An Enhancement of Leveled DAG Prioritized Task Scheduling Algorithm in Distributed Computing Systems

2017 ◽  
Vol 26 (1) ◽  
pp. 171-192
Author(s):  
Amal EL-NATTAT ◽  
Nirmeen A. El-Bahnasawy ◽  
Ayman EL-SAYED
2012 ◽  
Vol 457-458 ◽  
pp. 1039-1046 ◽  
Author(s):  
You Wei Lu ◽  
Zhen Zhen Xu ◽  
Feng Xia

Independent task scheduling algorithms in distributed computing systems deal with three main conflicting factors including load balance, task execution time and scheduling cost. In this paper, the problem of scheduling tasks arriving at a low rate and with long execution time in heterogeneous computing systems is studied, and a new scheduling algorithm based on prediction is proposed. This algorithm evaluates the utility of task scheduling based on statistics and prediction to solve the influence of heterogeneous computing systems. The experimental results reveal that the proposed algorithm adequately balances the conflicting factors, and thus performs better than some classical algorithms such as MCT and MET when the parameters are well selected.


Author(s):  
Hui Xie ◽  
Li Wei ◽  
Dong Liu ◽  
Luda Wang

Task scheduling problem of heterogeneous computing system (HCS), which with increasing popularity, nowadays has become a research hotspot in this domain. The task scheduling problem of HCS, which can be described essentially as assigning tasks to the proper processor for executing, has been shown to be NP-complete. However, the existing scheduling algorithm suffers from an inherent limitation of lacking global view. Here, we reported a novel task scheduling algorithm based on Multi-Logistic Regression theory (called MLRS) in heterogeneous computing environment. First, we collected the best scheduling plans as the historical training set, and then a scheduling model was established by which we could predict the following schedule action. Through the analysis of experimental results, it is interpreted that the proposed algorithm has better optimization effect and robustness.


Sign in / Sign up

Export Citation Format

Share Document