Edge-Cloud Collaborative Digital Twin and Hierarchical Intelligent Decision-Making Model for Low-Latency Energy Regulation
DOI:
https://doi.org/10.4108/ew.14340Keywords:
digital twin, edge-cloud collaboration, energy regulation, state estimation, hierarchical decision-making, model predictive controlAbstract
High penetrations of distributed energy resources require energy regulation that combines cloud-level global optimization with edge-level fast response. This paper proposes EC-HDT, a device-edge-cloud hierarchical digital twin in which a lightweight graph-attention-temporal-convolution estimator reconstructs local states under asynchronous, noisy, and missing measurements, while a cloud predictor and model predictive controller perform rolling economic optimization. A five-factor decision weight based on communication latency, information freshness, estimation confidence, operational risk, and edge computational load continuously allocates control authority between edge and cloud, and a quadratic-programming safety layer enforces physical constraints. On the IEEE 33-bus system, EC-HDT achieves a nodal-voltage MAE of 0.0076 p.u., mean/P95 end-to-end latencies of 56.4/89.4 ms, and a 99.2% control success rate; the daily operating cost is 3.51% lower than that of the fixed-fusion scheme. The results indicate that state-aware edge-cloud coordination can improve the latency-economy-safety trade-off in distribution-system regulation.
Downloads
References
[1] Aghazadeh Ardebili A, Zappatore M, Ramadan A I H A, et al. Digital Twins of smart energy systems: A systematic literature review on enablers, design, management and computational challenges[J]. Energy Informatics, 2024, 7: 94.
[2] Bayer D, Pruckner M. A digital twin of a local energy system based on real smart meter data[J]. Energy Informatics, 2023, 6: 8.
[3] Heluany J B, Gkioulos V. A review on digital twins for power generation and distribution[J]. International Journal of Information Security, 2024, 23: 1171-1195.
[4] Djebali S, Guérard G, Taleb I. Survey and insights on digital twins design and smart grid’s applications [J]. Future Generation Computer Systems, 2024, 153: 234-248.
[5] Das O, Zafar M H, Sanfilippo F, et al. Advancements in digital twin technology and machine learning for energy systems: A comprehensive review of applications in smart grids, renewable energy, and electric vehicle optimization [J]. Energy Conversion and Management: X, 2024, 24: 100715.
[6] Sifat M M H, Das S K, Choudhury S M. Design, development, and optimization of a conceptual framework of digital twin electric grid using systems engineering approach [J]. Electric Power Systems Research, 2024, 226: 109958.
[7] Krishnan S B, Tan K T, Zhang W. Cognitive digital twin for microgrid: A real-world study for intelligent energy management and optimization [J]. IEEE Internet Computing, 2025, 29(1): 39-47.
[8] Dellaly M, Skander-Mustapha S, Slama-Belkhodja I. A digital twin model-based approach to cost optimization of residential community microgrids [J]. Global Energy Interconnection, 2024, 7(1): 82-93.
[9] Thaler B, Posch S, Wimmer A, Pirker G. Hybrid model predictive control of renewable microgrids and seasonal hydrogen storage [J]. International Journal of Hydrogen Energy, 2023, 48: 36256-36273.
[10] Kumar P, Kumar R, Aljuhani A, et al. Digital twin-driven SDN for smart grid: A deep learning integrated blockchain for cybersecurity [J]. Solar Energy, 2023, 263: 111921.
[11] Yuan H, Xiao H, Shi Y, et al. ELECT: Energy-efficient intelligent edge-cloud collaboration for remote IoT services [J]. Future Generation Computer Systems, 2023, 147: 179-194.
[12] Li H, Yang Y, Liu Y, Pei W. Federated dueling DQN based microgrid energy management strategy in edge-cloud computing environment [J]. Sustainable Energy, Grids and Networks, 2024, 38: 101329.
[13] Habib M, Bollin E, Wang Q. Edge-based solution for battery energy management system: Investigating the integration capability into the building automation system [J]. Journal of Energy Storage, 2023, 72: 108479.
[14] Kundacina O, Cosovic M, Miskovic D, Vukobratovic D. Graph neural networks on factor graphs for robust, fast, and scalable linear state estimation with PMUs [J]. Sustainable Energy, Grids and Networks, 2023, 34: 101056.
[15] Ngo Q H, Nguyen B L H, Vu T V, et al. Physics-informed graphical neural network for power system state estimation [J]. Applied Energy, 2024, 358: 122602.
[16] Cibaku E, Gama F, Park S W. Boosting efficiency in state estimation of power systems by leveraging attention mechanism [J]. Energy and AI, 2024, 16: 100369.
[17] Yu J J Q, Wei X. ST-AGNet: Dynamic power system state prediction with spatial-temporal attention graph-based network [J]. Applied Energy, 2024, 365: 123252.
[18] Raghuvamsi Y, Teeparthi K, Kumar D M V, et al. Distribution system state estimation using physics-guided deep learning approach [J]. Electric Power Systems Research, 2024, 236: 110922.
[19] Casagrande V, Ferianc M, Rodrigues M R D, Boem F. Online end-to-end learning-based predictive control for microgrid energy management [J]. IEEE Transactions on Control Systems Technology, 2025, 33: 1-16.
[20] Nassereddine K, Turzynski M, Bielokha H, Strzelecki R. Simulation of energy management system using model predictive control in AC/DC microgrid [J]. Scientific Reports, 2025, 15: 5388.
[21] Lim S, Lee J, Lee S. Model predictive control-based energy management system for cooperative optimization of grid-connected microgrids [J]. Energies, 2025, 18(7): 1696.
[22] Kfouri M, et al. A resilient deep learning approach for state estimation in distribution grids with distributed generation [J]. International Transactions on Electrical Energy Systems, 2025: 2734170.
[23] Segura F, Andújar J M, et al. Methodology for energy management strategies design based on predictive control techniques for smart grids [J]. Applied Energy, 2023, 351: 121809.
[24] Sepehrzad R, Ghafourian J, Hedayatnia A, Al-Durra A, Khooban M H. Experimental and developed DC microgrid energy management integrated with battery energy storage based on multiple dynamic matrix model predictive control [J]. Journal of Energy Storage, 2023, 74: 109282.
[25] Roudnil R, et al. Energy management of microgrids: An MPC-based techno-economic optimisation for RES integration and ESS utilization [J]. IET Generation, Transmission & Distribution, 2025, 19: 70082.
[26] Habibi S, Effatnejad R, Hedayati M, et al. Stochastic energy management of a microgrid incorporating two-point estimation method, mobile storage, and fuzzy multi-objective enhanced grey wolf optimizer [J]. Scientific Reports, 2024, 14: 1667.
[27] Mathur A, Kumari R, Meena V P, et al. Data-driven optimization for microgrid control under distributed energy resource variability [J]. Scientific Reports, 2024, 14: 10806.
[28] Keshta H E, Hassaballah E G, Ali A A, et al. Multi-level optimal energy management strategy for a grid tied microgrid considering uncertainty in weather conditions and load [J]. Scientific Reports, 2024, 14: 10059.
[29] Ahmed D, Ebeed M, Kamel S, et al. An enhanced jellyfish search optimizer for stochastic energy management of multi-microgrids with wind turbines, biomass and PV generation systems considering uncertainty [J]. Scientific Reports, 2024, 14: 15558.
[30] Elazab R, Abo Dahab A, Abo Adma M, et al. Reviewing the frontier: Modeling and energy management strategies for sustainable 100% renewable microgrids [J]. Discover Applied Sciences, 2024, 6: 168.
[31] Moshtagh S, Azimian B, Golgol M, Pal A. Topology-aware graph neural network-based state estimation for PMU-unobservable power systems [J]. IEEE Transactions on Power Systems, 2025, 40(6): 4547-4560.
[32] Chen Q, Bu S, Wang H, Lei C. Real-time multi-stability risk assessment and visualization of power systems: A graph neural network-based method [J]. IEEE Transactions on Power Systems, 2025, 40(4): 2955-2968.
[33] Gorka J, Hsu T, Li W, et al. Cascading blackout severity prediction with statistically-augmented graph neural networks [J]. Electric Power Systems Research, 2024, 234: 110738.
[34] Solheim Ø R, Presthus G S, Høverstad B A, Korpås M. Visualizing graph neural networks in order to learn general concepts in power systems [J]. Electric Power Systems Research, 2024, 237: 110717.
[35] Li H, et al. Federated deep reinforcement learning for varying-scale multi-energy microgrids energy management considering comprehensive security [J]. Applied Energy, 2025, 380: 125072.
[36] Su Z, Zheng G, Hu M, et al. Short-term load forecasting of regional integrated energy system based on spatio-temporal convolutional graph neural network [J]. Electric Power Systems Research, 2024, 232: 110427.
[37] Yang M, Qiu G, Liu T, et al. Probabilistic power flow based on physics-guided graph neural networks [J]. Electric Power Systems Research, 2024, 235: 110864.
[38] Wu P, Mei X. Microgrids energy management considering net-zero energy concept: The role of renewable energy landscaping design and IoT modeling in digital twin realistic simulator [J]. Sustainable Energy Technologies and Assessments, 2024, 63: 103621.
[39] Kumar M, Tyagi B. A machine learning-based stochastic optimal energy management framework for a renewable energy-assisted isolated microgrid system [J]. Energy Sources, Part B: Economics, Planning, and Policy, 2024, 19(1): 2294869.
[40] Tan M, Wang L, et al. Federated reinforcement learning for smart and privacy-preserving energy management of residential microgrids clusters [J]. Engineering Applications of Artificial Intelligence, 2025, 139: 109579.
[41] Khan N H, Wang Y, Jamal R, et al. A novel modified artificial rabbit optimization for stochastic energy management of a grid-connected microgrid: A case study in China [J]. Energy Reports, 2024, 11: 5436-5455.
[42] Jena C J, Ray P K. Power allocation scheme for grid interactive microgrid with hybrid energy storage system using model predictive control [J]. Journal of Energy Storage, 2024, 81: 110401.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Xiaohua Zou
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.
