Parallel processing Monarch Butterfly Optimization (MBO) Genetic Algorithm (GA) Evolutionary computation
- 1.Wang, G.G., Deb, S., Cui, Z.: Monarch butterfly optimization. In: Neural Computing and Applications (2015)Google Scholar
- 3.Page, A.J., Naughton, T.J.: Dynamic task scheduling using genetic algorithms for heterogeneous distributed computing. In: 19th IEEE International Parallel and Distributed Processing Symposium, pp. 189a–189aGoogle Scholar
- 7.Beyer, H., Schwefel, H.: Nat. Comput. Kluwer Academic Publishers, Dordrecht (2002)Google Scholar