An Autonomous Agentic Ai Framework For Coverage-Guided Chaos Engineering And Resilience Optimisation In Cloud-Native Distributed Systems
DOI:
https://doi.org/10.63665/IJAICE.0201.09Keywords:
Agentic AI, Chaos Engineering, Cloud-Native Systems, Resilience Optimization, Machine Learning, Fault Injection, Predictive Analytics, MicroservicesAbstract
The distributed architecture complexity and dynamic failure behaviors drive the need for smart resilience solutions on cloud-native systems for increased resilience. The introduction of intelligent resilience strategies is driven by the distributed systems' increasing complexity and failure behaviors. The main goal of this research is to come up with an autonomous agentic AI framework for coverage-guided chaos engineering and resilience optimization. Machine learning models were then applied to the Synthetic Cloud telemetry data, and Gradient Boosting showed 95.85% accuracy and 99.37% ROC-AUC in predicting failure discovery. There are identified factors of resilience through feature analysis, which are considered important, involving dependency complexity, architecture complexity, and coverage gaps. This framework opens the door to intelligent chaos experiment prioritization and adaptive reliability improvement to further increase the robustness of cloud infrastructures and the ability to detect failures in a proactive manner.
References
[1]. Verma, H., 2024. AI Agentic Architectures for Autonomous Data Engineering Pipelines. International Journal of Research and Applied Innovations, 7(6), pp.11984-11994.
[2]. Olufemi, O.D., Ejiade, A.O., Ogunjimi, O. and Ikwuogu, F.O., 2024. AI-enhanced predictive maintenance systems for critical infrastructure: Cloud-native architectures approach. World Journal of Advanced Engineering Technology and Sciences, 13(02), pp.229-257.
[3]. Oladoja, T., 2024. Artificial Intelligence-Driven Innovations in VLSI, DevOps Security, and Cloud-Native Platforms: Addressing Challenges in Modern Technology Development.
[4]. Moretti, M.C., 2021. Intelligent Real-Time Software Optimization Framework: Deep Learning–Enhanced Hybrid Fuzzy Model with WPM, TOPSIS, and PSO for Agentic Negotiation in Autonomous Systems. International Journal of Engineering & Extended Technologies Research (IJEETR), 3(6), pp.4009-4013.
[5]. Rousseau, C.A., 2024. A cloud-native enterprise framework enabling AI-driven automation governance secure networks mobile platforms and ethical decision intelligence. International Journal of Research and Applied Innovations, 7(5), pp.11426-11436.
[6]. Dähling, S., Razik, L. and Monti, A., 2021. Enabling scalable and fault-tolerant multi-agent systems by utilizing cloud-native computing. Autonomous Agents and Multi-Agent Systems, 35(1), p.10.
[7]. Katta, T.B., 2023. Adaptive AI-driven integration pipelines for efficient data and process orchestration in cloud-native environments. International Journal of Research and Applied Innovations, 6(1), pp.8363-8374.
[8]. Patel, B.D., 2020. Architecting Enterprise Decision Intelligence through Cloud Native Computing and AI Powered Security Analytics. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 3(5), pp.3711-3717.
[9]. Rajasekar, M., 2023. Agentic AI–Driven CI/CD for Secure and Waste-Reduced SAP Deployments in Healthcare Hybrid Cloud Environments. International Journal of Research and Applied Innovations, 6(3), pp.8916-8921.
[10]. Reddy, V.A.R., 2023. Orchestrating the Future Autonomous Healthcare Data Pipeline Management through Agentic AI Architectures. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 6(2), pp.7979-7992.
[11]. Habibi, P. and Leon-Garcia, A., 2024. Slicesphere: Agile service orchestration and management framework for cloud-native application slices. Ieee Access, 12, pp.169024-169049.
[12]. Abhireddy, N., 2024. AI-driven cloud data orchestration for real-time enterprise decision intelligence systems. International Journal of Research and Applied Innovations, 7(6), pp.11963-11983.
[13]. Mitchell, B.S., Mancoridis, S. and Kashyap, J., 2024, December. On the automatic identification of misconfiguration errors in cloud native systems. In Proceedings of the 2024 7th Artificial Intelligence and Cloud Computing Conference (pp. 539-548).
[14]. Punzo, G., Tewari, A., Butans, E., Vasile, M., Purvis, A., Mayfield, M. and Varga, L., 2020. Engineering resilient complex systems: the necessary shift toward complexity science. IEEE Systems Journal, 14(3), pp.3865-3874.
[15]. Ramaswamy, Y., 2020. Resilience engineering in DevOps: Fault injection and chaos testing for distributed systems. NeuroQuantology, 18(12), pp.337-347.
[16]. Chava, S.C., 2024. Chaos Engineering for Multi-Cloud Resilience. work, 8, p.10.
[17]. Naghshbandi, S.N., Varga, L., Purvis, A., Mcwilliam, R., Minisci, E., Vasile, M., Troffaes, M., Sedighi, T., Guo, W., Manley, E. and Jones, D.H., 2020. A review of methods to study resilience of complex engineering and engineered systems. Ieee Access, 8, pp.87775-87799.
[18]. Torkura, K.A., Sukmana, M.I., Cheng, F. and Meinel, C., 2020. Cloudstrike: Chaos engineering for security and resiliency in cloud infrastructure. IEEE Access, 8, pp.123044-123060.
[19]. Dedousis, P., Stergiopoulos, G., Arampatzis, G. and Gritzalis, D., 2023. Enhancing operational resilience of critical infrastructure processes through chaos engineering. IEEE Access, 11, pp.106172-106189.
[20]. Bedoya, M., Palacios, S., Díaz-López, D., Laverde, E. and Nespoli, P., 2024. Enhancing DevSecOps practice with Large Language Models and Security Chaos Engineering: M. Bedoya et al. International Journal of Information Security, pp.1-24.
[21]. Jernberg, H., Runeson, P. and Engström, E., 2020, October. Getting Started with Chaos Engineering-design of an implementation framework in practice. In Proceedings of the 14th ACM/IEEE international symposium on Empirical Software Engineering and Measurement (ESEM) (pp. 1-10).
[22]. Hwang, J., Kale, G., Patel, P.P., Vishwakarma, R., Aliasgari, M., Hedayatipour, A., Rezaei, A. and Sayadi, H., 2023. Machine learning in chaos-based encryption: Theory, implementations, and applications. IEEE access, 11, pp.125749-125767.
[23]. Meiklejohn, C.S., Estrada, A., Song, Y., Miller, H. and Padhye, R., 2021, November. Service-level fault injection testing. In Proceedings of the ACM Symposium on Cloud Computing (pp. 388-402).
[24]. Gudelli, V.R., 2022. Microservice architecture: Challenges, solutions, and best practices. International Research Journal of Modernization in Engineering Technology and Science, 4(9), pp.2698-2712.
[25]. Dondapati, K., 2020. Robust software testing for distributed systems using cloud infrastructure, automated fault injection, and XML scenarios. World Journal of Advanced Engineering Technology and Sciences, 8(2).
[26]. Bencherqui, A., Tahiri, M.A., Karmouni, H., Alfidi, M., El Afou, Y., Qjidaa, H. and Sayyouri, M., 2024. Chaos-enhanced archimede algorithm for global optimization of real-world engineering problems and signal feature extraction. Processes, 12(2), p.406.
[27]. Al-Said Ahmad, A., Al-Qora’n, L.F. and Zayed, A., 2024. Exploring the impact of chaos engineering with various user loads on cloud native applications: an exploratory empirical study: AA-S. Ahmad et al. Computing, 106(7), pp.2389-2425.
[28]. Harve, B.M., Bidkar, D.M., Krishnappa, M.S., Pandy, G., Jayaram, V., Veerapaneni, P.K. and Mehta, G., 2024, December. The cloud-native revolution: Microservices in a cloud-driven world. In 2024 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) (pp. 1043-1048). IEEE.
[29]. Theodoropoulos, T., Rosa, L., Benzaid, C., Gray, P., Marin, E., Makris, A., Cordeiro, L., Diego, F., Sorokin, P., Girolamo, M.D. and Barone, P., 2023. Security in cloud-native services: A survey. Journal of Cybersecurity and Privacy, 3(4), pp.758-793.
[30]. Soumplis, P., Kontos, G., Kokkinos, P., Kretsis, A., Barrachina-Muñoz, S., Nikbakht, R., Baranda, J., Payaró, M., Mangues-Bafalluy, J. and Varvarigos, E., 2024. Performance optimization across the edge-cloud continuum: A multi-agent rollout approach for cloud-native application workload placement. SN computer science, 5(3), p.318.
[31]. Performance Analysis of Wireless Sensor Networks for Smart Monitoring Applications. (2016). International Journal of Humanities and Information Technology, 1(04), 10-29. https://doi.org/10.21590/ijhit.01.04.04
[32]. Distributed Data Processing Frameworks for Large-Scale Healthcare Analytics. (2019). International Journal of Advance Industrial Engineering, 7(04), 1-10. https://doi.org/10.14741/ijaie/v.7.4.01
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Author
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
