AI-Driven Cloud–Edge Infrastructure for Resilient Smart Water Systems in the United States
DOI:
https://doi.org/10.66280/ijair.v1i1.78Abstract
Urban water networks in the United States are increasingly instrumented with pressure, flow, and water-quality sensors, yet operational response remains constrained by fragmented supervisory systems and brittle communication paths. This paper presents AquaEdge-AI, an AI-driven cloud–edge infrastructure designed for resilient smart water operations under normal conditions and during disruptions such as sensor dropouts, network congestion, and pump sta- tion failures. The proposed design combines (i) edge-side spatiotemporal anomaly detection with uncertainty-aware inference, (ii) cloud-level cross-district coordination for demand forecasting and control recommendation, and (iii) a resilience orchestration layer that degrades gracefully when connectivity is impaired.
We evaluate the system using a multi-source dataset constructed from U.S. municipal teleme- try, synthetic-but-physics-consistent hydraulic events, and weather-demand covariates spanning
18 months and 42 district metered areas (DMAs). Experimental results show that AquaEdge-AI improves event detection F1 from 0.872 (best baseline) to 0.928, reduces median control-loop latency from 412 ms to 146 ms, and increases service continuity during communication outages by 19.7%. Under peak demand perturbations, the architecture sustains 2.4× higher inference throughput than cloud-only deployment while preserving pressure compliance. Ablation studies confirm that edge autonomy and uncertainty gating contribute the largest gains, with additive improvements in both robustness and false-alarm suppression.
The study demonstrates that resilient cloud–edge intelligence is not only computationally efficient but operationally meaningful for U.S. utilities facing aging infrastructure, climate vari- ability, and cybersecurity risk. The proposed framework and experimental protocol provide a reproducible blueprint for next-generation smart water platforms.
References
1.L. A. Rossman, EPANET 2: Users Manual. Cincinnati, OH, USA: U.S. Environmental Pro- tection Agency, 2000.
2.J. A. Stankovic, “Research directions for the Internet of Things,” IEEE Internet of Things Journal, vol. 1, no. 1, pp. 3–9, Feb. 2014.
3.W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, “Edge computing: Vision and challenges,” IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, Oct. 2016.
4.A. Zanella, N. Bui, A. Castellani, L. Vangelista, and M. Zorzi, “Internet of Things for smart cities,” IEEE Internet of Things Journal, vol. 1, no. 1, pp. 22–32, Feb. 2014.
5.R. Taormina, S. Galelli, N. O. Tippenhauer, E. Salomons, and A. Ostfeld, “Characterizing cyber-physical attacks on water distribution systems,” Journal of Water Resources Planning and Management, vol. 143, no. 5, 2017.
6.E. Q. Shahra, W. Wu, S. Basurra, and A. Aneiba, “Intelligent edge-cloud framework for water quality monitoring in water distribution system,” Water, vol. 16, no. 2, p. 196, 2024, doi: 10.3390/w16020196.
7.M. Boujelben, Z. Benmessaoud, M. Abid, and M. Elleuchi, “An efficient system for water leak detection and localization based on IoT and lightweight deep learning,” Internet of Things, vol. 24, p. 100995, 2023, doi: 10.1016/j.iot.2023.100995.
8.R. Yan and J. J. Huang, “Confident learning-based Gaussian mixture model for leakage detection in water distribution networks,” Water Research, vol. 247, p. 120773, 2023, doi: 10.1016/j.watres.2023.120773.
9.S. Jun, D. Jung, and K. Lansey, “Three-dimensional convolutional neural network for leak detection and localization in smart water distribution systems,” Water Research X, vol. 25, p. 100264, 2024, doi: 10.1016/j.wroa.2024.100264.
10.M. Adraoui, R. Azmi, J. Chenal, E. B. Diop, S. A. E. Abdem, I. Serbouti, M. Hlal, and M. Bounabi, “A two-phase approach for leak detection and localization in water distribution sys- tems using wavelet decomposition and machine learning,” Computers & Industrial Engineering, vol. 197, p. 110534, 2024, doi: 10.1016/j.cie.2024.110534.
11.Zhou, D. (2026). AI-Driven Hybrid SAST–DAST–SCA–IAST Framework for Risk-Based Vulnerability Prioritization in Microservice Architectures.
12.Liu, T. (2026). Volatility Forecasting and Early-Warning Market Stress Detection: A Leakage-Safe Evaluation with Tree Ensembles and Transformers.
13.Li, H., & Liu, T. (2023). Portfolio optimization based on the LSTM forecasting model. In Proceedings of the 2nd International Conference on Financial Technology and Business Analysis (Vol. 48, No. 1, pp. 97-106).
14.Liu, T. (2022, December). Financial Constraint’Impact on Firms’ ESG Rating Based on Chinese Stock Market. In 2022 4th International Conference on Economic Management and Cultural Industry (ICEMCI 2022) (pp. 1085-1095). Atlantis Press.
15.Yi, X. (2026). Trusted AI Commercialization Infrastructure for SMBs: A Unified Multi-Tenant Architecture Integrating Incentive Systems, Content Governance, and Standardized Recommendation APIs.
16.Yue, Y., Khanal, A., Lyu, T., Weissman, S., & Liang, C. (2025, May). EHR Phenotyping Methods for Measuring Treatment Adherence Among People Living With HIV in All of Us: Towards Disparities and Inequalities in HIV Care Continuum. In AMIA Annual Symposium Proceedings (Vol. 2024, p. 1294).
17.Yi, X. (2026). Privacy-Enhanced Ad Targeting for Social E-Commerce: A Federated Learning Framework with Zero-Knowledge Verification for Creator Monetization. Frontiers in Business and Finance, 3(1), 102-113.
18.Chang, C., Fu, M., Chen, X., Feng, S., Zhang, M., Zhou, X., ... & Liu, Z. (2025, November). Research on PDU-Net Lung Nodule Segmentation Algorithm Based on Path Aggregation and Dual Attention. In 2025 4th International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) (pp. 1897-1900). IEEE.
19.Liu, T. (2026). PCA-APT Stress Index for Market Drawdowns.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
