MapReduce framework based gridlet allocation technique in computational grid. (June 2021)

• Record Type: Journal Article
• Authors: D., Rajeswari; M., Prakash; S., Ramamoorthy; S., Sudhakar
• Is Part Of: Computers & electrical engineering. Volume 92(2021)
• Publication Date: 2021-06
• Subjects: Pareto genetic algorithm -- MapReduce -- Multi-objective -- Task scheduling -- Non-dominated sorting -- Pareto Hill Climbing; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107131
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: A Computational Grid (CG) consists of networks that are linked to implementing grid computing. Here, a huge computational task is shared amongst the individual machines, where the calculations are executed in parallel and the final results are combined and returned to the original computer. One of the most critical issues in the CG is to measure the performance, which is handled by the task scheduling algorithm. This algorithm is ultimately responsible for assigning the task to suitable resources like memory, CPU, and so on. Evolutionary Algorithm (EA) is one of the task scheduling algorithms that produce many feasible solutions for the given problem. In this article, the MapReduce framework is implemented using the Pareto Multi-Objective Evolutionary Algorithm (PMOEA) in CG. The Pareto Multi-Objective Evolutionary Algorithm (PMOEA) incorporates other two algorithms such as Pareto Multi-Objective Genetic Algorithm (PMOGA) and the Pareto Multi-Objective Particle Swarm Optimization (PMOPSO) to resolve the research problem effectively. The performance of the PMOEA can be further measured by the performance metrics like Ratio of Non-dominated Individuals (RNI), Maximum Spread (Smax ), and Coverage of Two sets (C). The evaluation result indicates that the Non-dominated Sorting Genetic Algorithm (NSGA2-PHC) outperforms all other techniques.