A new average case analysis for completion time scheduling

Scharbrodt, Mark; Schickinger, Thomas; Steger, Angelika

doi:10.1145/509907.509936

Cited by 15 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each stochastic task has an estimated start time, an estimated finish time, an actual start time, and an actual finish time. In the stochastic environment, the processing time and communication time are random, independent, and follow some probability distribution . Each workflow application, which is submitted for the execution, requires the user to determine the distributions obtained through statistical profiling and building a historical table .…”

Section: Problem Formulationmentioning

confidence: 99%

Cost‐effective deadline‐aware stochastic scheduling strategy for workflow applications on virtual machines in cloud computing

Haidri

Katti

Saxena

2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary This paper addresses the problems in scheduling the workflow tasks on cloud computing systems such as minimizing the total price for execution (TPE) and total execution time (TET) of the workflow while meeting the deadline constraints in a stochastic environment. Scheduling such precedence‐constrained stochastic tasks on the cloud with virtual machines of different computing capabilities is a difficult problem. However, instead of TPE and TET, the virtual machine's acquisition delay is one of the primary cloud's characteristics. The current paper first formulates the problem as a stochastic scheduling model on cloud. Then, a stochastic cost‐effective deadline‐aware (S‐CEDA) resource scheduler is developed. S‐CEDA incorporates the expected value and variance of the task's processing time and inter‐task communication time into the workflow scheduling. The experimental results show that S‐CEDA outperforms the existing state‐of‐the‐art algorithms such as stochastic heterogeneous earliest finish time (SHEFT) and cost‐effective deadline‐aware (CEDA) scheduling algorithms in terms of the TPE and TET of the workflow.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Cost‐effective deadline‐aware stochastic scheduling strategy for workflow applications on virtual machines in cloud computing

Haidri

Katti

Saxena

2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Numerous studies have addressed the topic of estimating task characteristics, such as analytical benchmarking, historical table, code profiling, and statistical and probabilistic techniques . However, these methods are not effective and suitable for predicting the features of cloud application tasks.…”

Section: System Modelsmentioning

confidence: 99%

“…However, in real‐world problems, cloud tasks usually have different execution cycles due to the program characteristic, cloud virtualization technology, resource sharing across multidomains, and so on. These phenomena are usually lead to unpredictable execution time, fluctuating workloads, and variable cost factors that makes the scheduling problem computationally intractable . The most suitable technique to tackle this problem is to adopt cloud task probability execution model and consider the problem as stochastic scheduling …”

Section: Introductionmentioning

confidence: 99%

“…M Scharbrodt et al dealt with the problem of scheduling n jobs on m machines so that the sum of job completion times is minimized. They proved that the classic SEPT scheduling strategy with Ω( n ) worst‐case competitive ratio achieves an average of ϑ (1) under several natural distributions . Gu and Lu devised a semi‐preemptive policy for uniform machine problem policy and proved the expected asymptotical ratio of semi‐preemptive is one .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Budget‐constraint stochastic task scheduling on heterogeneous cloud systems

Tang

2017

Concurrency and Computation

View full text Add to dashboard Cite

Summary In the past few years, more and more business‐to‐consumer and enterprise applications run in the heterogeneous clouds. Such cloud bag‐of‐tasks applications are usually budget constrained, and their scheduling is an essential problem for cloud provider. The problem is even more complex and challenging when the accurate knowledge about task execution time is unknown in advance. Focusing on these challenges, we first build a cloud resource management architecture and stochastic task model, which divides cloud task into two execution parts. Then, we deduce bag‐of‐tasks applications' schedule length (Makespan) and total cost according to heterogeneous clouds' online feedback information of task first part execution. Thirdly, we formulate this stochastic scheduling problem as a linear programming problem. Lastly, we propose a time and cost multiobjective stochastic task scheduling genetic algorithm, in which can find Pareto optimal schedules for stochastic cloud task that meet its budget constraint. The extensive simulation experiments were carried out on a heterogeneous cloud platform with 400 virtual machines, and tasks were derived from Parallel Workloads Archive and the analysis data of real‐world cloud systems. The experimental results show that our proposed stochastic task scheduling genetic algorithm can get shorter schedule length and lower cost with task budget constraints.

show abstract

“…Later, Megow et al improved the results under a more general environment [11]. Scharbrodt et al presented an average-case analysis for that problem [12].…”

Section: Related Workmentioning

confidence: 99%

Scheduling Precedence Constrained Stochastic Tasks on Heterogeneous Cluster Systems

Veeravalli

et al. 2015

IEEE Trans. Comput.

178

View full text Add to dashboard Cite

Generally, a parallel application consists of precedence constrained stochastic tasks, where task processing times and intertask communication times are random variables following certain probability distributions. Scheduling such precedence constrained stochastic tasks with communication times on a heterogeneous cluster system with processors of different computing capabilities to minimize a parallel application's expected completion time is an important but very difficult problem in parallel and distributed computing. In this paper, we present a model of scheduling stochastic parallel applications on heterogeneous cluster systems. We discuss stochastic scheduling attributes and methods to deal with various random variables in scheduling stochastic tasks. We prove that the expected makespan of scheduling stochastic tasks is greater than or equal to the makespan of scheduling deterministic tasks, where all processing times and communication times are replaced by their expected values. To solve the problem of scheduling precedence constrained stochastic tasks efficiently and effectively, we propose a stochastic dynamic level scheduling (SDLS) algorithm, which is based on stochastic bottom levels and stochastic dynamic levels. Our rigorous performance evaluation results clearly demonstrate that the proposed stochastic task scheduling algorithm significantly outperforms existing algorithms in terms of makespan, speedup, and makespan standard deviation.

show abstract

A new average case analysis for completion time scheduling

Cited by 15 publications

References 12 publications

Cost‐effective deadline‐aware stochastic scheduling strategy for workflow applications on virtual machines in cloud computing

Cost‐effective deadline‐aware stochastic scheduling strategy for workflow applications on virtual machines in cloud computing

Budget‐constraint stochastic task scheduling on heterogeneous cloud systems

Scheduling Precedence Constrained Stochastic Tasks on Heterogeneous Cluster Systems

Contact Info

Product

Resources

About