Research on Application of Intelligent Algorithm Based on Multi-Source Data Fusion in Dynamic Assessment of Power Quality
Main Article Content
Abstract
With the “double-high” characteristics of a high proportion of new energy and high power electronics in the new power system, the operating conditions of the power grid present strong randomness and time-varying features. Traditional static power quality assessment methods are difficult to adapt to the dynamically fluctuating power grid operating state, with problems such as assessment lag, insufficient accuracy, and single dimension. To address the above pain points, this paper proposes an intelligent dynamic power quality assessment method based on multi-source data fusion. First, a multi-source data preprocessing and feature extraction system for power operation is constructed, and deep mining of heterogeneous data is realized relying on a three-layer fusion mechanism of data level, feature level, and decision level. Second, the temporal intelligent algorithm is improved, and a sliding window dynamic assessment model is built to realize real-time judgment and dynamic update of power quality status. Finally, simulation verification is carried out with the measured power grid data set. The experimental results show that compared with traditional assessment methods, the proposed method improves the assessment accuracy by 9.2% and reduces the dynamic response delay by 47.5%. It has stronger anti-interference and generalization ability, can effectively meet the dynamic assessment needs of power quality under complex power grid conditions, and provides technical support for the refined management and control of power grid power quality.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Q. Wang, Y. Huang, Y. Zhu, et al., “Development direction, technical issues, and key construction tasks for new power system,” Renewable Energy System Equipment, vol. 1, no. 1, pp. 1–7, 2025, doi: 10.1016/J.RESE.2024.03.001.
B. Chen, Y. Wang, L. Wei, et al., “Quantitative assessment method of new energy output uncertainty based on the prediction error,” Frontiers in Energy Research, vol. 12, 2024, doi: 10.3389/FENRG.2024.1372465.
L. Liang, H. Su, Y. Song, et al., “Dynamic risk assessment method of variable grid cluster for new power system,” Big Data Electric Power, vol. 28, no. 5, pp. 59–67, 2025, doi: 10.19317/j.cnki.1008-083x.2025.05.006.
X. Xiao, Z. Wang, S. Shao, et al., “High-voltage DC grounding fault early warning method based on multi-sensor data fusion and correlation,” Journal of Physics: Conference Series, vol. 3231, no. 1, p. 012137, 2026, doi: 10.1088/1742-6596/3231/1/012137.
X. Lin, F. Zhang, M. Zhou, et al., “Power supply reliability evaluation of distribution network based on non-intrusive low-voltage power load identification and time series algorithm,” International Journal of Global Energy Issues, vol. 46, no. 6, pp. 618–634, 2024, doi: 10.1504/IJGEI.20 24.141921.
R. N. Perez, J. Matanza, G. Lopez, et al., “Measuring the digitalisation of electricity distribution systems in Europe: Towards the smart grid,” International Journal of Electrical Power & Energy Systems, vol. 159, p. 110009, 2024, doi: 10.1016/J.IJEPES.2024.110009.
C. Silva, P. Faria, and Z. Vale, “Demand Response Implementation: Overview of Europe and United States Status,” Energies, vol. 16, no. 10, 2023, doi: 10.3390/EN16104043.
Z. Zhou, B. Jiang, and Q. Wang, “A novel multi-source spatial-temporal forecasting network for power prediction of electric vehicle charging stations,” Electric Power Systems Research, vol. 259, p. 113149, 2026, doi: 10.1016/J.EPSR.2026.113149.
Y. Geng, L. Wang, J. Hu, et al., “A dual category-channel attention convolutional network fault diagnosis method for imbalanced multi-sensor data of spacecraft,” Aerospace Science and Technology, vol. 170, p. 111593, 2026, doi: 10.1016/J.AST.2025.111593.
X. Zhang, F. Mao, Y. Li, et al., “Analysis on output characteristics and source-load correlation of new energy in regional power grid under multiple time scales,” Electric Application, vol. 42, no. 2, pp. 28–32, 2023.
H. Naderi, N. Ghaderi, and M. Abedini, “Improving power quality and efficiency of multi-level inverter system through intelligent control algorithm,” Soft Computing, vol. 28, no. 21, pp. 1–14, 2024, doi: 10.1007/S0 0500-024-10354-5.
Y. Wang, H. Zhang, and P. Cui, “Research on deep learning-based model for identification and evaluation of perturbation characteristics in photovoltaic power quality,” Journal of Physics: Conference Series, vol. 3231, no. 1, p. 012104, 2026, doi: 10.1088/1742-6596/3231/1/012104.
S. J. Shaji, H. S. Ann, V. Lavanya, et al., “Power quality improvement in microgrids using artificial intelligence techniques: A review,” Science and Technology for Energy Transition, vol. 81, p. 14, 2026, doi: 10.2516/ST ET/2026015.
J. Liu, Q. Zhou, J. Zhou, et al., “Multi-source Data Fusion for New Power Systems Under Space-Air-Ground-Integrated Monitoring Framework: Challenges and Prospects,” in Lecture Notes in Electrical Engineering, pp. 840–857, 2025, doi: 10.1007/978-981-96-1671-8_55.
P. Lu and F. Dai, “A Study on Multi-sensor Data Fusion Algorithm,” Journal of Advanced Artificial Life Robotics, vol. 2, no. 4, pp. 195–200, 2022, doi: 10.57417/JAALR.2.4_195.
A. P. Jewsbury and S. M. Johnson, “Principal component analysis on the covariance matrix for large-scale assessment data reduction,” Large-Scale Assessments in Education, vol. 13, no. 1, p. 30, 2025, doi: 10.1186/S405 36-025-00264-9.
G. Z. Ma, “The Application of D-S Improving Algorithm in Data Fusion,” Advanced Materials Research, vols. 482–484, pp. 684–687, 2012, doi: 10.4028/www.scientific.net/AMR.482-484.684.