陈文进,杨晓丰,祁炜雯,王建军,赵峰,陈建国,王健
CHEN Wenjin,YANG Xiaofeng,QI Weiwen,WANG Jianjun,ZHAO Feng,CHEN Jianguo,WANG Jian

• 1:国网浙江省电力有限公司
• 2:国网浙江省电力有限公司绍兴供电公司
• 3:河海大学能源与电气学院

摘要(Abstract)：

在光伏发电渗透率不断提高的背景下，针对光伏电站集群划分效果差、耗时长的问题，提出一种基于原型提取和聚类的光伏电站快速集群划分方法。首先，对光伏数据进行预处理，消除不同数据在量级与量纲上的差异性；然后，基于Pearson相关系数法筛选出对光伏出力影响较大的因素，然后通过设置随机抽样、k-means++和改进谱聚类3个环节，分别实现光伏电站的抽样、原型提取和原型聚类；继而基于枚举法和分层优化的思想，搜索上述环节的最优超参数；最后，设置不同场景进行算例对照，计算聚类内外指标和聚类时间指标，通过综合分析，验证了所提方法在解决大规模光伏电站快速聚类问题上的有效性。
The penetration rate of photovoltaic power generation keeps increasing. To address the issues of poor cluster partitioning and lengthy processing times for photovoltaic power station clusters, the paper proposes a method for rapid cluster partitioning method for photovoltaic(PV) plants based on prototype extraction and clustering. Firstly, photovoltaic data is preprocessed to eliminate differences in magnitude and dimensionality among data sets. Subsequently, influential factors on photovoltaic output power are identified using the Pearson correlation coefficient method. Random sampling, k-means++, and an improved spectral clustering method are then employed for sampling, prototype extraction, and prototype clustering of PV plants, respectively. Building upon an enumeration approach and hierarchical optimization, optimal hyperparameters for the aforementioned processes are determined. Finally, various scenarios are set up for case study comparisons, calculating both intra-cluster and inter-cluster indicators as well as clustering time metrics. Through comprehensive analysis, the effectiveness of the proposed method in addressing the rapid clustering for large-scale PV plants is validated.

关键词(KeyWords)： 光伏电站;改进谱聚类算法;原型聚类;Pearson相关系数
photovoltaic power station;improved spectral clustering algorithm;prototype clustering;Pearson correlation coefficient

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211SX220001）

作者(Author): 陈文进,杨晓丰,祁炜雯,王建军,赵峰,陈建国,王健
CHEN Wenjin,YANG Xiaofeng,QI Weiwen,WANG Jianjun,ZHAO Feng,CHEN Jianguo,WANG Jian

DOI: 10.19585/j.zjdl.202404008

参考文献(References)：

• [1]韩梦瑶，熊焦，刘卫东.中国光伏发电的时空分布、竞争格局及减排效益[J].自然资源学报，2022,37(5):1338-1351.HAN Mengyao,XIONG Jiao,LIU Weidong. Spatiotemporal distribution,competitive development and emission reduction of China’s photovoltaic power generation[J].Journal of Natural Resources,2022,37(5):1338-1351. [2]中国能源局.2020年度全国可再生能源电力发展监测评价报告[R].北京：中国能源局，2021. [3]卢俊杰，蔡涛，郎建勋，等.基于集群划分的光伏电站集群发电功率短期预测方法[J].高电压技术，2022,48(5):1943-1951.LU Junjie,CAI Tao,LANG Jianxun,et al. Short-term power output forecasting of clustered photovoltaic solar plants based on cluster partition[J]. High Voltage Engineering,2022,48(5):1943-1951. [4]张永新，李飞，张榴晨，等.基于线路阻抗聚类的分布式光伏电站等效建模[J].太阳能学报，2022,43(5):312-318.ZHANG Yongxin,LI Fei,ZHANG Liuchen,et al.Equivalent modeling of distributed photovoltaic power stations based on line impedance clustering[J].Acta Energiae Solaris Sinica,2022,43(5):312-318. [5]吴春华，俞薛颖，李智华，等.基于FCM与高斯隶属度的光伏组件健康状态诊断[J].电网技术，2022,46(5):1887-1896.WU Chunhua,YU Xueying,LI Zhihua,et al.Health state diagnosis of photovoltaic modules based on FCM and Gaussian membership[J]. Power System Technology,2022,46(5):1887-1896. [6]王开艳，杜浩东，贾嵘，等.基于相似日聚类和QR-CNNBiLSTM模型的光伏功率短期区间概率预测[J].高电压技术，2022,48(11):4372-4388.WANG Kaiyan,DU Haodong,JIA Rong,et al.Short-term interval probability prediction of photovoltaic power based on similar daily clustering and QR-CNN-BiLSTM model[J].High Voltage Engineering,2022,48(11):4372-4388. [7]刘圣洋，冬雷，王晓晓，等.基于高斯核模糊C均值聚类的光伏阵列故障诊断方法[J].太阳能学报，2021,42(5):286-294.LIU Shengyang,DONG Lei,WANG Xiaoxiao,et al.Photovoltaic array fault diagnosis based on gkfcm[J].Acta Energiae Solaris Sinica,2021,42(5):286-294. [8]梁嘉文，严贝峰，景楷楠，等.基于K-Medoids聚类的分布式光伏台区线损异常感知算法[J].电机与控制应用，2022,49(12):47-52.LIANG Jiawen,YAN Beifeng,JING Kainan,et al.Distributed photovoltaic station area line loss anomaly sensing algorithm based on K-medoids clustering[J]. Electric Machines&Control Application,2022,49(12):47-52. [9]董雪，赵宏伟，赵生校，等.基于SOM聚类和二次分解的BiGRU超短期光伏功率预测[J].太阳能学报，2022,43(11):85-93.DONG Xue,ZHAO Hongwei,ZHAO Shengxiao,et al.Ultra-short-term forecasting method of photovoltaic power based on som clustering, secondary decomposition and bigru[J].Acta Energiae Solaris Sinica,2022,43(11):85-93. [10]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 Lei,ZHANG Fan,KOU Lingfeng,et al. Largescale distributed pv cluster division based on fast unfolding clustering algorithm[J]. Acta Energiae Solaris Sinica,2021,42(10):29-34. [11]周志华.机器学习[M].北京：清华大学出版社，2016:23-95. [12]兰洲，蒋晨威，谷纪亭，等.促进可再生能源发电消纳和碳减排的数据中心优化调度与需求响应策略[J].电力建设，2022,43(4):1-9.LAN Zhou,JIANG Chenwei,GU Jiting,et al.Optimal dispatch and demand response strategies of data centers for promoting accommodation of renewable energy generation and reducing carbon emission[J].Electric Power Construction,2022,43(4):1-9. [13]孙玉芹，王亚文，朱威，等.基于考虑气温影响的门限自回归移动平均模型居民日用电负荷预测[J].电力建设，2022,43(9):117-124.SUN Yuqin,WANG Yawen,ZHU Wei,et al.Residential daily power load forecasting based on threshold ARMA model considering the influence of temperature[J].Electric Power Construction,2022,43(9):117-124. [14]孙宇航，田亮.基于KPCA-kmeans++数据挖掘的二次风燃烧优化[J/OL].华北电力大学学报（自然科学版）：1-9[2023-01-16]. http：//kns. cnki. net/kcms/detail/13.1212.TM.20220314.1147.002.html.SUN Yuhang,TIAN Liang.Secondary air combustion optimization based on KPCA-kmeans++data mining[J/OL].Journal of North China Electric Power University(Natural Science Edition):1-9[2023-01-16].http：//kns.cnki.net/kcms/detail/13.1212.TM.20220314.1147.002.html. [15] VON LUXBURG U.A tutorial on spectral clustering[J].Statistics and Computing,2007,17(4):395-416. [16] CHUNG FR,GRAHAM FC.Spectral graph theory[M].[S.l:s.n.],1997. [17] JIA H J,DING S F,XU X Z,et al.The latest research progress on spectral clustering[J].Neural Computing and Applications,2014,24(7):1477-1486. [18] YAN D H,HUANG L,JORDAN M I.Fast approximate spectral clustering[C]//Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining. 28 June 2009,Paris,France. ACM,2009:907–916. [19] YANG Y Y,DENG S C,LU J,et al. GraphLSHC:towards large scale spectral hypergraph clustering[J].Information Sciences,2021,544:117-134. [20] CAI D,CHEN X L. Large scale spectral clustering via landmark-based sparse representation[J]. IEEE Transactions on Cybernetics,2015,45(8):1669-1680. [21]杨莉，黄文焘，余墨多，等.港口大规模冷箱负荷群用电的一致性分层优化调度方法[J/OL].中国电机工程学报：1-12[2023-02-09]. DOI:10.13334/j. 0258-8013. pcsee.222370.Yang Li,Hung Wentao,Yu Moduo,et al. Consensus Based Hierarchical Optimization Scheduling Method for Large-Scale Reefer Loads in Ports[J/OL].Proceedings of the CSEE:1-12[2023-02-09]. DOI:10.13334/j. 0258-8013.pcsee.222370. [22] MUNSHI A A,MOHAMED Y A R I. Photovoltaic power pattern clustering based on conventional and swarm clustering methods[J].Solar Energy,2016,124:39-56.
• （本文编辑：徐晗）