Proxy-Cost-Aware Explainable Graph Neural Network for Multi-Domain O&M Decision Support in Digital Twin-Enabled Smart-City IoT Systems
DOI:
https://doi.org/10.4108/ew.14036Keywords:
smart-city IoT, digital twin, explainable graph neural network, multi-domain O&M, proxy operational costAbstract
INTRODUCTION: Digital twin-enabled smart-city IoT systems may interact with interconnected transportation, parking, environmental, communication, and edge-computing infrastructures. Failures or congestion in one domain may propagate across service chains and increase operational burden, yet existing spatiotemporal graph models rarely represent cost semantics, risk propagation, and maintenance actions jointly.
OBJECTIVES: This study develops a cost-aware explainable graph neural network for multi-domain operation and maintenance decision support, with emphasis on proxy-cost prediction, risk identification, rule-based action ranking, and interpretable attribution.
METHODS: A multi-layer digital twin graph integrates sensing, communication, computing, service, maintenance, and proxy-cost nodes. A state–risk–cost three-channel propagation mechanism separately models operational states, abnormal-risk diffusion, and cost-impact transmission. Rule-based graph interventions, including maintenance, task migration, link switching, and sampling adjustment, are used to estimate action-induced proxy-cost changes. CityPulse is used as a heterogeneous multi-domain proxy scenario, while Caltrans PeMS provides a homogeneous traffic-sensor reference. Performance is evaluated using MAE, F1, NDCG@5, and Fidelity, where NDCG@5 measures consistency with predefined action-ranking rules.
RESULTS: On CityPulse, the proposed method achieved lower MAE and higher NDCG@5 and Fidelity than the strongest corresponding baselines, although its F1 was slightly lower than STAEformer. On PeMS, it achieved the highest Fidelity but remained below the best traffic-specific models in MAE, F1, and NDCG@5. Ablation results showed the respective contributions of cost nodes, explicit three-channel propagation, rule-based intervention evaluation, and explanation constraints.
CONCLUSION: The method is more effective for heterogeneous multi-domain O&M scenarios than for homogeneous traffic forecasting. Because both datasets provide proxy rather than real financial, energy-system, and intervention records, the results support proxy-based methodological validation but do not constitute direct physical-energy-system validation or evidence of realized cost savings and causal intervention effectiveness.
Downloads
References
[1] Choudhary A. Internet of Things: a comprehensive overview, architectures, applications, simulation tools, challenges and future directions. Discover Internet of Things. 2024;4(1):31.
[2] Alourani A, Alam M, Ali A, Khan IR, Samal CK. Hybrid AI-IoT Framework with Digital Twin Integration for Predictive Urban Infrastructure Management in Smart Cities. CMC-COMPUTERS MATERIALS & CONTINUA. 2025;86(1).
[3] Wang Q, Li W, Yu Z, Abbasi Q, Imran M, Ansari S, et al. An overview of emergency communication networks. Remote Sensing. 2023;15(6):1595.
[4] Sowmya R, Nandhini M, Priyanga M. Enhancing Edge Node Resilience through SDN-Driven Proactive Failure Management. In: 2024 IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE). IEEE; 2024. p. 15-20.
[5] Jayadharshini P, Santhiya S, Vasuki C, Vanaja T, Archanaa S, Samyuktha K. The Impact of Digital Twin in Industry 4.0 Using Graph Neural Network: An Approach to Explainability in the Manufacturing Industry. In: Distributed Deep Learning and Explainable AI (XAI) in Industry 4.0. Cham: Springer Nature Switzerland; 2025. p. 185-212.
[6] Yu P, Zhang J, Fang H, Li W, Feng L, Zhou F, et al. Digital twin driven service self-healing with graph neural networks in 6G edge networks. IEEE Journal on Selected Areas in Communications. 2023;41(11):3607-3623.
[7] Ngo DT, Aouedi O, Piamrat K, Hassan T, Raipin-Parvédy P. Empowering digital twin for future networks with graph neural networks: Overview, enabling technologies, challenges, and opportunities. Future Internet. 2023;15(12):377.
[8] Mahmoudi Rashid S. Graph Neural Network-Based Digital Twin for Cyber-Resilient and Predictive Teleoperation Systems. Journal of AI and Data Mining. 2026;14(1):1-12.
[9] Guo K, Chen J, Dong P, Zou T, Zhu J, Huang X, et al. Dtfl: A digital twin-assisted graph neural network approach for service function chains failure localization. IEEE Transactions on Cloud Computing. 2023;11(4):3573-3590.
[10] Dahmane WM, Ouchani S, Bouarfa H. Smart cities services and solutions: A systematic review. Data and Information Management. 2025;9(2):100087.
[11] Zaman M, Puryear N, Abdelwahed S, Zohrabi N. A review of IoT-based smart city development and management. Smart Cities. 2024;7(3):1462-1501.
[12] Trigka M, Dritsas E. Edge and cloud computing in smart cities. Future Internet. 2025;17(3):118.
[13] Banerjee A, Costa B, Forkan ARM, Kang YB, Marti F, McCarthy C, et al. 5G enabled smart cities: A real-world evaluation and analysis of 5G using a pilot smart city application. Internet of Things. 2024;28:101326.
[14] Nikpour M, Yousefi PB, Jafarzadeh H, Danesh K, Shomali R, Asadi S, et al. Intelligent energy management with iot framework in smart cities using intelligent analysis: An application of machine learning methods for complex networks and systems. Journal of Network and Computer Applications. 2025;235:104089.
[15] Fereira RJ, Ranaweera C, Lee K, Schneider JG. Energy efficient resource management for real-time IoT applications. Internet of Things. 2025;30:101515.
[16] Fan G, Sabri AQM, Rahman SSA, Pan L, Rahardja S. Emerging Trends in Graph Neural Networks for Traffic Flow Prediction: A Survey. Archives of Computational Methods in Engineering. 2025;32(8):4811-4855.
[17] Hu N, Zhang D, Xie K, Liang W, Li KC, Zomaya AY. Dynamic multi-scale spatial–temporal graph convolutional network for traffic flow prediction. Future Generation Computer Systems. 2024;158:323-332.
[18] Qadir MA, Naeem M, Ejaz W. Digital twin-assisted multi-layer networks for low-latency and energy-efficient communication. Computer Communications. 2025;108219.
[19] Rostami M, Goli-Bidgoli S. An overview of QoS-aware load balancing techniques in SDN-based IoT networks. Journal of Cloud Computing. 2024;13(1):89.
[20] Zhang Z, Liu Y, Peng Z, Chen M, Xu D, Cui S. Digital twin-assisted data-driven optimization for reliable edge caching in wireless networks. IEEE Journal on Selected Areas in Communications. 2024;42(11):3306-3320.
[21] Zhang Z, Peng Z, Yu H, Chen M, Liu Y. Digital network twins for next-generation wireless: Creation, optimization, and challenges. IEEE Network. 2025.
[22] Zhang Z, Chen M, Yang Z, Liu Y. Mapping wireless networks into digital reality through joint vertical and horizontal learning. In: 2024 IFIP Networking Conference (IFIP Networking). IEEE; 2024. p. 359-367.
[23] Mbasso WF, Harrison A, Dagal I, Jangir P, Khishe M, Kotb H, et al. Digital twins in renewable energy systems: A comprehensive review of concepts, applications, and future directions. Energy Strategy Reviews. 2025;61:101814.
[24] Ba L, Tangour F, El Abbassi I, Absi R. Analysis of digital twin applications in energy efficiency: A systematic review. Sustainability. 2025;17(8):3560.
[25] Materwala H, Ismail L, Shubair RM, Buyya R. Energy-SLA-aware genetic algorithm for edge–cloud integrated computation offloading in vehicular networks. Future Generation Computer Systems. 2022;135:205-222.
[26] Serra G, Niepert M. L2XGNN: learning to explain graph neural networks. Machine Learning. 2024;113(9):6787-6809.
[27] Yousefzadeh N, Sengupta R, Dilmore J, Ranka S. TGDT: A Temporal Graph-based Digital Twin for Urban Traffic Corridors. arXiv preprint arXiv:2504.18008. 2025.
[28] Aykurt K, Stephan M, Ayvasik S, Zerwas J, Kellerer W. Digital Twin Opportunities with Leveraging Graph Neural Networks on Real Network Data. ITU Journal on Future and Evolving Technologies (ITU J-FET). 2024.
[29] Ying R, Bourgeois D, You J, Zitnik M, Leskovec J. Gnnexplainer: Generating explanations for graph neural networks. Advances in Neural Information Processing Systems. 2019;32:9240-9251.
[30] Li Y, Yu R, Shahabi C, Liu Y. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In: Proceedings of the 6th International Conference on Learning Representations (ICLR 2018). 2018.
[31] Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018). 2018. p. 3634-3640.
[32] Jiang J, Han C, Zhao WX, Wang J. Pdformer: Propagation delay-aware dynamic long-range transformer for traffic flow prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 37, No. 4. 2023. p. 4365-4373.
[33] Jiang R, Wang Z, Yong J, Jeph P, Chen Q, Kobayashi Y, et al. Spatio-temporal meta-graph learning for traffic forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 37, No. 7. 2023. p. 8078-8086.
[34] Liu H, Dong Z, Jiang R, Deng J, Deng J, Chen Q, et al. Spatio-temporal adaptive embedding makes vanilla transformer sota for traffic forecasting. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2023. p. 4125-4129.
[35] Wang X, Ji H, Shi C, Wang B, Ye Y, Cui P, et al. Heterogeneous graph attention network. In: The World Wide Web Conference. 2019. p. 2022-2032.
[36] Hu Z, Dong Y, Wang K, Sun Y. Heterogeneous graph transformer. In: Proceedings of the Web Conference 2020. 2020. p. 2704-2710.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fujing Qin
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
