Intelligent AI-Cloud Architecture for Zero-Touch Digital BMS Operations Leveraging BERT, SVM, and SDN
DOI:
https://doi.org/10.15662/IJARCST.2025.0806004Keywords:
AI-Cloud Architecture, Zero-Touch Digital BMS, BERT, SVM, SDN, Intelligent Automation, Predictive Analytics, Smart Building EcosystemsAbstract
This paper presents an Intelligent AI-Cloud Architecture for zero-touch digital Building Management System (BMS) operations, integrating BERT, Support Vector Machine (SVM), and Software-Defined Networking (SDN) to enable automated, real-time monitoring and control of smart building infrastructures. The proposed framework leverages AI-driven analytics and cloud computing to predict system anomalies, optimize energy usage, and enhance operational efficiency. BERT-based models support natural language understanding for system commands and reporting, while SVM provides accurate predictive classification for fault detection and risk assessment. SDN ensures dynamic, secure, and efficient network management across distributed BMS components. This architecture emphasizes minimal human intervention, scalable deployment, and intelligent automation, fostering resilient, digital, and energy-efficient building ecosystems.
Results show that AI‑based monitoring combined with automated policy enforcement can detect a broad spectrum of threats—including insider access anomalies, misconfigurations, and external attacks—with high accuracy (above 90%) and low false positive rates (<10%), reducing incident response times by over 50% compared to traditional methods. The architecture scales well in cloud‑native environments, with acceptable performance overhead for microservices and serverless functions. However, challenges remain, including the complexity of modeling policies, ensuring auditability and explainability, managing drift in AI models, and satisfying strict regulatory compliance. The paper concludes that the proposed framework provides a viable path toward more secure and resilient cloud‑native banking, while maintaining performance. Future work includes deploying in production settings, extending to newer threat types (e.g., supply chain attacks), and integrating emerging privacy technologies like federated learning and confidential computing.
References
1. Boggarapu, N. B. (2024). Modernizing Banking Compliance: An Analysis of AI Powered Data Governance in a Hybrid Cloud Environment. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 10(6), 2373 2381. ResearchGate
2. Madasamy, S. (2022). Secure cloud architectures for AI enhanced banking and insurance services. International Research Journal of Modernization in Engineering Technology and Science, 04(05), 6345 6353. ResearchGate
3. Adari, V. K. (2024). The Path to Seamless Healthcare Data Exchange: Analysis of Two Leading Interoperability Initiatives. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 7(6), 11472-11480.
4. Azmi, S. K. (2021). Delaunay Triangulation for Dynamic Firewall Rule Optimization in Software-Defined Networks. Well Testing Journal, 30(1), 155-169.
5. Rahaman, M. S., Nasrin Tisha, S., Eunjee Song, & Cerny, T. (2023). Access Control Design Practice and Solutions in Cloud Native Architecture: A Systematic Mapping Study. Sensors, 23(7), article 3413. MDPI
6. Nallamothu, T. K. (2025). AI-DRIVEN WORKFLOW TRANSFORMATION IN CLINICAL PRACTICE: EVALUATING THE EFFECTIVENESS OF DRAGON COPILOT. International Journal of Research and Applied Innovations, 8(3), 12298-13013.
7. Thambireddy, S., Bussu, V. R. R., Madathala, H., Mane, V., & Inamdar, C. (2025, August). AI-Enabled SAP Enterprise Systems: A Comprehensive Business Use Case Survey. In 2025 5th International Conference on Soft Computing for Security Applications (ICSCSA) (pp. 1045-1052). IEEE.
8. Turpu, R. R. (2022). Leveraging Machine Learning for Anomaly Detection in Banking Cloud Environments. International Journal of Artificial Intelligence & Machine Learning, 1(1), 29 38. ResearchGate
9. Arjunan, T., Arjunan, G., & Kumar, N. J. (2025, May). Optimizing Quantum Support Vector Machine (QSVM) Circuits Using Hybrid Quantum Natural Gradient Descent (QNGD) and Whale Optimization Algorithm (WOA). In 2025 6th International Conference for Emerging Technology (INCET) (pp. 1-7). IEEE
10. Vashistha, A., & Tiwari, A. K. (2024). Building Resilience in Banking Against Fraud with Hyper Ensemble Machine Learning and Anomaly Detection Strategies. SN Computer Science, 5, 556. SpringerLink
11. Punia, A., Gulia, P., Gill, N. S., Ibeke, E., & Shukla, P. K. (2024). A systematic review on blockchain based access control systems in cloud environment. Journal of Cloud Computing, 13, 146. SpringerOpen
12. Lanka, S. (2024). Redefining Digital Banking: ANZ’s Pioneering Expansion into Multi-Wallet Ecosystems. International Journal of Technology, Management and Humanities, 10(01), 33-41.
13. Shaon, F., Rahaman, S., & Kantarcioglu, M. (2021). The Queen’s Guard: A Secure Enforcement of Fine grained Access Control In Distributed Data Analytics Platforms. arXiv preprint arXiv:2106.13123. arXiv
14. Narapareddy, V. S. R., &Yerramilli, S. K. (2024). Zero-TouchEmployee UX. Universal Library of Engineering Technology., 01(02), 55–63. https://doi.org/10.70315/uloap.ulete. 2024.0102009
15. Industry / Practitioner sources: Aqua Security (on CNAPPs), Palo Alto Networks (on microsegmentation, container workload protection) etc. Aqua+1
16. Konda, S. K. (2022). ENGINEERING RESILIENT INFRASTRUCTURE FOR BUILDING MANAGEMENT SYSTEMS: NETWORK RE-ARCHITECTURE AND DATABASE UPGRADE AT NESTLÉ PHX. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 5(1), 6186-6201.
17. Huang, Z., & Pearlson, K. (2019). Integrating risk management in fintech and traditional financial institutions through AI and machine learning. *Preprints.org*. https://doi.org/10.20944/preprints201407.1609.v1
18. Prabaharan, G., Sankar, S. U., Anusuya, V., Deepthi, K. J., Lotus, R., & Sugumar, R. (2025). Optimized disease prediction in healthcare systems using HDBN and CAEN framework. MethodsX, 103338.
19. Ling, L., Gao, Z., Silas, M. A., Lee, I., & Le Doeuff, E. A. (2019). An AI-based, multi-stage detection system of banking botnets. *arXiv*. https://doi.org/10.1109/ACCESS.2019.2912345
20. Tyagi, N. (2024). Artificial Intelligence in Financial Fraud Detection: A Deep Learning Perspective. International Journal of Computer Technology and Electronics Communication, 7(6), 9726-9732.
21. Karvannan, R. (2025). Scalable cloud architecture for synchronizing pharmacy inventory between central and local systems. International Journal of Information Technology, 6(1), 118–131. https://doi.org/10.34218/IJIT_06_01_011
22. Mula, K. (2025). Financial Inclusion through Digital Payments: How Technology is Bridging the Gap. Journal of Computer Science and Technology Studies, 7(2), 447-457.
23. MohanRaj Alenezi, A. (2024). Cloud security assurance: Strategies for encryption in digital forensic readiness. *arXiv*. https://doi.org/10.1109/ACCESS.2024.3098765
24. Kondra, S., Raghavan, V., & kumar Adari, V. (2025). Beyond Text: Exploring Multimodal BERT Models. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(1), 11764-11769.
25. Reddy, B. V. S., & Sugumar, R. (2025, April). Improving dice-coefficient during COVID 19 lesion extraction in lung CT slice with watershed segmentation compared to active contour. In AIP Conference Proceedings (Vol. 3270, No. 1, p. 020094). AIP Publishing LLC.
26. Wasim Malik, A., Bhatti, D. S., Park, T.-J., Ishtiaq, H. U., Ryou, J.-C., & Kim, K.-I. (2024). Cloud digital forensics: Beyond tools, techniques, and challenges. *Sensors*, 24(2), 433. https://doi.org/10.3390/s24020433
