Comparison and Improvement of Hadoop MapReduce Performance Prediction Models in the Private Cloud

2016 ◽  
pp. 77-91 ◽  
Author(s):  
Nini Wang ◽  
Jian Yang ◽  
Zhihui Lu ◽  
Xiaoyan Li ◽  
Jie Wu
Keyword(s):  
Performance Prediction ◽  
Prediction Models ◽  
Private Cloud ◽  
Hadoop Mapreduce

scholarly journals Machine Learning–enabled Scalable Performance Prediction of Scientific Codes

2021 ◽  
Vol 31 (2) ◽  
pp. 1-28
Author(s):  
Gopinath Chennupati ◽  
Nandakishore Santhi ◽  
Phill Romero ◽  
Stephan Eidenbenz
Keyword(s):  
Machine Learning ◽  
Performance Prediction ◽  
Prediction Models ◽  
Radiation Transport ◽  
Discrete Event ◽  
Basic Block ◽  
Distribution Models ◽  
Scientific Application ◽  
High Level ◽  
Access Patterns

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. We present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. PPT-AMMP uses machine learning and regression techniques to build the prediction models based on small instances of the input code, then integrates into a higher-order discrete-event simulation model of PPT running on Simian PDES engine. We validate PPT-AMMP on four standard computational physics benchmarks and present a use case of hardware parameter sensitivity analysis to identify bottleneck hardware resources on different code inputs. We further extend PPT-AMMP to predict the performance of a scientific application code, namely, the radiation transport mini-app SNAP. To this end, we analyze multi-variate regression models that accurately predict the reuse profiles and the basic block counts. We validate predicted SNAP runtimes against actual measured times.

scholarly journals Using Decision Trees and Random Forest Algorithms to Predict and Determine Factors Contributing to First-Year University Students’ Learning Performance

Algorithms ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 318
Author(s):  
Thao-Trang Huynh-Cam ◽  
Long-Sheng Chen ◽  
Huynh Le
Keyword(s):  
Random Forest ◽  
Performance Prediction ◽  
Prediction Models ◽  
Family Background ◽  
Educational Practice ◽  
Poor Performance ◽  
Learning Performance ◽  
First Year ◽  
First Year Students ◽  
Early Performance

First-year students’ learning performance has received much attention in educational practice and theory. Previous works used some variables, which should be obtained during the course or in the progress of the semester through questionnaire surveys and interviews, to build prediction models. These models cannot provide enough timely support for the poor performance students, caused by economic factors. Therefore, other variables are needed that allow us to reach prediction results earlier. This study attempts to use family background variables that can be obtained prior to the start of the semester to build learning performance prediction models of freshmen using random forest (RF), C5.0, CART, and multilayer perceptron (MLP) algorithms. The real sample of 2407 freshmen who enrolled in 12 departments of a Taiwan vocational university will be employed. The experimental results showed that CART outperforms C5.0, RF, and MLP algorithms. The most important features were mother’s occupations, department, father’s occupations, main source of living expenses, and admission status. The extracted knowledge rules are expected to be indicators for students’ early performance prediction so that strategic intervention can be planned before students begin the semester.

Pavement Management Systems: Past, Present, and Future

2003 ◽  
Vol 1853 (1) ◽  
pp. 65-71 ◽  
Author(s):  
Ram B. Kulkarni ◽  
Richard W. Miller
Keyword(s):  
Performance Prediction ◽  
Prediction Models ◽  
Pavement Management ◽  
Pavement Performance ◽  
Management Systems ◽  
Seamless Integration ◽  
Positioning Systems ◽  
Pavement Management Systems ◽  
Transportation Organization ◽  
Pavement Performance Prediction

The progress made over the past three decades in the key elements of pavement management systems was evaluated, and the significant improvements expected over the next 10 years were projected. Eight specific elements of a pavement management system were addressed: functions, data collection and management, pavement performance prediction, economic analysis, priority evaluation, optimization, institutional issues, and information technology. Among the significant improvements expected in pavement management systems in the next decade are improved linkage among, and better access to, databases; systematic updating of pavement performance prediction models by using data from ongoing pavement condition surveys; seamless integration of the multiple management systems of interest to a transportation organization; greater use of geographic information and Global Positioning Systems; increasing use of imaging and scanning and automatic interpretation technologies; and extensive use of formal optimization methods to make the best use of limited resources.

Sign in / Sign up

Export Citation Format

Share Document