Research on Data Recovery for the Power Grid Industry Based on Diffusion Models

YAN Yandong; LI Chenxi; LI Shijie; YANG Yang; GE Yuhao; HUANG Yu

doi:10.11999/JEIT250435

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2025 >

YAN Yandong, LI Chenxi, LI Shijie, YANG Yang, GE Yuhao, HUANG Yu. Research on Data Recovery for the Power Grid Industry Based on Diffusion Models[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250435

Citation:

YAN Yandong, LI Chenxi, LI Shijie, YANG Yang, GE Yuhao, HUANG Yu. Research on Data Recovery for the Power Grid Industry Based on Diffusion Models[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250435

Citation:

PDF( 0 KB)

Research on Data Recovery for the Power Grid Industry Based on Diffusion Models

doi: 10.11999/JEIT250435 cstr: 32379.14.JEIT250435

1.
School of Computer Science, Peking University, Beijing 100871, China
2.
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
3.
China Southern Power Grid (csg), Guangzhou 510000, China
4.
China Southern Power Grid Digital Platform Technology, Guangzhou 510000, China
5.
National Engineering Research Center for Software Engineering, Peking University, Beijing 100871, China

Funds: China Southern Power Grid (csg) Science and Technology Item (ZBKJXM20240174)

Received Date: 2025-05-20
Accepted Date: 2025-11-03
Rev Recd Date: 2025-11-03

Available Online: 2025-11-12

Abstract

Abstract

Objective Smart grid construction drives modern power systems. As a key link connecting the main grid to end-users, distribution networks rely on data management/analysis for stability, power quality, and efficiency—yet generate massive multi-source heterogeneous data (user consumption, real-time meteorology, equipment status, marketing info). This data often becomes incomplete during collection/transmission due to noise, sensor failures, aging, or bad weather. Missing data impairs real-time monitoring and critical tasks (load forecasting, fault diagnosis, health assessment, O&M decisions), while traditional methods (mean/regression imputation) and generative models (GANs, VAEs) fail to capture grid data’s temporal dependencies and complex distributions, limiting accuracy. Thus, this research aims to develop a novel diffusion model-based data augmentation method for distribution networks, to effectively recover missing data, preserve its semantic/statistical integrity, and boost data utility for smart grid stability and efficiency. Methods This paper proposes a novel power grid data augmentation method based on diffusion models. The core of this method involves mapping input Gaussian noise to the target distribution space of the missing data, enabling the restoration of this data in accordance with its original underlying distribution patterns. Furthermore, to minimize the semantic discrepancy between the recovered data and the actual data, the proposed approach integrates time-series sequence embeddings as conditional information. This conditional input guides and optimizes the diffusion generation process, ensuring a more contextually accurate imputation. Results and Discussions Experimental results demonstrate that the proposed diffusion model-based data augmentation technique achieves state-of-the-art accuracy in recovering missing power grid data when compared to conventional methods. This superior performance highlights the method's capability to significantly enhance the completeness and reliability of datasets crucial for various analytical applications and operational decision-making in smart grids. Conclusions This study successfully introduces and validates a diffusion model-based data augmentation method tailored for addressing data missingness in power distribution networks. Unlike traditional data restoration methods and conventional generative models that struggle to capture the temporal dependencies and complex distribution characteristics of grid data, this method effectively leverages temporal sequence information as a conditional guide, which not only enables accurate imputation of missing values but also well preserves the semantic integrity and statistical consistency of the original data. By solving the long-standing problem of low accuracy in restoring missing distribution network data, this method offers a robust and advanced solution for improving data quality, thereby providing solid technical support for the enhanced stability and efficiency of smart grid operations.
- Power Industry,
- Power Grid Fault Diagnosis,
- Power Grid Operation and Maintenance,
- Data Recovery,
- Diffusion Model

FullText(HTML)

References(26)

References

[1]	秀春男. 张家口公司解锁智慧电网运维密码[J]. 华北电业, 2025(2): 12–13. XIU Chunnan. Zhangjiakou Company unlocks the code of smart grid operation and maintenance[J]. North China Power, 2025(2): 12–13. (查阅网上资料, 未找到本条文献英文翻译, 请确认).
[2]	黄耀辉, 何浩然, 陈绍铭, 等. 基于深度学习的电力系统数据质量提升研究综述[J]. 电力系统自动化, 2023, 47(15): 175–187. doi: 10.7500/AEPS20221227007. (查阅网上资料,未找到本条文献信息,请确认). HUANG Yaohui, HE Haoran, CHEN Shaoming, et al. Review of research on improving power system data quality based on deep learning[J]. Automation of Electric Power Systems, 2023, 47(15): 175–187. doi: 10.7500/AEPS20221227007.
[3]	李欣, 吴凌霄, 李新宇, 等. 基于缺失数据插补和改进集成策略的电力系统暂态稳定评估[J]. 电力系统及其自动化学报, 2025, 37(8): 38–48. doi: 10.19635/j.cnki.csu-epsa.001525. LI Xin, WU Lingxiao, LI Xinyu, et al. Transient stability assessment of power system based on missing data imputation and improved ensemble strategy[J]. Proceedings of the CSU-EPSA, 2025, 37(8): 38–48. doi: 10.19635/j.cnki.csu-epsa.001525.
[4]	钟尧, 刘清蝉, 李昕泓, 等. 计及非负和低秩特性的用电数据缺失值插补[J]. 重庆大学学报, 2025, 48(9): 1–11. doi: 10.11835/j.issn.1000-582X.2024.214. ZHONG Yao, LIU Qingchan, LI Xinhong, et al. Complete electricity data reconstruction based on weighted nonnegative matrix factorization[J]. Journal of Chongqing University, 2025, 48(9): 1–11. doi: 10.11835/j.issn.1000-582X.2024.214.
[5]	马燕玲. 基于线性回归法的电力计量数据缺失重构研究[J]. 电气技术与经济, 2025(2): 46–47, 54. doi: 10.3969/j.issn.1673-8845.2025.02.016. MA Yanling. Research on reconstruction of missing electric energy metering data based on linear regression method[J]. Electrical Equipment and Economy, 2025(2): 46–47, 54. doi: 10.3969/j.issn.1673-8845.2025.02.016. (查阅网上资料,未找到本条文献英文翻译,请确认).
[6]	YANG Ling, ZHANG Zhilong, SONG Yang, et al. Diffusion models: A comprehensive survey of methods and applications[J]. ACM Computing Surveys, 2024, 56(7): 105. doi: 10.1145/3626235.
[7]	LUO C. Understanding diffusion models: A unified perspective[Z]. arXiv preprint arXiv: 2208.11970, 2022. doi: 10.48550/arXiv.2208.11970. (查阅网上资料,请作者核对文献类型及格式是否正确并确认修改是否正确).
[8]	郑骁麟, 王天昊, 王凯奇, 等. 配电系统伪量测数据增强方法[J/OL]. 电力系统及其自动化学报, 1–10. https://doi.org/10.19635/j.cnki.csu-epsa.001607, 2025. ZHENG Xiaolin, WANG Tianhao, WANG Kaiqi, et al. Data enhancement of pseudo-measurement in power distribution system[J/OL]. Proceedings of the CSU-EPSA, 1–10. https://doi.org/10.19635/j.cnki.csu-epsa.001607, 2025.
[9]	庞传军, 张波, 余建明. 基于LSTM循环神经网络的短期电力负荷预测[J]. 电力工程技术, 2021, 40(1): 175–180,194. doi: 10.12158/j.2096-3203.2021.01.025. PANG Chuanjun, ZHANG Bo, and YU Jianming. Short-term power load forecasting based on LSTM recurrent neural network[J]. Electric Power Engineering Technology, 2021, 40(1): 175–180,194. doi: 10.12158/j.2096-3203.2021.01.025.
[10]	雷傲宇, 高永强, 王嘉琦, 等. 基于多测点数据相关性的PMU量测谐波数据缺失填补方法[J/OL]. 南方电网技术, 1–9. http://kns.cnki.net/kcms/detail/44.1643.tk.20250421.1656.004.html, 2025. LEI Aoyu, GAO Yongqiang, WANG Jiaqi, et al. Method for filling harmonic data missing in PMU measurement based on the correlation of multi-measurement point data[J/OL]. Southern Power System Technology, 1–9. http://kns.cnki.net/kcms/detail/44.1643.tk.20250421.1656.004.html, 2025.
[11]	HO J, JAIN A, and ABBEEL P. Denoising diffusion probabilistic models[C]. Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, 2020: 574.
[12]	SONG Yang, SOHL-DICKSTEIN J, KINGMA D P, et al. Score-based generative modeling through stochastic differential equations[C]. Proceedings of the 9th International Conference on Learning Representations, Austria, 2021: 1–35. (查阅网上资料, 未找到本条文献出版城市信息, 请确认并补充).
[13]	SONG Yang, DURKAN C, MURRAY I, et al. Maximum likelihood training of score-based diffusion models[C]. Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021: 109. (查阅网上资料, 未找到本条文献出版地信息, 请确认并补充).
[14]	NICHOL A Q and DHARIWAL P. Improved denoising diffusion probabilistic models[C]. Proceedings of the 38th International Conference on Machine Learning, 2021: 8162–8171. (查阅网上资料, 未找到本条文献出版地信息, 请确认并补充).
[15]	KARRAS T, AITTALA M, AILA T, et al. Elucidating the design space of diffusion-based generative models[C]. Proceedings of the 36th International Conference on Neural Information Processing Systems, New Orleans, USA, 2022: 1926.
[16]	ALCARAZ J M L and STRODTHOFF N. Diffusion-based time series imputation and forecasting with structured state space models[Z]. arXiv preprint arXiv: 2208.09399, 2022. doi: 10.48550/arXiv.2208.09399. (查阅网上资料,请作者核对文献类型及格式是否正确并确认修改是否正确).
[17]	TASHIRO Y, SONG Jiaming, SONG Yang, et al. CSDI: Conditional score-based diffusion models for probabilistic time series imputation[C]. Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021: 1900. (查阅网上资料, 未找到本条文献出版地信息, 请确认并补充).
[18]	ROMBACH R, BLATTMANN A, LORENZ D, et al. High-resolution image synthesis with latent diffusion models[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 10674–10685. doi: 10.1109/CVPR52688.2022.01042.
[19]	ZHOU Haoyi, ZHANG Shanghang, PENG Jieqi, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[C]. Proceedings of the 35th AAAI Conference on Artificial Intelligence, Virtual Conference, 2021: 11106–11115. doi: 10.1609/aaai.v35i12.17325. (查阅网上资料,未找到本条文献出版地信息,请确认并补充).
[20]	HEBRAIL G and BERARD A. Individual household electric power consumption[EB/OL]. https://doi.org/10.24432/C58K54, 2006.
[21]	ZENG Ailing, CHEN Muxi, ZHANG Lei, et al. Are transformers effective for time series forecasting?[C]. Proceedings of the 37th AAAI Conference on Artificial Intelligence, Washington, USA, 2023: 11121–11128. doi: 10.1609/aaai.v37i9.26317.
[22]	BAI Shaojie, KOLTER J Z, and KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[Z]. arXiv preprint arXiv: 1803.01271, 2018. doi: 10.48550/arXiv.1803.01271. (查阅网上资料,请作者核对文献类型及格式是否正确).
[23]	GUPTA P, MEHLAWAT M K, and KHAN A Z. Multi-period portfolio optimization using coherent fuzzy numbers in a credibilistic environment[J]. Expert Systems with Applications, 2021, 167: 114135. doi: 10.1016/j.eswa.2020.114135.
[24]	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, 2014: 2672–2680.
[25]	KINGMA D P and WELLING M. Auto-encoding variational bayes[C]. Proceedings of the 2nd International Conference on Learning Representations, Banff, Canada, 2014.
[26]	CHEN Peng, ZHANG Yingying, CHENG Yunyao, et al. Pathformer: Multi-scale transformers with adaptive pathways for time series forecasting[C]. Proceedings of the 12th International Conference on Learning Representations, Vienna, Austria, 2024.