Profit-Oriented Scheduling Optimization for Workflow in Clouds

Clouds have become a new paradigm by enabling on-demand provisioning of applications, platforms or computing resources for clients. Workflow scheduling is one of the most challenging problems in Clouds. Getting more profits is one of the most important objectives in workflow scheduling. Conventional workflow scheduling strategies developed on the kind of systems mainly focus on the workflow. In this paper, we take the communication into account and develop a novel scheduling algorithm based on the topology characters of degree and path length named Music Chair Algorithm (MCA). The algorithm gives a good performance on searching for the optimum schedule in getting the most profit. Also, we find that there exists a certain resource amount, which gets the most profit to help us get more enthusiasm for further developing the Clouds. Experimental results demonstrate that the analysis of the strategies for most profits are reasonable, and the MCA is available to efficiently get the optimum schedule with low computing complexity.