Data-driven Digital Twin Construction and Terminal Collaborative Control Method of Distribution Network

DOI: https://doi.org/10.62517/jes.202602122

Author(s)

Feng Wang1,*, Kunkun Wang1,*, Pengbo Zhao2, Xikui Li2

Affiliation(s)

1State Grid Shangqiu Power Supply Company, Shangqiu, Henan, China 2Zhengzhou Jingyun Technology Co., Ltd., Zhengzhou, Henan, China *Corresponding Author

Abstract

This paper proposes a data-driven new distribution network digital twin construction and terminal collaborative control method to solve the problem of new distribution network operation control in the context of high proportion of renewable energy access. The research constructs a four-layer digital twin architecture including the physical perception layer, data fusion layer, model construction layer and application service layer, and establishes a technical framework for deep integration of physical systems and virtual space. On this basis, a hybrid modeling method that combines mechanism models and data-driven models is proposed. Through multi-source data fusion and dynamic update mechanisms, high-fidelity digital representation of distribution network operating characteristics is achieved. We further designed a collaborative control mechanism based on digital twin simulation deduction, using a virtual sandbox for control strategy pre-verification and safety verification, achieving closed-loop collaboration of centralized optimization and distributed execution. Research shows that this method can improve the distribution network status sensing accuracy, control decision-making foresight and terminal collaboration efficiency, provide theoretical basis and technical support for enhancing the power grid's ability to absorb distributed energy, operational safety and economy, and has important application value in promoting the construction of new power systems.

Keywords

New Distribution Network; Digital Twin; Data-Driven; Collaborative Control; Hybrid Modeling

References

[1] Habbak, H., Mahmoud, M., Metwally, K., et al. (2023). Load forecasting techniques and their applications in smart grids. Energies, 16(3), 1480. [2] Huang, J., Chen, C., Sun, C., et al. (2023). An integrated risk assessment model for the multi-perspective vulnerability of distribution networks under multi-source heterogeneous data distributions. International Journal of Electrical Power & Energy Systems, 153, 109397. [3] Jia, W., Wang, W., Zhang, Z. (2022). From simple digital twin to complex digital twin Part I: A novel modeling method for multi-scale and multi-scenario digital twin. Advanced Engineering Informatics, 53, 101706. [4] Onaji, I., Tiwari, D., Soulatiantork, P., et al. (2022). Digital twin in manufacturing: conceptual framework and case studies. International journal of computer integrated manufacturing, 35(8), 831-858. [5] Pacheco-Cherrez, D. S., Guillen, D., Mayo-Maldonado, J. C., et al. (2024). Data-driven optimal voltage performance index tracking in active distribution networks. IEEE Transactions on Smart Grid, 15(5), 4804-4818. [6] El Rhatrif, A., Bouihi, B., Mestari, M. (2024). Challenges and limitations of artificial intelligence implementation in modern power grid. Procedia Computer Science, 236, 83-92. [7] Huang, C., Yang, M. (2023). Memory long and short term time series network for ultra-short-term photovoltaic power forecasting. Energy, 279, 127961. [8] Shen, J., Hu, L., Yang, Y., et al. (2025). Real-time update algorithms for digital twin models of distribution network equipment under internet of things and optical imaging technology. Scientific Reports, 15(1), 5910. [9] Yang, C., Cai, B., Wu, Q., et al. (2023). Digital twin-driven fault diagnosis method for composite faults by combining virtual and real data. Journal of Industrial Information Integration, 33, 100469. [10]Wu, Q., Wang, W., Wang, Q., et al. (2022). Digital twin approach for degradation parameters identification of a single-phase DC-AC inverter. In 2022 IEEE Applied Power Electronics Conference and Exposition (APEC) (pp. 1725-1730). IEEE.