Home / Current Issue / Paper 1704282
Performance Bottleneck Detection and Root Cause Analysis Using Explainable AI
Subject area: Science,Engineering and Technology · Area of research: Explainable AI
Abstract
Performance bottlenecks in complex systems can significantly hinder operational efficiency and user satisfaction. These bottlenecks often result from various factors, including resource limitations, inefficient algorithms, or suboptimal system configurations. Detecting and analyzing these issues promptly is crucial for maintaining system integrity and performance (Adadi & Berrada, 2018). This research explores the integration of Explainable Artificial Intelligence (XAI) in identifying and addressing the root causes of performance bottlenecks, providing a framework that enhances interpretability and trust in AI-driven solutions. Our study leverages advanced machine learning algorithms coupled with interpretability techniques to provide actionable insights into performance issues. Through empirical testing and analysis, we demonstrate that XAI significantly improves the detection accuracy of performance bottlenecks compared to traditional methods, enabling organizations to implement timely interventions (Lipton, 2016). Furthermore, XAI fosters a deeper understanding of the decision-making processes behind automated systems, empowering stakeholders to make informed choices regarding system optimization. We present a comprehensive methodology for applying XAI to performance data, detailing the steps involved in detecting bottlenecks and analyzing their root causes. Our findings indicate that organizations employing XAI in their performance management strategies not only benefit from enhanced detection capabilities but also from improved user trust and satisfaction. This paper contributes to the growing body of knowledge on XAI by providing empirical evidence of its effectiveness in performance optimization, paving the way for future research in this critical area.
Keywords
Performance Bottlenecks, Root Cause Analysis, Explainable AI, Performance Optimization, Machine Learning
References
[1] Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on Explainable Artificial Intelligence (XAI). IEEE Access, 6, 52138–52160.
[2] Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys (CSUR), 41(3), 1–58.
[3] Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018). Explaining explanations: An overview of interpretability of machine learning. 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), 80–89.
[4] Hodge, V. J., & Austin, J. (2004). A survey of outlier detection methodologies. Artificial Intelligence Review, 22(2), 85–126.
[5] Kim, S., Lee, J., & Park, J. (2021). Performance monitoring of cloud applications: Analysis and lessons. IEEE Transactions on Cloud Computing, 9(1), 216–228.
[6] Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the 14th International Joint Conference on Artificial Intelligence.
[7] Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.
[8] Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1–38.
[9] Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–1144.
[10] Zhang, Y., Zhou, L., & Wu, M. (2020). Real-time anomaly detection in large-scale IT infrastructures. IEEE Access, 8, 18456–18468.ip]\
How to cite this paper
@article{1704282,
author = {Shanmugasundaram Sivakumar},
title = {Performance Bottleneck Detection and Root Cause Analysis Using Explainable AI},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {6},
number = {10},
pages = {1005-1011},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1704282.pdf},
abstract = {Performance bottlenecks in complex systems can significantly hinder operational efficiency and user satisfaction. These bottlenecks often result from various factors, including resource limitations, inefficient algorithms, or suboptimal system configurations. Detecting and analyzing these issues promptly is crucial for maintaining system integrity and performance (Adadi & Berrada, 2018). This research explores the integration of Explainable Artificial Intelligence (XAI) in identifying and addressing the root causes of performance bottlenecks, providing a framework that enhances interpretability and trust in AI-driven solutions.
Our study leverages advanced machine learning algorithms coupled with interpretability techniques to provide actionable insights into performance issues. Through empirical testing and analysis, we demonstrate that XAI significantly improves the detection accuracy of performance bottlenecks compared to traditional methods, enabling organizations to implement timely interventions (Lipton, 2016). Furthermore, XAI fosters a deeper understanding of the decision-making processes behind automated systems, empowering stakeholders to make informed choices regarding system optimization.
We present a comprehensive methodology for applying XAI to performance data, detailing the steps involved in detecting bottlenecks and analyzing their root causes. Our findings indicate that organizations employing XAI in their performance management strategies not only benefit from enhanced detection capabilities but also from improved user trust and satisfaction. This paper contributes to the growing body of knowledge on XAI by providing empirical evidence of its effectiveness in performance optimization, paving the way for future research in this critical area.},
keywords = {Performance Bottlenecks, Root Cause Analysis, Explainable AI, Performance Optimization, Machine Learning},
month = {April},
}