Taxonomies of workflow scheduling problem and techniques in the cloud

• We propose taxonomies of cloud workflow scheduling problem and techniques.
• Aspects and classifications unique to cloud workflow scheduling are identified.
• Several techniques are reviewed and classified based on the proposed taxonomies.
• Some issues of future concern in cloud workflow scheduling are discussed.

Scientific workflows, like other applications, benefit from the cloud computing, which offers access to virtually unlimited resources provisioned elastically on demand. In order to efficiently execute a workflow in the cloud, scheduling is required to address many new aspects introduced by cloud resource provisioning. In the last few years, many techniques have been proposed to tackle different cloud environments enabled by the flexible nature of the cloud, leading to the techniques of different designs. In this paper, taxonomies of cloud workflow scheduling problem and techniques are proposed based on analytical review. We identify and explain the aspects and classifications unique to workflow scheduling in the cloud environment in three categories, namely, scheduling process, task and resource. Lastly, review of several scheduling techniques are included and classified onto the proposed taxonomies. We hope that our taxonomies serve as a stepping stone for those entering this research area and for further development of scheduling technique.