Research Review on Photovoltaic Monitoring Data Processing Methods

Qiuping He

doi:10.6919/ICJE.202603_12(3).0040

Authors

Qiuping He

DOI:

https://doi.org/10.6919/ICJE.202603_12(3).0040

Keywords:

Photovoltaics; Data Processing; Missing Value Imputation; Feature Analysis.

Abstract

Photovoltaic power stations are subject to variable weather phenomena and equipment operational conditions during operation, resulting in a significant number of outliers and missing values in photovoltaic monitoring data. This poses substantial challenges for photovoltaic data analysis and evaluation, photovoltaic power forecasting, and photovoltaic equipment status analysis. This paper systematically outlines the fundamental principles and typical methods for anomaly detection and missing value imputation in PV monitoring data processing. It summarizes the current technical challenges and limitations in short-term PV monitoring data processing and provides insights into the key areas and research directions for future PV monitoring data processing methods.

Downloads

Download data is not yet available.

References

[1] Zhao Yongning, Ye Lin, Zhu Qianwen. Characteristics and Processing Methods of Anomalous Data Clusters in Wind Farm Curtailment [J]. Automation of Electric Power Systems, 2014, 38 (21): 39-46.

[2] ZHAO Y, LEHMAN B, BALL R, et al. Outlier detection rules for fault detection in solar photovoltaic arrays[C]//2013 Twenty-Eighth Annual IEEE Applied Power Electronics Conference and Exposition (APEC). Long Beach, CA, USA, 2013: 2913-2920.

[3] Hao Ying, Dong Lei, Wang Lijie et al. An Abnormal Data Identification Algorithm for Photovoltaic Power Generation Curtailment Based on Mathematical Morphology Denoising [J]. Transactions of the Chinese Society for Electrical Engineering, 2022, 42 (21): 7843-7855.

[4] Li Huanlong. Short-Term Photovoltaic Power Generation Data Processing and Power Forecasting for Anomalous Data [D]. Qinghai University, 2024. DOI:10.27740/d.cnki.gqhdx.2024.000988..

[5] Lin Lixin, Yu Yanhua, Tu Jianfeng. Anomaly Detection Method for Network Data Flows Based on an Improved KNN Algorithm [J]. Information and Computers(Theoretical Edition), 2023, 35 (08): 108-110.

[6] Wan Chulin, Chen Haoyong, Guo Manlan. Pattern Recognition-Based Active Power Error Data Processing for WAMS [J]. Power System Technology, 2017, 41(3): 922-930.

[7] Ren Yulu, Cheng Yushu, Wang Shushu, et al. Ultra-Short-Term Prediction Method for Photovoltaic Output Based on MMD-OHCP Data Preprocessing [J]. Power Grids and Clean Energy, 2025, 41(02): 93-99.

[8] LONG H, SANG L W, WU Z J, et al. Image-based abnormal data detection and cleaning algorithm via wind power curve［J］. IEEE transactions on sustainable energy, 2020, 11(2): 938-946

[9] Yutong Han, Ningbo Wang, Ming Ma, et al. A PV power interval forecasting basedon seasonal model and nonparametric estimation algorithm[J]. Solar Energy, 2019,184:515-526.

[10] Yin Hao, Ding Weifeng, Chen Shun, et al. A Method for Reconstructing Missing Photovoltaic Data Based on Generative Adversarial Networks and Crossed Particle Swarm Optimization [J]. Power System Technology, 2022, 46 (04): 1372-1381.

[11] Wang Shouxang, Chen Haiwen, Pan Zhixin, et al. A Method for Reconstructing Missing Measurement Data in Power Systems Using an Improved Generative Adversarial Network [J]. Chinese Journal of Electrical Engineering, 2019, 39(01): 56–64+320. DOI: 10.13334/j.0258-8013.pcsee.181282.

[12] YANG M, HUANG X. Abnormal data identification algorithm for photovoltaic power based on characteristics analysis of illumination process[J]. Automation of electric power systems, 2019, 43(6): 64-69.

[13] GONG Shanghong, PAN Tinglong, WU Dinghui, et al. Research on MCMC-Based Method for Filling Missing Photovoltaic Data in Microgrids [J]. Renewable Energy, 2018, 36(03): 346-350. DOI:10.13941/j.cnki.21-1469/tk.2018.03.005.

[14] Cao Min. Research on Data Cleaning for New Energy Power Generation Based on Artificial Intelligence [D]. Southeast University, 2023. DOI:10.27014/d.cnki.gdnau.2023.005025.

[15] Layanun V, Suksamosorn S, Songsiri J. Missing-data imputation for solarirradiance forecasting in Thailand.2017 56th Annual Conference of theSociety of Instrument and Control Engineers of Japan (SICE): IEEE; 2017. p.1234-9.

[16] Demirhan H, Renwick Z. Missing value imputation for short to mid-termhorizontal solar irradiance data. Applied Energy. 2018;225:998-1012.

[17] He Jianping. Method for Filling Missing Data in Photovoltaic Systems Based on Multi-Time-Series Prediction Models [D]. North China Electric Power University, 2025. DOI:10.27139/d.cnki.ghbdu.2025.000082.

[18] Zhang, H. P., Liu, J. Q., Duan, Z. W., et al. Research on PV Power Missing Data Imputation Based on an Improved Cloud Segmented Model [J]. Renewable Energy, 2020, 38(12): 1590-1596. DOI:10.13941/j.cnki.21-1469/tk.2020.12.005.

[19] Lin S, Li P, Xue W, et al. Recognition and reconstruction of photovoltaic output abnormal databased on geographic correlation[C]/ 2021 3rd Asia Energy and Electrical EngineeringSymposium (AEEES). Chengdu, China: IEEE, 2021: 942-948.

[20] Qiao Ying, Sun Rongfu, Ding Ran, et al. Short-Term Power Forecasting for Distributed PV Plant Clusters Based on Data Augmentation (Part I): Methodological Framework and Data Augmentation [J]. Power System Technology, 2021, 45(5): 1799-1808.

[21] Ren Hui, Yu Guangfa, Qiang Hanyue, et al. Regional PV Output Data Quality Enhancement and Ultra-Short-Term Power Forecasting Based on DGAT-Trans Combined Algorithm [J/OL]. Journal of Solar Energy, 1-11 [2026-03-04]. https://doi.org/10.19912/j.0254-0096.tynxb.2024-2352.

[22] Guo Hui. Repairing Faulty Data in Photovoltaic Power Stations Based on Clustering of Power Stations and Similar Meteorological Days [D]. Xi'an: Xi'an University of Technology, 2019.

[23] Li H, Li M, Lin X, He F, Wang Y. A spatiotemporal approach for traffic dataimputation with complicated missing patterns. Transportation research part C:emerging technologies. 2020;119:102730.