Self-Healing Cloud Database Platforms: Python Automation and Machine Learning for Proactive Issue Detection Across Multi-Cloud Oracle and SQL Server Deployments

Adithya Sirimalla

doi:10.63397/ISCSITR-IJCC_2024_05_01_003

Authors

Adithya Sirimalla USA. Author

DOI:

https://doi.org/10.63397/ISCSITR-IJCC_2024_05_01_003

Keywords:

Self-healing systems, cloud database administration, machine learning, autonomous remediation, Python automation, multi-cloud environments, anomaly detection, AIOps, Oracle, and SQL Server

Abstract

Modern multi-cloud foundations that run mission-critical Oracle and SQL server databases are becoming increasingly complex due to dynamic workloads, heterogeneous environments, and disjointed monitoring systems. Traditional threshold-based or human-mitigated remediation methods are usually slow and reactive, and therefore increase downtime, service-level agreement failure, and operational budgets. This study aims to address these shortcomings by designing a self-repairing cloud database system that combines machine-learning-based anomaly dynamics with Python autonomized correction processes to deliver active real-time mitigation of performance deviations on AWS, Azure, and GCP. The proposed solution materializes an end-to-end feedback loop of continuous monitoring, machine-learned analytics, explainable decision making, and automated execution that is meant to identify aberrations in CPU utilization, I/O latency, and backup delays, and to automatically engage in context-oriented corrective actions.
A multi-cloud stress test of the platform was conducted under a well-planned experimental design to assess the resilience of the platform. The results show significant improvements in performance, such as faster anomaly detection, calculated decreases in mean time to recovery, and better SLA adherence, compared to the normal reactive and replication-based approaches. The aspect of the system, in terms of generalization among different cloud providers, also lends strength to the resiliency of the architecture and its ability to be deployed in a running environment. Along with operational efficiency, the inclusion of explainability mechanisms enhances transparency and aids human supervision in high-stakes contexts. The study is both theoretically and practically contributory in that it presents a repeatable engineering system for the autonomous management of cloud databases. This study demonstrates the practicality and utility of smart self-healing infrastructures and serves as the basis for future developments in predictive analytics, adaptive learning, and safe AI-based automation.

References

W. Khan, T. Kumar, C. Zhang, K. Raj, A. M. Roy, and B. Luo, “SQL and NoSQL Databases Software architectures performance analysis and assessments -- A Systematic Literature review,” arXiv (Cornell University), Sep. 2022, doi: 10.48550/arxiv.2209.06977.

Y. Zhu et al., “Towards Building Autonomous Data Services on Azure,” p. 217, Jun. 2023, doi: 10.1145/3555041.3589674.

B. P. Chaudhari and S. Kabade, “AI-Driven Cloud Services for Guaranteed Disaster Recovery, Improved Fault Tolerance, and Transparent High Availability in Dynamic Cloud Systems,” International Journal of Scientific Research in Science Engineering and Technology, p. 437, Nov. 2023, doi: 10.32628/ijsrset25122169.

H. Bhandari and R. Jaiswal, “Automation of Databases in Oracle,” International Journal for Research in Applied Science and Engineering Technology, vol. 11, no. 11, p. 946, Nov. 2023, doi: 10.22214/ijraset.2023.56643.

J. Kossmann and R. Schlößer, “Self-driving database systems: a conceptual approach,” Distributed and Parallel Databases, vol. 38, no. 4, p. 795, Mar. 2020, doi: 10.1007/s10619-020-07288-w.

J. Alonso et al., “Optimization and Prediction Techniques for Self-Healing and Self-Learning Applications in a Trustworthy Cloud Continuum,” Information, vol. 12, no. 8, p. 308, Jul. 2021, doi: 10.3390/info12080308.

“Foundational Framework Self-Healing Data Pipelines for AI Engineering: A Framework and Implementation,” International Journal of Artificial Intelligence Data Science and Machine Learning, vol. 3, Jan. 2022, doi: 10.63282/3050-9262.ijaidsml-v3i1p107.

F. Li, “Modernization of Databases in the Cloud Era: Building Databases that Run Like Legos,” Proceedings of the VLDB Endowment, vol. 16, no. 12, p. 4140, Aug. 2023, doi: 10.14778/3611540.3611639.

X. Zhou, G. Li, and Z. Liu, “LLM As DBA,” arXiv (Cornell University), Jan. 2023, doi: 10.48550/arxiv.2308.05481.

J. George, “Optimizing hybrid and multi-cloud architectures for real-time data streaming and analytics: Strategies for scalability and integration,” World Journal of Advanced Engineering Technology and Sciences, vol. 7, no. 1, p. 174, Oct. 2022, doi: 10.30574/wjaets.2022.7.1.0087.

S. B. Molina, P. Nespoli, and F. G. Mármol, “Tackling Cyberattacks through AI-based Reactive Systems: A Holistic Review and Future Vision,” arXiv (Cornell University) . Cornell University, Dec. 12, 2023. doi: 10.48550/arxiv.2312.06229.

J. Chen, C. Yi, S. D. Okegbile, J. Cai, and X. Shen, “Networking Architecture and Key Supporting Technologies for Human Digital Twin in Personalized Healthcare: A Comprehensive Survey,” IEEE Communications Surveys & Tutorials, vol. 26, no. 1, p. 706, Sep. 2023, doi: 10.1109/comst.2023.3308717.

E. Wang, P. Tayebi, and Y.-T. Song, “Cloud-Based Digital Twins’ Storage in Emergency Healthcare,” ˜The œInternational journal of networked and distributed computing, vol. 11, no. 2, p. 75, Aug. 2023, doi: 10.1007/s44227-023-00011-y.

V. Shaik and N. Kalyanasundaram, “Assimilating sense into disaster recovery databases and judgement framing proceedings for the fastest recovery,” International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering, vol. 13, no. 4, p. 4234, Apr. 2023, doi: 10.11591/ijece.v13i4.pp4234-4245.

M. Muthusubramanian and J. Jeyaraman, “Data Engineering Innovations: Exploring the Intersection with Cloud Computing, Machine Learning, and AI,” Journal of Knowledge Learning and Science Technology ISSN 2959-6386 (online), vol. 1, no. 1, p. 76, Feb. 2023, doi: 10.60087/jklst.vol1.n1.p84.

Q. Cheng et al., “AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges,” arXiv (Cornell University), Jan. 2023, doi: 10.48550/arxiv.2304.04661.

X. Feng, C. Guo, T. Jiao, and J. Song, “A maturity model for AI-empowered cloud-native databases: from the perspective of resource management,” Journal of Cloud Computing Advances Systems and Applications, vol. 11, no. 1, Sep. 2022, doi: 10.1186/s13677-022-00318-1.

E. O. Alonge, N. L. Eyo-Udo, B. C. Ubanadu, A. I. Daraojimba, E. D. Balogun, and K. O. Ogunsola, “Real-Time Data Analytics for Enhancing Supply Chain Efficiency,” International Journal of Multidisciplinary Research and Growth Evaluation, vol. 2, no. 1, p. 759, Jan. 2021, doi: 10.54660/.ijmrge.2021.2.1.759-771.

J. Uddoh, D. Ajiga, B. P. Okare, and T. D. Aduloju, “AI-Based Threat Detection Systems for Cloud Infrastructure: Architecture, Challenges, and Opportunities,” Journal of Frontiers in Multidisciplinary Research, vol. 2, no. 2, p. 61, Jan. 2021, doi: 10.54660/.ijfmr.2021.2.2.61-67.

A. P. Perumal and P. Chintale, “Improving operational efficiency and productivity through the fusion of DevOps and SRE practices in multi-cloud operations,” International Journal of Cloud Computing and Database Management, vol. 3, no. 2, p. 49, Jul. 2022, doi: 10.33545/27075907.2022.v3.i2a.51.

S. D. Veeravalli, “Proactive Threat Detection in CRM: Applying Salesforce Einstein AI and Event Monitoring to anomaly detection and fraud prevention,” vol. 4, no. 1, p. 16, Oct. 2023, doi: 10.63397/iscsitr-ijsraiml_04_01_002.

S. Amgothu and G. Kankanala, “SRE and DevOps: Monitoring and Incident Response in Multi-Cloud Environments,” International Journal of Science and Research (IJSR), vol. 12, no. 9, p. 2214, Sep. 2023, doi: 10.21275/sr230903224924.

J. Narkarunai, A. Malaiyappan, M. J. K. -, and A. Tadimarri, “Towards Autonomous Infrastructure Management: A Survey of AI-driven Approaches in Platform Engineering,” Journal of Knowledge Learning and Science Technology ISSN 2959-6386 (online), vol. 2, no. 2, p. 303, May 2023, doi: 10.60087/jklst.vol2.n2.p314.

S. A. Oladosu, C. C. Ike, P. A. Adepoju, A. I. Afolabi, A. B. Ige, and O. O. Amoo, “Advancing cloud networking security models: Conceptualizing a unified framework for hybrid cloud and on-premise integrations,” Magna Scientia Advanced Research and Reviews, vol. 3, no. 1, p. 79, Oct. 2021, doi: 10.30574/msarr.2021.3.1.0076.

M. J. Karamthulla, J. Narkarunai, A. Malaiyappan, and S. Prakash, “AI-powered Self-healing Systems for Fault Tolerant Platform Engineering: Case Studies and Challenges,” Journal of Knowledge Learning and Science Technology ISSN 2959-6386 (online), vol. 2, no. 2, p. 327, May 2023, doi: 10.60087/jklst.vol2.n2.p338.

M. A. Naqvi, S. Malik, M. Astekin, and L. Moonen, “On Evaluating Self-Adaptive and Self-Healing Systems using Chaos Engineering,” vol. 52, p. 1, Sep. 2022, doi: 10.1109/acsos55765.2022.00018.

Et. al M. S. Zahoor, “Security Challenges and Solutions in AI-Enhanced Cloud Platforms: A Comprehensive Study.,” Power System Technology, vol. 47, no. 4, p. 103, Dec. 2023, doi: 10.52783/pst.161.

“Lessons from Australia’s ‘Robodebt’ Debacle.” Jul. 17, 2020.

X. Li, Y. Fan, and S. Cheng, “AIGC In China: Current Developments And Future Outlook,” arXiv (Cornell University), Jan. 2023, doi: 10.48550/arxiv.2308.08451.

C. Seah, “Liability Arising from the Use of Artificial Intelligence.” May 2023.

S. Mostafa, D. Mondal, K. Panjvani, L. V. Kochian, and I. Stavness, “Explainable deep learning in plant phenotyping,” Frontiers in Artificial Intelligence, vol. 6. Frontiers Media, Sep. 19, 2023. doi: 10.3389/frai.2023.1203546.

A. Gomaa and M. S. Feld, “Adaptive User-centered Neuro-symbolic Learning for Multimodal Interaction with Autonomous Systems,” arXiv (Cornell University), Jan. 2023, doi: 10.48550/arxiv.2309.05787.

A. Goodman, R. O’Shea, N. Hirschorn, and H. Chrostowski, “Assurance for Deployed Continual Learning Systems,” arXiv (Cornell University), Jan. 2023, doi: 10.48550/arxiv.2311.10787.

M. Altoub, F. Alqurashi, T. Yiğitcanlar, J. M. Corchado, and R. Mehmood, “An Ontological Knowledge Base of Poisoning Attacks on Deep Neural Networks,” Applied Sciences, vol. 12, no. 21, p. 11053, Oct. 2022, doi: 10.3390/app122111053.

S. Du et al., “Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness,” 2023, doi: 10.48550/ARXIV.2308.03666.

S. V. Bayani, R. Tillu, and J. Jeyaraman, “Streamlining Compliance: Orchestrating Automated Checks for Cloud-based AI/ML Workflows,” Journal of Knowledge Learning and Science Technology ISSN 2959-6386 (online), vol. 2, no. 3, p. 413, Aug. 2023, doi: 10.60087/jklst.vol2.n3.p435.

Y. Remil, “A data mining perspective on explainable AIOps with applications to software maintenance,” HAL (Le Centre pour la Communication Scientifique Directe), Oct. 2023, Accessed: Aug. 2025. [Online]. Available: https://theses.hal.science/tel-04391281

V. Baladari, “Cloud Resiliency Engineering: Best Practices for Ensuring High Availability in Multi-Cloud Architectures,” International Journal of Science and Research (IJSR), vol. 11, no. 6, p. 2062, Jun. 2022, doi: 10.21275/sr220610115023.

V. Nagpure, “Network Automation Platforms: Improving Operational Efficiency in Data Centers,” ESP International Journal of Advancements in Computational Technology, Jan. 2023, doi: 10.56472/25838628/ijact-v1i1p119.

F. Ahsan et al., “Data-driven next-generation smart grid towards sustainable energy evolution: techniques and technology review,” Protection and Control of Modern Power Systems, vol. 8, no. 1, Sep. 2023, doi: 10.1186/s41601-023-00319-5.

S. Prabhakaran, S. M. Polisetty, and S. K. Pendyala, “BUILDING A UNIFIED AND SCALABLE DATA ECOSYSTEM: AI-DRIVEN SOLUTION ARCHITECTURE FOR CLOUD DATA ANALYTICS,” INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY, vol. 13, no. 3, p. 137, Dec. 2022, doi: 10.34218/ijcet_13_03_015.

A. Brogi, J. Carrasco, F. Durán, E. Pimentel, and J. Soldani, “Self-healing trans-cloud applications,” Computing, vol. 104, no. 4, p. 809, Jul. 2021, doi: 10.1007/s00607-021-00977-z.

S. Kamadi, “AI-POWERED RATE ENGINES: MODERNIZING FINANCIAL FORECASTING USING MICROSERVICES AND PREDICTIVE ANALYTICS,” INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY, vol. 13, no. 2, p. 220, Aug. 2022, doi: 10.34218/ijcet_13_02_024.

“Utilizing Probability Distribution for Selecting Optimal and Minimal Replicas to Achieving Fault Tolerance in a Distributed System,” International journal of intelligent engineering and systems, vol. 17, no. 1, p. 356, Dec. 2023, doi: 10.22266/ijies2024.0229.32.

K. Mitropoulou, P. Kokkinos, P. Soumplis, and E. Varvarigos, “Anomaly Detection in Cloud Computing using Knowledge Graph Embedding and Machine Learning Mechanisms,” Journal of Grid Computing, vol. 22, no. 1, Dec. 2023, doi: 10.1007/s10723-023-09727-1.

R. Shelby et al., “Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction,” p. 723, Aug. 2023, doi: 10.1145/3600211.3604673.

K. Zaouk, “Neural-Based Modeling for Performance Tuning of Cloud Data Analytics,” HAL (Le Centre pour la Communication Scientifique Directe), Mar. 2021, Accessed: Mar. 2025. [Online]. Available: https://theses.hal.science/tel-03284173

T. Muciaccia and P. Tedeschi, “Future scenarios for the infrastructure digitalization: The road ahead,” Frontiers in the Internet of Things, vol. 2, Mar. 2023, doi: 10.3389/friot.2023.1140799.

D. Yang, J. Yu, Z. He, P. Li, and X. Du, “Applying self-powered sensor and support vector machine in load energy consumption modeling and prediction of relational database,” Scientific Reports, vol. 13, no. 1, Nov. 2023, doi: 10.1038/s41598-023-46414-3.

D. J. Abadi et al., “The Seattle Report on Database Research,” ACM SIGMOD Record, vol. 48, no. 4, p. 44, Feb. 2020, doi: 10.1145/3385658.3385668.