Predicting running time of aerodynamic jobs in HPC system by combining supervised and unsupervised learning method

Improving resource utilization is an important goal of high-performance computing systems of supercomputing centers.To meet this goal,the job scheduler of high-performance computing systems often uses backfilling scheduling to fill short-time jobs into job gaps at the front of the queue.Backfilling scheduling needs to obtain the running time of the job.In the past,the job running time is usually given by users and often far exceeded the actual running time of the job,which leads to inaccurate backfilling and a waste of computing resources.In particular,when the predicted job running time is lower than the actual time,the damage caused to the utilization of the system’s computing resources becomes more serious.Therefore,the prediction accuracy of the job running time is crucial to the utilization of system resources.The use of machine learning methods can make more accurate predictions of the job running time.Aiming at the parallel application of aerodynamics,we propose a job running time prediction framework SU combining supervised and unsupervised learning and verify it on the real historical data of the high-performance computing systems of China Aerodynamics Research and Development Center(CARDC).The experimental results show that SU has a high prediction accuracy(80.46%)and a low underestimation rate(24.85%).

MODELING AND PREDICTION CONCERNING TIME SERIES OF FLOOD/DROUGHT RUNS USING THE SELF-EXCITING THRESHOLD AUTOREGRESSIVE MODEL

When linear regressive models such as AR or ARMA model are used for fitting and predicting climatic time series,results are often not sufficiently good because nonlinear variations in the time series.In this paper, a nonlinear self-exciting threshold autoregressive(SETAR)model is applied to modeling and predicting the time series of flood/drought runs in Beijing,which were derived from the graded historical flood/drought records in the last 511 years(1470—1980).The results show that the modeling and predicting with the SETAR model are much better than that of the AR model.The latter can predict the flood/drought runs with a length only less than two years,while the formal can predict more than three-year length runs.This may be due to the fact that the SETAR model can renew the model according to the run-turning points in the process of predic- tion,though the time series is nonstationary.