Differential Evolution Algorithm for Workflow Scheduling (DEWS) in Public Cloud

Infrastructure as a Service (IaaS) is one of the common Cloud service models, which is most used by the scientific applications. As the users are charged only for the usage of resources based on the Service Level Agreements (SLA), the users are attracted towards the IaaS. Workflow scheduling is a complex issue in IaaS because multiple scheduling parameters are to be considered to satisfy the Quality of Service parameters. Workflow applications comprises of various sub-tasks, which are to be executed in a particular method. These tasks have parent child relationship. The parent task needs to be executed before its child task. Workflow scheduling algorithms are supposed to preserve dependency constraints implied by their nature and structure. Resources are allocated to various sub-tasks of the original task by keeping into account these constraints. The role of workflow scheduling algorithm is to find the schedule which satisfies the SLA document which is written between a cloud user and a cloud service provider. Many heuristic algorithms were proposed in the literature, targeted only a single parameter for scheduling. But the user may require multiple objectives to be satisfied such as cost optimization, makespan optimization, reliability, deadline constrained, budget constrained etc. Hence, it is the responsibility of the Scheduling algorithm to find the optimal schedule that satisfies the SLA. The proposed algorithm uses Differential Evolution technique to optimize the scheduling parameters such as execution time of the application and Cost of executing the application in the Cloud. The proposed algorithm is compared with the Genetic Algorithm and the results outperform the Genetic Algorithm.