Open AccessCluster Based Real Time Scheduling for Distributed System
Author(s) -
Girish Talmale,
Urmila Shrawankar
Publication year - 2021
Publication title -
advances in distributed computing and artificial intelligence journal
Language(s) - English
Resource type - Journals
ISSN - 2255-2863
DOI - 10.14201/adcaij2021102137156
Subject(s) - fixed priority pre emptive scheduling , computer science , fair share scheduling , rate monotonic scheduling , two level scheduling , dynamic priority scheduling , round robin scheduling , distributed computing , earliest deadline first scheduling , preemption , scheduling (production processes) , deadline monotonic scheduling , parallel computing , lottery scheduling , real time computing , computer network , mathematical optimization , operating system , mathematics , quality of service
Real time tasks scheduling on a distributed system is a complex problem. The existing real time tasks scheduling techniques are primarily based on partitioned and global scheduling. In partitioned based scheduling the tasks are assigned on a dedicated processor. The advantages of partitioned based approach is existing uni-processor scheduling techniques can be used; no migration overheads but task assignment is NP hard problem and optimal utilization of processing nodes is not possible. In global scheduling all tasks are maintained in a single tasks queue and allocated to multiple processing nodes. The advantage of global scheduling is optimal utilization of processing nodes but suffer from high migration and preemption overheads. This paper proposed cluster based real time tasks scheduling on a distributed system which is a hybrid scheduling approach where processing nodes group into cluster and scheduling using global scheduling. The simulation result shows that the proposed scheduling increases the tasks acceptance ratio, resource utilization as compared to partitioned and global scheduling and reduces migration as well as preemption overheads.