The rapid deployment of artificial intelligence (AI) across distributed environments has created a need for computing architectures capable of simultaneously supporting low-latency inference, scalable model execution, communication efficiency, privacy, and reliable decision automation. Conventional cloud-centric AI architectures provide substantial computational capacity but can introduce communication delays, bandwidth dependency, privacy exposure, and service disruption risks when real-time decisions must be generated close to data sources. Edge-cloud AI computing addresses these limitations by distributing inference, coordination, and computational workloads across edge devices and cloud infrastructure. This research and review article develops a robust conceptual framework for real-time edge-cloud AI inference and decision automation by synthesizing research on federated learning, communication compression, heterogeneous model aggregation, blockchain-enabled healthcare systems, reinforcement learning, and distributed AI pipelines. The analysis identifies communication efficiency, heterogeneous computational capabilities, privacy preservation, adaptive resource allocation, and resilient inference coordination as the principal architectural requirements. The proposed framework integrates edge-level preprocessing and inference, adaptive communication, cloud-level model coordination, and automated decision orchestration. Findings indicate that compression and knowledge distillation can reduce communication burdens, while heterogeneous aggregation and adaptive learning mechanisms improve the practicality of distributed AI environments. Reinforcement learning further provides a mechanism for dynamic resource and decision optimization. However, the framework remains constrained by device heterogeneity, synchronization overhead, model inconsistency, security requirements, and the trade-off between inference accuracy and latency. The study establishes an integrated theoretical foundation for designing scalable and resilient edge-cloud AI systems capable of supporting real-time intelligent decision processes.

Edge-cloud computing, artificial intelligence, real-time inference, decision automation

M. Beitollahi and N. Lu, “FLAC: Federated learning with autoencoder compression and convergence guarantee,” in Proc. IEEE GLOBECOM Glob. Commun. Conf., 2022, pp. 4589–4594.

L. Cui, X. Su, Y. Zhou, and J. Liu, “Optimal rate adaption in federated learning with compressed communications,” in Proc. IEEE INFOCOM Conf, Comput. Commun., 2022, pp. 1459–1468.

L. Hu, H. Yan, L. Li, Z. Pan, X. Liu, and Z. Zhang, “Mhat: An efficient model-heterogenous aggregation training scheme for federated learning,” Inf. Sci., vol. 560, pp. 493–503, 2021.

A. Lakhan, “Federated-learning based privacy preservation and fraud-enabled blockchain IoMT system for healthcare,” IEEE J. Biomed. Health Inform., vol. 27, no. 2, pp. 664–672, Feb. 2023.

Y. Mao, “SAFARI: Sparsity-enabled federated learning with limited and unreliable communications,” IEEE Trans. Mobile Comput., early access, Jul. 18, 2023, doi: 10.1109/TMC.2023.3296624.

R. Myrzashova, S. H. Alsamhi, A. V. Shvetsov, A. Hawbani, and X. Wei, “Blockchain meets federated learning in healthcare: A systematic review with challenges and opportunities,” IEEE Internet Things J., vol. 10, no. 16, pp. 14418–14437, Aug. 2023.

M. M. Salim and J. H. Park, “Federated learning-based secure electronic health record sharing scheme in medical informatics,” IEEE J. Biomed. Health Inform., vol. 27, no. 2, pp. 617–624, Feb. 2023.

H. Sun, X. Ma, and R. Q. Hu, “Adaptive federated learning with gradient compression in uplink noma,” IEEE Trans. Veh. Technol., vol. 69, no. 12, pp. 16325–16329, Dec. 2020.

J. Wen, “Federated offline reinforcement learning with multimodal data,” IEEE Trans. Consum. Electron., early access, Nov. 08, 2023, doi: 10.1109/TCE.2023.3330943.

C. Wu, F. Wu, L. Lyu, Y. Huang, and X. Xie, “Communication-efficient federated learning via knowledge distillation,” Nature Commun., vol. 13, no. 1, 2022, Art. no. 2032.

M. Xi, “A lightweight reinforcement learning-based real-time path planning method for unmanned aerial vehicles,” IEEE Internet Things J., early access, Jan. 05, 2024, doi: 10.1109/JIOT.2024.3350525.

J. Xu, B. S. Glicksberg, C. Su, P. Walker, J. Bian, and F. Wang, “Federated learning for healthcare informatics,” J. Healthcare Inform. Res., vol. 5, pp. 1–19, 2021.

J. Yang, C. Cheng, S. Xiao, G. Lan, and J. Wen, “High fidelity face-swapping with style convtransformer and latent space selection,” IEEE Trans. Multimedia, vol. 26, pp. 3604–3615, 2024.

Y. Xue, L. Su, and V. K. Lau, “Fedocomp: Two-timescale online gradient compression for over-the-air federated learning,” IEEE Internet Things J., vol. 9, no. 19, pp. 19330–19345, Oct. 2022.

M. Zhang, L. Qu, P. Singh, J. Kalpathy-Cramer, and D. L. Rubin, “SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging,” IEEE J. Biomed. Health Inform., vol. 26, no. 9, pp. 4635–4644, Sep. 2022.

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.

K. Ramamurthy, N. Bellamkonda and N. Amanmadov, "ScalePulse: Combinatorial Llm Framework for Scalability Constraint," SoutheastCon 2026, Huntsville, AL, USA, 2026, pp. 1-6, doi: 10.1109/SoutheastCon63549.2026.11476075

Philip, P. G. (2025). Explainable Artificial Intelligence (XAI) for Project Governance: Improving Transparency and Stakeholder Trust in Automated Project Decision. Journal of Project Management Studies, 2(1), 37–55. https://doi.org/10.58425/jpms.v2i1.570

Kodela, S., Kurada, S. B., Mogili, V. B., & Duggirala, J. (2026, March). Deep Learning-Enhanced Cloud Accounting Model for Real-Time Fraud and Financial Risk Prediction. In 2026 Innovations in Machine, Engineering, and Digital Conference (IMED) (pp. 1-6). IEEE