This week on Journal Club session Na Helian will talk about the paper "Dynamic Hierarchical Structure for Cloud Computing Job Scheduling Utilizing Artificial Intelligence Technologies".
Cloud computing is widely used due to its cost effectiveness and starvation free execution of processes. There has been substantial research done in job scheduling algorithm in cloud computing to improve scheduling performance, but little attention has been paid to structure design for job scheduling. This paper aims to improve job scheduling makespan (max processing time for given jobs) in a cloud environment. A dynamic hierarchical structure, which introduces sub-schedulers between scheduler and servers, is proposed to dynamically change the connection pattern between sub-schedulers and servers by using artificial intelligence search algorithms. Due to its dynamic and flexible nature, this design enables the system to adaptively accommodate the heterogeneity of jobs and resources in order to make most use of the resources available. Experimental results demonstrate that a dynamic hierarchical structure can significantly reduce the total makespan of the heterogeneous tasks allocated to heterogeneous resources, compared with a one-layer structure. This reduction is particularly pronounced when resources are scarce.
- "Dynamic Hierarchical Structure for Cloud Computing Job Scheduling Utilizing Artificial Intelligence Technologies"