Model-Based Resource Utilization and Performance Risk Prediction using Machine Learning Techniques

Haitham A.M Salih - Sudan University of Science and Technology, Khartoum, Sudan
Hany H Ammar - West Virginia University, West Virginia, USA

Citation Format:



The growing complexity of modern software systems makes the performance prediction a challenging activity. Many drawbacks incurred by using the traditional performance prediction techniques such as time consuming and inability to surround all software system when large scaled. To contribute to solving these problems, we adopt a model-based approach for resource utilization and performance risk prediction. Firstly, we model the software system into annotated UML diagrams. Secondly, performance model is derived from UML diagrams in order to be evaluated. Thirdly, we generate performance and resource utilization training dataset by changing workload. Finally, when new instances are applied we can predict resource utilization and performance risk by using machine learning techniques. The approach will be used to enhance work of human experts and improve efficiency of software system performance prediction. In this paper, we illustrate the approach on a case study. A performance training dataset has been generated, and three machine learning techniques are applied to predict resource utilization and performance risk level. Our approach shows prediction accuracy within 68.9 % to 93.1 %.


machine learning; performance; risk prediction; WEKA.

Full Text:



V. Cortellessa, K. Goseva-popstojanova, S. S. Member, K. Appukkutty, A. R. Guedem, A. Hassan, S. S. Member, R. Elnaggar, W. Abdelmoez, S. S. Member, H. H. Ammar, and I. C. Society, “Model-Based Performance Risk Analysis,” vol. 31, no. 1, pp. 3–20, 2005.

A. Radhakrishnan and W. Virginia, “Tool Support for Software Performance Risk Assessment Tool Support for Software Performance Risk Assessment,” 2007.

H. A. Moniem, “A framework for Performance Prediction of Service-Oriented Architecture,” vol. 4, no. 11, pp. 865–870, 2015.

B. Islam, “Predict Software Reliability by Support Vector Machine,” vol. 2, no. 4, pp. 46–52, 2013.

B. Rabta, A. Alp, and G. Reiner, “Queueing Networks Modeling Software for Manufacturing", Rapid Modelling for Increasing Competitiveness pp 15-23, DOI: 10.1007/978-1-84882-748-6_2

Z. Omary and F. Mtenzi, “Machine Learning Approach to Identifying the Dataset Threshold for the Performance Estimators in Supervised Learning,” Int. J., vol. 3, no. 3, pp. 314–325, 2010.

Z. Omary and F. Mtenzi, “Dataset threshold for the performance estimators in supervised machine learning experiments,” 2009 Int. Conf. Internet Technol. Secur. Trans., vol. 3, no. 3, pp. 314–325, 2009.

Q. Zhang, L. Cherkasova, and E. Smirni, “A Regression-Based Analytic Model for Dynamic Resource Provisioning of Multi-Tier Applications,” 2007.

R. Mohanty, “Classification of Web Services Using Bayesian Network,” J. Softw. Eng. Appl., vol. 05, no. 04, pp. 291–296, 2012.

N. Based, “Neighbor Based Algorithm for Multi-label Classification,” pp. 718–721, 2004.

S. Abe, “Fuzzy support vector machines for multilabel classification,” Pattern Recognit., vol. 48, no. 6, pp. 2110–2117, 2015.

A. Ganapathi, “Predicting and optimizing system utilization and performance via statistical machine learning,” UC Berkeley, no. UCB/EECS-2009–181, p. 97, 2009.

K. Singh, E. .Ipek, S. a McKee, B. R. de Supinski, M. Schulz, and R. Caruana, “Predicting parallel application performance via machine learning approaches: Research Articles,” Concurr. Comput. Pr. Exper., vol. 19, no. 17, pp. 2219–2235, 2007.

E. Ipek, B. R. De Supinski, M. Schulz, E. Ipek, B. R. de Supinski, B. R. de Supinski, M. Schulz, M. Schulz, S. A. McKee, and S. A. McKee, “An Approach to Performance Prediction for Parallel Applications,” Euro-Par 2005 Parallel Process., pp. 196 – 205, 2005.

A. Brunnert and H. Krcmar, “Continuous performance evaluation and capacity planning using resource profiles for enterprise applications,” J. Syst. Softw., 2015.

S. Balsamo, R. Mamprin, and M. Marzolla, “Performance evaluation of software architectures with queuing network models’,” Work. Softw. Perform., 1998.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

JOIV : International Journal on Informatics Visualization
ISSN 2549-9610  (print) | 2549-9904 (online)
Organized by Department of Information Technology - Politeknik Negeri Padang, and Institute of Visual Informatics - UKM and Soft Computing and Data Mining Centre - UTHM
W :
E :,,

View JOIV Stats

Creative Commons License is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.