An Optimized Weighted Average Makespan in Fault-Tolerant Heterogeneous MPSoCs

Youness, Hassan; Omar, Aly; Moness, Mohammed

doi:10.1109/tpds.2021.3053150

Cited by 8 publications

(2 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Ref. [37], the concept of the weighted average makespan was introduced for improving the reliability of executing workflows in a multiprocessor system. Two scheduling algorithms were presented for fault-tolerant scheduling based on task replication and simulated annealing.…”

Section: Robust Workflow Schedulingmentioning

confidence: 99%

Monte Carlo Simulation-Based Robust Workflow Scheduling for Spot Instances in Cloud Environments

Wu,

Fang,

Zeng

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

When deploying workflows in cloud environments, the use of Spot Instances (SIs) is intriguing as they are much cheaper than on-demand ones. However, SIs are volatile and may be revoked at any time, which results in a more challenging scheduling problem involving execution interruption and hence hinders the successful handling of conventional cloud workflow scheduling techniques. Although some scheduling methods for SIs have been proposed, most of them are no more applicable to the latest SIs, as they have evolved by eliminating bidding and simplifying the pricing model. This study focuses on how to minimize the execution cost with a deadline constraint when deploying a workflow on volatile SIs in cloud environments. Based on Monte Carlo simulation and list scheduling, a stochastic scheduling method called MCLS is devised to optimize a utility function introduced for this problem. With the Monte Carlo simulation framework, MCLS employs sampled task execution time to build solutions via deadline distribution and list scheduling, and then returns the most robust solution from all the candidates with a specific evaluation mechanism and selection criteria. Experimental results show that the performance of MCLS is more competitive compared with traditional algorithms.

show abstract

Section: Robust Workflow Schedulingmentioning

confidence: 99%

Monte Carlo Simulation-Based Robust Workflow Scheduling for Spot Instances in Cloud Environments

Wu,

Fang,

Zeng

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…(2) Copy-based fault tolerance technology It is also a common fault tolerance technology to improve the reliability of DSs by creating replicas. A system with replicas can continue to provide services through replicas when the primary node fails [9]. However, such systems generally also need to design a mechanism to ensure the consistency between the replica node and the master node.…”

Section: Fault-tolerant Technologymentioning

confidence: 99%

Performance Optimization Technology of Fault Tolerance Mechanism in Distributed System Based on Neural Network

2022

DPS

View full text Add to dashboard Cite

In the era of big data, distributed systems(DS) have to deal with more and more data, and the possibility of system hardware failure is higher and higher. Traditional disk arrays can no longer meet the high reliability requirements of large-scale distributed clusters. Data fault tolerance has become an important problem in DSs. In order to ensure the reliability of data processing in DSs and continue to provide users with high-quality services, the performance optimization of fault-tolerant mechanisms has become an important research content in DSs. Aiming at the distributed core storage framework proposed in this paper, the fault-tolerant mechanism of its client module and metadata storage management module is designed and implemented, and the performance of the DS is tested through the performance optimization experiment of fault-tolerant mechanism. The experimental results of Prime-based and neural network-based data inpainting show that the neural network-based data inpainting technology can reduce the network cost of data inpainting. The experimental results of distributed computing delay based on radial basis neural network algorithm, C.T. algorithm and Pedone algorithm show that the delay time of RBF algorithm tends to converge with the increase of MRR.

show abstract