Adaptive Causal Discovery in Dynamic Web Architectures: A Real-Time Framework for Performance Bottleneck Identification

Minghao Xu; Brandon Whitaker

doi:10.54097/eyd0p366

Authors

Minghao Xu
Brandon Whitaker

DOI:

https://doi.org/10.54097/eyd0p366

Keywords:

Causal discovery, Performance bottleneck detection, Dynamic web architectures, Microservices, Real-time monitoring, Graph neural networks, Adaptive systems

Abstract

Dynamic web architectures face increasing complexity in identifying performance bottlenecks due to their distributed nature and rapidly changing operational conditions. Traditional monitoring approaches often rely on correlation-based metrics that fail to capture the underlying causal relationships between system components, leading to suboptimal diagnosis and remediation strategies. This paper presents an adaptive causal discovery framework specifically designed for real-time performance bottleneck identification in dynamic web architectures. The proposed framework integrates temporal causal inference with graph neural networks to construct dynamic causal graphs representing the evolving relationships between microservices, resource utilization patterns, and service transition probabilities. By employing a hybrid approach that combines Granger causality analysis with adaptive threshold detection at resource saturation points, the framework achieves high accuracy in identifying root causes of performance degradation. The methodology incorporates streaming data processing capabilities that enable continuous monitoring and real-time causal graph updates, ensuring effectiveness even as the architecture scales or undergoes reconfigurations. Experimental evaluation on three production-scale microservice applications demonstrates that the proposed framework achieves 91.3% accuracy in bottleneck localization with an average detection latency of 127 milliseconds, significantly outperforming existing correlation-based and static causal analysis methods.

Downloads

Download data is not yet available.

References

[1] Yang, Y., Ding, G., Chen, Z., & Yang, J. (2025). GART: Graph Neural Network-based Adaptive and Robust Task Scheduler for Heterogeneous Distributed Computing. IEEE Access.

[2] Dakkak, A., Bosch, J., Olsson, H. H., & Mattos, D. I. (2023). Continuous deployment in software-intensive system-of-systems. Information and Software Technology, 159, 107200.

[3] Wang, M., Zhang, X., & Han, X. (2025). AI Driven Systems for Improving Accounting Accuracy Fraud Detection and Financial Transparency. Frontiers in Artificial Intelligence Research, 2(3), 403-421.

[4] Sabuhi, M. (2023). Strategies For Building Performant Containerized Applications.

[5] Lu, K., Fang, X., Fang, N., & Asare, E. (2022). Discovery of effective infrequent sequences based on maximum probability path. Connection Science, 34(1), 63-82

[6] Lin, H., & Liu, W. (2025). Causal Inference-Driven Web Performance Modeling: A Structure-Aware Framework with Symmetric Dependency Analysis for Predictive Optimization. Symmetry.

[7] Zheng X, et al. Comprehensive Review and Empirical Evaluation of Causal Discovery Algorithms for Numerical Data. arXiv preprint arXiv:2407.13054. 2024.

[8] Yaghoobi, A. (2025). Hybrid AI-driven Approach to Context-Aware Inter-Slice Load Balancing for Cloud-Native Functions in 5G Networks (Doctoral dissertation, Carleton University).

[9] Mardanshahi, A., Sreekumar, A., Yang, X., Barman, S. K., & Chronopoulos, D. (2025). Sensing techniques for structural health monitoring: A state-of-the-art review on performance criteria and new-generation technologies. Sensors, 25(5), 1424.

[10] Wang, K., Gao, Q., Pang, X., Li, H., & Liu, W. (2024). Estimating the Health State of Lithium-Ion Batteries Using an Adaptive Gated Sequence Network and Hierarchical Feature Construction. Batteries, 10(8), 278.

[11] Fida, M. R., Ahmed, A. H., Dreibholz, T., Ocampo, A. F., Elmokashfi, A., & Michelinakis, F. I. (2023). Bottleneck identification in cloudified mobile networks based on distributed telemetry. IEEE Transactions on Mobile Computing, 23(5), 5660-5676.

[12] Li, J., Li, S., Tan, J., Cheng, S., Jin, D., Chen, S., & Yang, J. (2024, October). Graph Coding Aided Deep Reinforcement Learning for Fault-tolerant Workflow Scheduling. In 2024 IEEE 24th International Conference on Communication Technology (ICCT) (pp. 60-65). IEEE.

[13] Sun, T., Yang, J., Li, J., Chen, J., Liu, M., Fan, L., & Wang, X. (2024). Enhancing auto insurance risk evaluation with transformer and SHAP. IEEE Access.

[14] Zhang, X., Li, P., Han, X., Yang, Y., & Cui, Y. (2024). Enhancing Time Series Product Demand Forecasting with Hybrid Attention-Based Deep Learning Models. IEEE Access.

[15] Sun, T., & Wang, M. (2025). Usage-Based and Personalized Insurance Enabled by AI and Telematics. Frontiers in Business and Finance, 2(02), 262-273.

[16] Chen, S., Liu, Y., Zhang, Q., Shao, Z., & Wang, Z. (2025). Multi‐Distance Spatial‐Temporal Graph Neural Network for Anomaly Detection in Blockchain Transactions. Advanced Intelligent Systems, 2400898.

[17] Wang, M., Zhang, X., Yang, Y., & Wang, J. (2025). Explainable Machine Learning in Risk Management: Balancing Accuracy and Interpretability. Journal of Financial Risk Management, 14(3), 185-198.

[18] Zhang, H., Ge, Y., Zhao, X., & Wang, J. (2025). Hierarchical deep reinforcement learning for multi-objective integrated circuit physical layout optimization with congestion-aware reward shaping. IEEE Access.

[19] Ren, S., & Chen, S. (2025). Large Language Models for Cybersecurity Intelligence, Threat Hunting, and Decision Support. Computer Life, 13(3), 39-47.

[20] Ge, Y., Wang, Y., Liu, J., & Wang, J. (2025). GAN-Enhanced Implied Volatility Surface Reconstruction for Option Pricing Error Mitigation. IEEE Access.

[21] Wang, Y., Ding, G., Zeng, Z., & Yang, S. (2025). Causal-Aware Multimodal Transformer for Supply Chain Demand Forecasting: Integrating Text, Time Series, and Satellite Imagery. IEEE Access.

[22] Liu, J., Wang, J., and Lin, H. (2025). Coordinated Physics-Informed Multi-Agent Reinforcement Learning for Risk-Aware Supply Chain Optimization. IEEE Access

[23] Yang, Y., Wang, M., Wang, J., Li, P., & Zhou, M. (2025). Multi-Agent Deep Reinforcement Learning for Integrated Demand Forecasting and Inventory Optimization in Sensor-Enabled Retail Supply Chains. Sensors (Basel, Switzerland), 25(8), 2428.

[24] Chen, S., & Ren, S. (2025). AI-enabled Forecasting, Risk Assessment, and Strategic Decision Making in Finance. Frontiers in Business and Finance, 2(02), 274-295.

[25] Han, X., Yang, Y., Chen, J., Wang, M., & Zhou, M. (2025). Symmetry-Aware Credit Risk Modeling: A Deep Learning Framework Exploiting Financial Data Balance and Invariance. Symmetry (20738994), 17(3).

[26] Jiang, B., Cao, J., Tan, Y., & Qiu, S. (2025). Deep Learning Architectures for Sequential Decision-Making in Financial Systems: From Fraud Detection to Risk Management. Journal of Banking and Financial Dynamics, 9(9), 1-11.

[27] Wang, M., Zhang, X., Yang, Y., & Wang, J. (2025). Explainable Machine Learning in Risk Management: Balancing Accuracy and Interpretability. Journal of Financial Risk Management, 14(3), 185-198.

[28] Zhang, S., Qiu, L., & Zhang, H. (2025). Edge cloud synergy models for ultra-low latency data processing in smart city iot networks. International Journal of Science, 12(10).

[29] Yang, J., Zeng, Z., & Shen, Z. (2025). Neural-Symbolic Dual-Indexing Architectures for Scalable Retrieval-Augmented Generation. IEEE Access.

[30] Sun, T., Wang, M., & Chen, J. (2025). Leveraging Machine Learning for Tax Fraud Detection and Risk Scoring in Corporate Filings. Asian Business Research Journal, 10(11), 1-13.