Improving a Run Time Job Prediction Model for Distributed Computing Based on Two Level Predictions

Al-Najjar, Hazem; Alhady, S. S. N.; Saleh, Junita Mohammad

doi:10.1007/978-981-13-6447-1_5

Cited by 5 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schlagkamp et al, 15 Kumar et al, 16 AlZubi, 18 Yu et al, 19 Kaur et al, 21 Al-Najjar et al, 35 Rawal and Rani, 43 Bansal et al, 44 Garg and Singh, 45 Yin et al, 49 describe job performance. This paper presents new DJS algorithms to serve the dependent jobs in a grid system by considering job weight generated using clustering and ranking methods.…”

Section: Run Time/makespan Waiting Time Scheduling Cost Energy Consumption Slowdownmentioning

confidence: 99%

“…Moreover, to define a job weight in grid system, researchers used mainly two main methods including clustering models [31][32][33] and run-time prediction models. 11,12,[34][35][36][37] In clustering models, jobs are divided into groups by using different discrimination methods such as clustering algorithms, wherein the runtime prediction model is used to predict the job's run time using job variables. The clustering and run-time prediction models were considered as the main modeling approaches for calculating the weight of jobs in a grid system.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Scheduling of workflow jobs based on twostep clustering and lowest job weight

Al-Najjar

Alhady

Mohamad–Saleh

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Scheduling is an important technique to improve the productivity of workflow applications in a grid system. Serving workflow applications added overhead on the scheduling system since the scheduler should choose the best zero-dependent job that improves the performance of a grid system. This paper proposes two dependent job scheduling algorithms based on analyzing the effect of categorical and continuous variables of the job, which are used in the calculation of job weight. To find the job weight, twostep clustering is used with 10 groups and the ranking equation. In addition, to verify the ability to apply the proposed algorithms in a real environment, weighted least squares estimation is used. The results showed that the prediction rate is equal to 99.88%, which indicates that the proposed algorithms could be applied in a real grid system with low overhead. Through simulations and after testing the proposed algorithms, the average results showed that the Dependent Job Scheduling (DJS) algorithm outperformed the previous algorithms, in total execution time and an average waiting time with an improvement value of 1.18 and 1.92 times, respectively. While DJS algorithm with weighting factor (DJSJP) outperformed the previous algorithms in total execution time only with an improvement value equal to 1.17 times. The overall results indicated that the proposed algorithms are efficient to be used in a grid system, besides four bits are sufficient to improve the performance of the job scheduling system.

show abstract