Skip to Main content Skip to Navigation

Scheduling independent tasks under budget and time constraints

yiqin Gao 1, 2 
Abstract : In this thesis, we design scheduling heuristics for independent tasks under budget and time constraints, in order to satisfy the requirement on performance or on energy consumption. The first three chapters of this thesis have performance as objective, while the fourth chapter focuses on energy-efficiency. The first three chapters have a common framework: We have a bag of tasks whose execution times follow some probability distributions. We can decide at any instant to interrupt the execution of a long running task and to launch a new one instead. The main questions are how many (or which) processors to enroll, and whether and when to interrupt tasks if they have been executing for a long time. In previous work, the problem has been dealt with on a homogeneous platform and with the same release time and deadline for all tasks. Our work extends the state-of-the-art in three directions: In the first work, we consider an heterogeneous platform. In the second work, we assume that the distribution of task execution times is unknown. In the third work, tasks are released periodically and have their own deadline. The fourth work considers a real-time framework. We have periodic tasks and an heterogeneous platform. We consider transient fault. Tasks are replicated to guarantee a pre-defined reliability threshold. We aim at find a heuristic which minimizes the expected energy consumption, while matching the deadline and reliability constraints of all tasks. This alls for a difficult trade-off between reliability and energy consumption.
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Wednesday, November 3, 2021 - 11:12:16 AM
Last modification on : Monday, May 16, 2022 - 4:46:02 PM


Version validated by the jury (STAR)


  • HAL Id : tel-03412631, version 2


yiqin Gao. Scheduling independent tasks under budget and time constraints. Distributed, Parallel, and Cluster Computing [cs.DC]. Université de Lyon, 2021. English. ⟨NNT : 2021LYSEN051⟩. ⟨tel-03412631v2⟩



Record views


Files downloads