In this paper, a partial duplication based scheduling algorithm is designed that focuses on reducing the schedule length and processor count of the schedule by reducing the idle time slots. The proposed algorithm clusters the tasks so that it reduces the total job completion time i.e reducing the schedule length of the tasks. Then the compaction process is used to yield reduced number of processors. Finally bidding process is carried out to select the optimal resources for the tasks. The bidding process is one way. i.e only the resources bid. After selecting the resources task files are dispatched to the appropriate resources where the task execution is done.
Published in:
Advanced Computing (ICoAC), 2010 Second International Conference on
Date of Conference: 14-16 Dec. 2010