eISSN: 2978-3739 editor@irjernet.com
All Journals
Submit your article

Frontiers in Emerging Multidisciplinary Sciences

Open Access Peer Review International
Open Access

Edge-to-Cloud AI Inference: A Scalable Architecture for Real-Time Intelligent Decision Systems

DOI
PDF
Dr. Vikram Rao 1 Dr. Neha Kapoor 1
4 Department of Artificial Intelligence and Machine Learning India
4 Department of Computer Science and Artificial Intelligence India

Abstract

The rapid integration of artificial intelligence (AI), Internet of Things (IoT), and distributed computing has created a requirement for inference architectures capable of processing heterogeneous data with low latency, security, scalability, and operational efficiency. Conventional cloud-centric AI pipelines provide substantial computational resources but can introduce communication delays, bandwidth dependence, privacy concerns, and centralized points of failure. Conversely, fully edge-based inference reduces transmission latency but is constrained by limited computational, storage, and energy resources. This paper examines an edge-to-cloud AI inference architecture designed to distribute intelligent decision-making across sensing, edge, intermediate processing, and cloud layers. A research-driven synthesis of existing work on Internet of Medical Things (IoMT), edge-cloud AI, federated learning, secure routing, privacy-preserving data fusion, and decentralized trust management is used to formulate the architectural framework. The methodology integrates adaptive workload placement, secure communication, privacy-aware learning, and hierarchical inference. The analysis indicates that edge-to-cloud inference can improve responsiveness by processing latency-sensitive workloads close to data sources while retaining cloud resources for computationally intensive model operations, historical analytics, and global coordination. The proposed conceptual architecture also addresses security and privacy requirements through decentralized trust, federated learning, and privacy-enhanced data processing. The study identifies workload orchestration, heterogeneous edge capabilities, model synchronization, security overhead, and energy consumption as major limitations. The findings position edge-to-cloud inference as a practical architecture for real-time intelligent systems in healthcare, smart environments, and connected infrastructure.

How to Cite

Dr. Vikram Rao, & Dr. Neha Kapoor. (2026). Edge-to-Cloud AI Inference: A Scalable Architecture for Real-Time Intelligent Decision Systems. Frontiers in Emerging Multidisciplinary Sciences, 3(08), 76–82. Retrieved from https://irjernet.com/index.php/fems/article/view/500
⬇ Endnote/Zotero/Mendeley (RIS) ⬇ BibTeX

References

M. Ebrahimi, M. S. Haghighi, A. Jolfaei, N. Shamaeian, and M. H. Tadayon, “A secure and decentralized trust management scheme for Smart health systems,” IEEE J. Biomed. Health Inform., vol. 26, no. 5, pp. 1961–1968, May 2022.
G. J. Joyia, R. M. Liaqat, A. Farooq, and S. Rehman, “Internet of medical things (IoMT): Applications, benefits and future challenges in healthcare domain,” J. Commun., vol. 12, no. 4, pp. 240–247, 2017.
S. More, “Security assured CNN-based model for reconstruction of medical images on the internet of healthcare things,” IEEE Access, vol. 8, pp. 126333–126346, 2020.
J. Liu, “A comprehensive privacy-preserving federated learning scheme with secure authentication and aggregation for internet of medical things,” IEEE J. Biomed. Health Inform., early access, Aug. 23, 2023, doi: 10.1109/JBHI.2023.3304361.
C. Chakraborty, A. Banerjee, M. H. Kolekar, L. Garg, and B. Chakraborty, Eds. Internet of Things for Healthcare Technologies. Springer, 2021.
A. Balasundaram, S. Routray, A. V. Prabu, P. Krishnan, P. P. Malla, and M. Maiti, “Internet of Things (IoT) based smart healthcare system for efficient diagnostics of health parameters of patients in emergency care,” IEEE Internet Things J., 2023.
H. Lin, S. Garg, J. Hu, X. Wang, M. Jalil Piran, and M. S. Hossain, “Privacy-enhanced data fusion for COVID-19 applications in intelligent internet of medical things,” IEEE Internet Things J., vol. 8, no. 21, pp. 15683–15693, Nov. 2021.
P. Krishnan, A. V. Prabu, S. Loganathan, S. Routray, U. Ghosh, and M. AL-Numay, “Analyzing and managing various energy-related environmental factors for providing personalized IoT services for smart buildings in smart environment,” Sustainability, vol. 15, no. 8, 2023, Art. no. 6548.
S. Rajasoundaran, “Secure routing with multi-watchdog construction using deep particle convolutional model for IoT based 5G wireless sensor networks,” Comput. Commun., vol. 187, pp. 71–82, 2022.
J. Srivastava and S. Routray, “AI enabled internet of medical things framework for smart healthcare,” in Proc Int. Conf. Innov. Intell. Comput. Commun., Cham, Dec. 2022, pp. 30–46.
L. Sun, X. Jiang, H. Ren, and Y. Guo, “Edge-cloud computing and artificial intelligence in internet of medical things: Architecture, technology and application,” IEEE Access, vol. 8, pp. 101079–101092, 2020.
F. Ullah, G. Srivastava, H. Xiao, S. Ullah, J. C. W. Lin, and Y. Zhao, “A scalable federated learning approach for collaborative smart healthcare systems with intermittent clients using medical imaging,” IEEE J. Biomed. Health Inform., early access, Jun. 06, 2023, doi: 10.1109/JBHI.2023.3282955.
K. Kumar, "Edge-to-Cloud AI Inference Pipelines: A Resilient Architecture for Real-Time Decision Systems," 2025 International Conference on Computer and Applications (ICCA), Bahrain, Bahrain, 2025, pp. 1-6, doi: 10.1109/ICCA66035.2025.11430905.