基于BIRCH聚类的光伏集群发电功率预测研究

文贤馗; 何明君; 周科; 李晓江; 唐乾

doi:10.19912/j.0254-0096.tynxb.2024-1754

PDF(939 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (2) : 60-66. DOI: 10.19912/j.0254-0096.tynxb.2024-1754

基于BIRCH聚类的光伏集群发电功率预测研究

文贤馗¹, 何明君¹, 周科¹, 李晓江², 唐乾²

作者信息 +

RESEARCH ON POWER GENERATION PREDICTION OF PHOTOVOLTAIC CLUSTERS BASED ON BIRCH CLUSTERING

Wen Xiankui¹, He Mingjun¹, Zhou Ke¹, Li Xiaojiang², Tang Qian²

Author information +

文章历史 +

摘要

针对分布式光伏功率预测中存在的原始数据有限问题,提出一种基于中位数与平均数为计算指标,结合BIRCH聚类方法进行集群划分,并采用集群累加法的预测框架。通过分别对各集群建立多种预测模型进行光伏功率预测,最终汇总各集群结果,实现对区域分布式光伏出力的整体预测。基于贵州省某区域20座分布式光伏电站的实际数据开展仿真分析,实验结果表明,所提方法预测精度较高,能满足实际应用需求。

Abstract

This article proposes a cluster partitioning method based on median and mean as calculation indicators and using BIRCH clustering algorithm to address the problems of limited raw data and information in power prediction of distributed photovoltaics. On the basis of cluster division, cluster accumulation method is adopted to predict the photovoltaic power of each cluster using multiple models, and then the prediction results of all clusters are integrated to achieve distributed photovoltaic area prediction. This article combines data from 18 distributed photovoltaic power stations in a certain region of Guizhou Province for simulation analysis. The experimental results show that the proposed algorithm has high accuracy and the proposed method can meet the practical application requirements.

导出引用

文贤馗, 何明君, 周科, 李晓江, 唐乾. 基于BIRCH聚类的光伏集群发电功率预测研究[J]. 太阳能学报. 2026, 47(2): 60-66 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1754

Wen Xiankui, He Mingjun, Zhou Ke, Li Xiaojiang, Tang Qian. RESEARCH ON POWER GENERATION PREDICTION OF PHOTOVOLTAIC CLUSTERS BASED ON BIRCH CLUSTERING[J]. Acta Energiae Solaris Sinica. 2026, 47(2): 60-66 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1754

中图分类号： TM731

参考文献

[1] 陈炜, 艾欣, 吴涛, 等. 光伏并网发电系统对电网的影响研究综述[J]. 电力自动化设备, 2013, 33(2): 26-32, 39.
CHEN W, AI X, WU T, et al.Influence of grid-connected photovoltaic system on power network[J]. Electric power automation equipment, 2013, 33(2): 26-32, 39.
[2] 李升, 卫志农, 孙国强, 等. 大规模光伏发电并网系统电压稳定分岔研究[J]. 电力自动化设备, 2016, 36(1): 17-23.
LI S, WEI Z N, SUN G Q, et al.Voltage stability bifurcation of large-scale grid-connected PV system[J]. Electric power automation equipment, 2016, 36(1): 17-23.
[3] 张小萌, 白恺, 柳玉, 等. 大规模分布式光伏短期集群功率预测综述[J]. 华北电力技术, 2017(6): 1-7.
ZHANG X M, BAI K, LIU Y, et al.Overview for large-scale distributed photovoltaic power prediction with clustered method[J]. North China electric power, 2017(6): 1-7.
[4] 栗峰, 丁杰, 周才期, 等. 新型电力系统下分布式光伏规模化并网运行关键技术探讨[J]. 电网技术, 2024, 48(1): 184-199.
LI F, DING J, ZHOU C Q, et al.Key technologies of large-scale grid-connected operation of distributed photovoltaic under new-type power system[J]. Power system technology, 2024, 48(1): 184-199.
[5] 欧阳永健, 缪希仁, 林蔚青, 等. 基于分层有向图与动态时空相关性的小区域光伏超短期预测方法[J]. 电网技术, 2024, 48(6): 2458-2468.
OUYANG Y J, MIAO X R, LIN W Q, et al.Small area PV ultra-short-term prediction method using stratified digraph and dynamic spatial-temporal correlation[J]. Power system technology, 2024, 48(6): 2458-2468.
[6] 王东风, 刘婧, 黄宇, 等. 结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究[J]. 太阳能学报, 2024, 45(2): 443-450.
WANG D F, LIU J, HUANG Y, et al.Photovoltaic power prediction method combinating solar radiation calculation and CNN-LSTM[J]. Acta energiae solaris sinica, 2024, 45(2): 443-450.
[7] 乔颖, 孙荣富, 丁然, 等. 基于数据增强的分布式光伏电站群短期功率预测(一): 方法框架与数据增强[J]. 电网技术, 2021, 45(5): 1799-1808.
QIAO Y, SUN R F, DING R, et al.Distributed photovoltaic station cluster gridding short-term power forecasting part Ⅰ: methodology and data augmentation[J]. Power system technology, 2021, 45(5): 1799-1808.
[8] 乔颖, 孙荣富, 丁然, 等. 基于数据增强的分布式光伏电站群短期功率预测(二): 网格化预测[J]. 电网技术, 2021, 45(6): 2210-2218.
QIAO Y, SUN R F, DING R, et al.Distributed photovoltaic station cluster short-term power forecasting part Ⅱ: gridding prediction[J]. Power system technology, 2021, 45(6): 2210-2218.
[9] 杨俊闯, 赵超. K-means聚类算法研究综述[J]. 计算机工程与应用, 2019, 55(23): 7-14, 63.
YANG J C, ZHAO C.Survey on K-means clustering algorithm[J]. Computer engineering and applications, 2019, 55(23): 7-14, 63.
[10] 邰彬, 黄杨珏, 沈开程, 等. 基于指标加权K-means++算法的分布式光伏功率波动平抑控制方法[J]. 武汉大学学报(工学版), 2023, 56(11): 1413-1424.
TAI B, HUANG Y J, SHEN K C, et al.Smoothing control method of distributed photovoltaic power fluctuation based on the index weighted K-means++ algorithm[J]. Engineering Journal of Wuhan University, 2023, 56(11): 1413-1424.
[11] 武艺, 姚良忠, 廖思阳, 等. 一种基于改进K-means++算法的分布式光储聚合调峰方法[J]. 电网技术, 2022, 46(10): 3923-3931.
WU Y, YAO L Z, LIAO S Y, et al.A peak shaving method of aggregating the distributed photovoltaics and energy storages based on the improved K-means++ algorithm[J]. Power system technology, 2022, 46(10): 3923-3931.
[12] 王丹, 薛激光, 旋璇, 等. 考虑相似日优选的EPGA-BPNN短期光伏功率预测[J]. 供用电, 2024, 41(5): 80-87.
WANG D, XUE J G, XUAN X, et al.Short-term PV power prediction of EPGA-BPNN considering similar day preferences[J]. Distribution & utilization, 2024, 41(5): 80-87.
[13] 欧阳静, 秦龙, 王坚锋, 等. 基于PCA-ShapeDTW-QWGRU的分布式光伏集群短期功率预测[J]. 太阳能学报, 2024, 45(5): 458-467.
OUYANG J, QIN L, WANG J F, et al.Short-term power prediction for distributed pv clusters based on PCA-ShapeDTW-QWGRU[J]. Acta energiae solaris sinica, 2024, 45(5): 458-467.
[14] 陈振祥, 林培杰, 程树英, 等. 基于K-means++和混合深度学习的光伏功率预测[J]. 电气技术, 2021, 22(9): 7-13, 33.
CHEN Z X, LIN P J, CHENG S Y, et al.Photovoltaic power prediction based on K-means++ and hybrid deep learning[J]. Electrical engineering, 2021, 22(9): 7-13, 33.
[15] BLONDEL V D, GUILLAUME J L, LAMBIOTTE R, et al.Fast unfolding of communities in large networks[J]. Journal of statistical mechanics: theory and experiment, 2008, 2008(10): P10008.
[16] 王磊, 张帆, 寇凌峰, 等. 基于Fast Unfolding聚类算法的规模化分布式光伏电源集群划分[J]. 太阳能学报, 2021, 42(10): 29-34.
WANG L, ZHANG F, KOU L F, et al.Large-scale distributed PV cluster division based on Fast Unfolding clustering algorithm[J]. Acta energiae solaris sinica, 2021, 42(10): 29-34.
[17] 陈磊, 吴润秀, 李沛武, 等. 加权K近邻和多簇合并的密度峰值聚类算法[J]. 计算机科学与探索, 2022, 16(9): 2163-2176.
CHEN L, WU R X, LI P W, et al.Weighted K-nearest neighbors and multi-cluster merge density peaks clustering algorithm[J]. Journal of frontiers of computer science and technology, 2022, 16(9): 2163-2176.
[18] 张赟宁, 石泽. 基于快速搜索与发现密度峰值聚类算法的含有分布式光伏的配电网电压分区协调控制[J]. 现代电力, 2020, 37(1): 35-41.
ZHANG Y N, SHI Z.Voltage partition coordinated control of distribution network with distributed photovoltaic based on CFSFDP algorithm[J]. Modern electric power, 2020, 37(1): 35-41.
[19] CHEN H, WANG L X, GONG Y C, et al.Distributed photovoltaic power cluster partition based on DPC clustering algorithm[C]//2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT). Shanghai, China, 2022: 974-979.
[20] WU Z J, PAN Q, ZHOU Y, et al.Distributed PV cluster partition based on KNN-DPC clustering algorithm[C]//2023 5th International Conference on Electrical Engineering and Control Technologies(CEECT). Chengdu, China, 2023: 1-5.
[21] BEZDEK J C, EHRLICH R, FULL W.FCM: the fuzzy C-means clustering algorithm[J]. Computers & geosciences, 1984, 10(2/3): 191-203.
[22] 超木日力格, 于剑, 朱杰. 结合Total-Bregman距离的模糊聚类算法[J]. 计算机科学与探索, 2016, 10(2): 220-229.
CHAO M, YU J, ZHU J.Fuzzy clustering algorithm based on total-bregman divergence[J]. Journal of frontiers of computer science and technology, 2016, 10(2): 220-229.
[23] CHEN Y Z, WANG X Y, ZHANG B S.An unsupervised deep learning approach for scenario forecasts[C]//2018 Power Systems Computation Conference (PSCC). Dublin, Ireland, 2018: 1-7.
[24] HU Y, LIU W Y, LI X, et al.A group division method for voltage control based on distributed photovoltaic scaled access to rural power grid[C]//2020 5th Asia Conference on Power and Electrical Engineering (ACPEE). Chengdu, China, 2020: 580-586.
[25] 朱墨, 张德正. 基于模糊聚类法的分布式发电集群划分策略[J]. 电工技术, 2023(18): 26-28, 31.
ZHU M, ZHANG D Z.Distributed generation cluster division strategy based on fuzzy clustering method[J]. Electric engineering, 2023(18): 26-28, 31.
[26] LYU N J, LIU X T, HU J J, et al.Cluster partition method development for high penetration of distributed photovoltaics using intelligent algorithm and K-means[C]//2022 IEEE 5th International Conference on Electronics Technology (ICET). Chengdu, China, 2022: 1255-1260.
[27] MENG T, LYU X Y, LI C G, et al.Research on partition method of distributed photovoltaic cluster based on modularity index and absorption ability[C]//2023 2nd International Conference on Smart Grids and Energy Systems (SGES). Guangzhou, China, 2023: 323-327.
[28] CHEN L, SUN Y H, WU Z R, et al.Distributed PV cluster partitioning strategy based on GAN data synthesis federation clustering[C]//2023 8th International Conference on Power and Renewable Energy (ICPRE). Shanghai, China, 2023: 1730-1735.