Performance Testing using Machine Learning

International Journal of Computer Science and Engineering

© 2023 by SSRG - IJCSE Journal

Volume 10 Issue 6

Year of Publication : 2023

Authors : Vivek Basavegowda Ramu

10.14445/23488387/IJCSE-V10I6P105

How to Cite?

Vivek Basavegowda Ramu, "Performance Testing using Machine Learning," SSRG International Journal of Computer Science and Engineering , vol. 10,  no. 6, pp. 36-42, 2023. Crossref, https://doi.org/10.14445/23488387/IJCSE-V10I6P105

Abstract:

Performance testing is a very important aspect of software development, aiming to ensure that applications meet the desired performance standards under various load conditions. Traditional performance testing approaches often face limitations and challenges in accurately identifying performance bottlenecks. This research investigates the idea of enhancing performance testing by utilizing machine learning techniques in order to go above these limits. This paper gives an overview of machine learning and some potential uses for it in performance evaluation. It discusses the benefits and advantages of incorporating machine learning, highlighting its ability to predict system behavior, detect anomalies and provide optimization recommendations. The paper also explores key performance metrics and data collection methods, emphasizing the significance of collecting accurate and relevant data for training machine learning models. The predictive modeling capabilities of machine learning are explored, showcasing how these models can be trained using historical performance data to forecast system behavior under different load scenarios. Techniques for evaluating the accuracy and effectiveness of predictive models are also discussed. The research also looks at the use of machine learning for performance anomaly detection, addressing the difficulties in locating performance-related issues. In order to identify and resolve performance bottlenecks, various methods, including outlier identification and grouping, are discussed. Additionally, the paper explores optimization and recommendation techniques driven by machine learning models. It highlights how these models can identify performance bottlenecks and provide suggestions for enhancing system performance, ultimately improving the user experience. By leveraging the capabilities of machine learning models, performance testers and software developers can enhance their ability to identify performance issues, optimize system performance and deliver efficient software.

Keywords:

Performance testing, Machine learning, Predictive modeling, Anomaly detection, Optimization.

References:

[1] Rijwan Khan, and Mohd Amjad, “Performance Testing (Load) of Web Applications Based on Test Case Management,” Perspectives in Science, vol. 8, pp. 355–357, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Vivek Basavegowda Ramu, and Ajay Reddy Yeruva, “The Capability of Observing Performance in Healthcare Systems,” Computational Intelligence for Clinical Diagnosis, EAI/Springer Innovations in Communication and Computing, Springer, Cham, pp. 541-548, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Victor Costa, “Taxonomy of Performance Testing Tools,” Proceedings of the 35th Annual ACM Symposium on Applied Computing, pp. 1997-2004, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] IBM Developer, IBM Developer, 2020. [Online]. Available: Https://Developer.Ibm.Com/Learningpaths/Get-Started-With-DeepLearning/An-Introduction-to-Deep-Learning/
[5] Denio Duarte, and Niclas Ståhl, “Machine Learning: A Concise Overview,” Studies in Big Data, pp. 27–58.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Mahshid Helali Moghadam et al., “Poster: Performance Testing Driven By Reinforcement Learning,” 2020 IEEE 13th International Conference on Software Testing, Validation and Verification (ICST), pp. 402-405, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Mahshid Helali Moghadam et al., “Machine Learning to Guide Performance Testing: An Autonomous Test Framework,” 2019 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), pp. 164-167, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Mahshid Helali Moghadam, “Machine Learning-Assisted Performance Testing,” Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 1187-1189, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ali Sedaghatbaf et al., “Automated Performance Testing Based on Active Deep Learning,” 2021 IEEE/ACM International Conference on Automation of Software Test (AST), pp. 11-19, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Munidhanalakshmi Kumbakonam, and R. Mahammad Shafi, “Application Measurement and Software Quality Testing Using Machine Learning Performance Techniques,” 2021 Fourth International Conference on Computational Intelligence and Communication Technologies (CCICT), pp. 372-376, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Beyond Supervised Learning, Deep Learning for Physics Research, pp. 217–218, 2021.
[CrossRef] [Publisher Link]
[12] M. Emre Celebi, and Kemal Aydin, Unsupervised Learning Algorithms, 2016. [CrossRef] [Publisher Link] [13] Omer Gottesman et al., “Guidelines for Reinforcement Learning in Healthcare,” Nature Medicine, vol. 25, pp. 16–18, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Rakesh Kumar Lenka et al., “Performance and Load Testing: Tools and Challenges,” 2018 International Conference on Recent Innovations in Electrical, Electronics & Communication Engineering (ICRIEECE), pp. 2257-2261, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Nisha Arya, A Brief Introduction to Reinforcement Learning. Ejable, 2022. [Online]. Available: Https://Www.Ejable.Com/TechCorner/Ai-Machine-Learning-and-Deep-Learning/A-Brief-Introduction-to-Reinforcement-Learning/
[16] Qiang Zhu, “Business Applications of Predictive Modeling at Scale,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2139–2140, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[17] What Is Predictive Modeling? Definition and Overview, What Is Predictive Modeling? Definition and Overview | Outsystems, 2023. [Online]. Avaialable: Https://Www.Outsystems.Com/Glossary/What-Is-Predictive-Modeling/
[18] Xavier Baril et al., “Application Performance Anomaly Detection with LSTM on Temporal Irregularities in Logs,” Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 1961-1964, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Kazuo Minami et al., “Performance Optimization of Applications,” The Art of High Performance Computing for Computational Science, vol. 2, pp. 11–39, 2019.[CrossRef] [Publisher Link]