Journal
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
Volume 18, Issue 6, Pages 1737-1757Publisher
SPRINGER
DOI: 10.1007/s11280-015-0335-3
Keywords
Cloud computing; Task scheduling; Multi-objective particle swarm optimization; Multi-objective genetic algorithm; Jswarm; Cloudsim
Funding
- Australian Research Council (ARC) [DP140101366]
Ask authors/readers for more resources
Optimizing task scheduling in a distributed heterogeneous computing environment, which is a nonlinear multi-objective NP-hard problem, plays a critical role in decreasing service response time and cost, and boosting Quality of Service (QoS). This paper, considers four conflicting objectives, namely minimizing task transfer time, task execution cost, power consumption, and task queue length, to develop a comprehensive multi-objective optimization model for task scheduling. This model reduces costs from both the customer and provider perspectives by considering execution and power cost. We evaluate our model by applying two multi-objective evolutionary algorithms, namely Multi-Objective Particle Swarm Optimization (MOPSO) and Multi-Objective Genetic Algorithm (MOGA). To implement the proposed model, we extend the Cloudsim toolkit by using MOPSO and MOGA as its task scheduling algorithms which determine the optimal task arrangement among VMs. The simulation results show that the proposed multi-objective model finds optimal trade-off solutions amongst the four conflicting objectives, which significantly reduces the job response time and makespan. This model not only increases QoS but also decreases the cost to providers. From our experimentation results, we find that MOPSO is a faster and more accurate evolutionary algorithm than MOGA for solving such problems.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available