基于气象分类的光伏发电预测
Meteorological Classification-Based Photovoltaic Power Generation Forecasting
DOI: 10.12677/sa.2026.157154, PDF,    科研立项经费支持
作者: 吴林河：长安大学理学院，陕西 西安；中创新能网络科技有限公司，陕西 西安；万建飞*：长安大学理学院，陕西 西安；杨 杭：中创新能网络科技有限公司，陕西 西安
关键词: 光伏发电；发电预测；分类预测；Photovoltaic Power Generation； Power Generation Forecasting； Classification-Based Prediction
摘要: 随着节能降碳行动方案的推出，光伏发电产业得到空前的发展，其发电量的不确定性对电网的稳定性带来重大冲击，所以，对光伏发电的精准预测是确保电网稳定运行的重要环节。通过对光伏发电的主要影响因素的分析，将气象等非定量且强非线性的因素进行分类，对各分类情况分别进行建模，得到分类预测模型。充分利用我们数据完整的优势，确定分类预测模型的参数，对测试集数据的比较分析表明，分类预测模型稳定性好，鲁棒性强，预测精度高。
Abstract: With the introduction of energy conservation and carbon reduction action plans, the photovoltaic (PV) power generation industry has experienced unprecedented growth. However, the uncertainty of PV power output poses significant challenges to the stability of the power grid. Therefore, accurate forecasting of PV power generation is crucial for ensuring reliable grid operation. By analyzing the main influencing factors of PV power generation, non-quantitative and strongly nonlinear factors, such as weather conditions, are classified. A separate prediction model is developed for each category, resulting in a classification-based forecasting model. Leveraging the advantage of complete data, the parameters of the classification-based prediction model are determined. Comparative analysis of the test set data demonstrates that the proposed model exhibits good stability, strong robustness, and high prediction accuracy.
文章引用：吴林河, 万建飞, 杨杭. 基于气象分类的光伏发电预测[J]. 统计学与应用, 2026, 15(7): 119-126. https://doi.org/10.12677/sa.2026.157154

参考文献

[1] Schultz, M.G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen, L.H., et al. (2021) Can Deep Learning Beat Numerical Weather Prediction? Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 379, Article 20200097. [Google Scholar] [CrossRef] [PubMed]
[2] Taillardat, M., Mestre, O., Zamo, M. and Naveau, P. (2016) Calibrated Ensemble Forecasts Using Quantile Regression Forests and Ensemble Model Output Statistics. Monthly Weather Review, 144, 2375-2393. [Google Scholar] [CrossRef] 
[3] Rasp, S., Pritchard, M.S. and Gentine, P. (2018) Deep Learning to Represent Subgrid Processes in Climate Models. Proceedings of the National Academy of Sciences, 115, 9684-9689. [Google Scholar] [CrossRef] [PubMed]
[4] Ham, Y.G., Kim, J.H. and Luo, J.J. (2019) Deep Learning for Multi-Year ENSO Forecasts. Nature, 573, 568-572. [Google Scholar] [CrossRef] [PubMed]
[5] 王嫄, 霍鹏, 韩毅, 等. 基于深度学习的气象预报模型研究综述[J]. 中国电机工程学报, 2023, 43(20): 7929-7940.
[6] 张童彦, 廖清芬, 唐飞, 等. 基于气象资源插值与迁移学习的广域分布式光伏功率预测方法[J]. 中国电机工程学报, 2023, 43(20): 7929-7940.
[7] Sezen, M., Shabani, M. and Demir, I. (2024) Spatio-Temporal Graph Neural Networks for Multi-Site Photovoltaic Power Forecasting. Applied Energy, 362, Article 123000.
[8] El Bakali, S., Ouadi, H. and Gheouany, S. (2025) Wind Turbine and PV Power Prediction Using a Deterministic Data-Driven Model with Variational Mode Decomposition Preprocessing. Transactions of the Institute of Measurement and Control, 47, 1413-1428. [Google Scholar] [CrossRef] 
[9] Shin, W.G., Lee, J.S., Ju, Y.C., Hwang, H.M. and Ko, S.W. (2025) Data Preprocessing and Machine Learning Method Based on Ameliorated Mathematical Models for Inferring the Power Generation of Photovoltaic System. Energy Conversion and Management, 333, Article 119793. [Google Scholar] [CrossRef] 
[10] Zhang, X., Deng, Q., Jia, M., Dai, X., Gao, X. and Zhou, H. (2024) Integrating a Hybrid Data Processing Strategy into an Optimized Light Gradient Boosting Machine for Photovoltaic Power Forecasting. Neural Computing and Applications, 37, 1633-1650. [Google Scholar] [CrossRef] 
[11] Zhu, C., Tu, Y., Wei, Q., Zang, Y., Zhou, P., Yang, L., et al. (2025) Short-Term Power Prediction of Photovoltaic Power Station Based on LSTM-XGBoost Model. Solar Energy, 300, Article 113819. [Google Scholar] [CrossRef] 
[12] 龙小慧, 秦际赟, 张青雷, 等. 基于相似日聚类及模态分解的短期光伏发电功率组合预测研究[J]. 电网技术, 2024, 48(7): 2948-2957.
[13] Alghassab, M. (2025) Advancing Photovoltaic Power Forecast Accuracy: A Hybrid Particle Filter and Recurrent Neural Network Model for Data-Scarce Scenarios toward Thermal Adaptation. Case Studies in Thermal Engineering, 75, Article 107247. [Google Scholar] [CrossRef] 
[14] 臧鹏发, 王珂琪, 张中伟, 等. 基于多特征提取的超短期光伏发电功率预测研究[J]. 激光与光电子学进展, 2025, 62(5): 333-343.
[15] 任惠, 于光发, 强涵悦, 等. 基于DGAT-Transformer组合算法的区域光伏出力数据质量增强与超短期功率预测方法[J]. 太阳能学报, 2026, 47(5): 639-649.

为你推荐