A Scalable Architecture for AI-Enabled, Data-Driven Cloud Operations with Integrated Identity and Access Governance

DOI

10.2991/978-94-6239-654-8_70How to use a DOI?

Keywords

Deep reinforcement learning; Zero Trust security framework; Graph Neural Networks (GNNs); Proximal Policy Optimization (PPO); cloud computing

Abstract

In the cloud computing model has become main support and helpful for modern digital services, that makes more scalability and data-intensive application across different domains. But due to its fast and speed growth the risk-complexity also increases the amount of traditional methods often failure to provide more security and safety. The Static of non-changeable data resource setup, rule-based monitoring, and conventional identity access management model struggle to adapt to change dynamic work frames or workloads, large-scale data, and evolving security and safety of malware threat attacks. Existing past method of cloud operation systems are largely increase in reactive, which results as an output of delay fault detection, inefficient resource utilization, increased the amount of operational costs, and limited visibility into identity-related risks. Furthermore, traditional role-based access control mechanisms lack continuous complex risk assessment and failure to perform effectively in distributed and multi-cloud environment. To overcome these challenges, this paper proposes a scalable AI-enabled, data-driven cloud operations architecture with integrated identity and access management. The proposed system is designed with transformer-based time series prediction models for proactive workload prediction, self-supervised anomaly detection using masked auto coders for intelligent monitoring, and deep reinforcement learning algorithms Proximal Policy Optimization for autonomous resource allocation and optimization. In addition, a Zero Trust security and safety framework is implemented using continuous complex risk-adaptive control and graph bases identity analysis powered Graph Neural Networks to identify anomalous access behaviour and privilege escalation. Experimental results show that the proposed architecture outperforms existing cloud management and identity governance approaches in terms of operational efficiency, anomaly detection accuracy, access control precision, and cost-performance optimization. The proposed framework also shows improved scalability and faster response times under dynamic workload conditions. The architecture is highly suitable for future applications including autonomous cloud operations, safe enterprise systems, large-scale multi-cloud environments, and next-generation intelligent infrastructure, which provides a strong and adaptable foundation for secure and efficient cloud management.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Pramod Gannavarapu
AU  - Santosh Durgam
AU  - Sridhar Rangu
PY  - 2026
DA  - 2026/04/24
TI  - A Scalable Architecture for AI-Enabled, Data-Driven Cloud Operations with Integrated Identity and Access Governance
BT  - Proceedings of the Global Conference on Sustainable Energy Systems, Smart Electronics and Intelligent Computing (GCSESEIC 2025)
PB  - Atlantis Press
SP  - 901
EP  - 914
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-654-8_70
DO  - 10.2991/978-94-6239-654-8_70
ID  - Gannavarapu2026
ER  -