周航,马立红,李中中,王海生,李思凡,张昌俊,符林贝
ZHOU Hang,MA Lihong,LI Zhongzhong,WANG Haisheng,LI Sifan,ZHANG Changjun,FU Linbei

• 1:海南电网有限责任公司

摘要(Abstract)：

可再生能源出力的波动性及用户侧用电行为的随机性导致源荷不确定性日益加剧，给微电网运行带来了较大的运行风险。为此，提出一种基于源-荷运行模式划分的微电网经济运行决策方法，以实现源荷不确定性下的微电网经济运行。首先，基于信息粒表征多变量时间序列，引入SWMD（空间加权矩阵距离）改进传统近邻传播聚类算法，采用多变量时间序列聚类算法量化各变量维度之间的相关性，实现微电网运行模式划分；其次，利用同种运行模式下的相似日数据构建待预测日的源-荷概率预测模型，通过场景生成和场景缩减获取典型源-荷预测场景；最后，采用自适应权重粒子群优化算法完成微电网随机优化模型的求解。算例结果表明，所提微电网经济运行方法能在有效处理源荷不确定性的基础上降低运行成本。
The volatility of renewable energy output and the randomness of user-side electricity consumption behavior have led to increasing source-load uncertainties, posing significant operational risks to microgrids. To address this issue, an economic operation decision-making method for microgrids based on source-load operation mode classification is proposed to achieve economic operation under uncertain conditions. First, a multivariate time series representation based on information granules is used, and the traditional affinity propagation(AP) is improved with spatial weighted matrix distance(SWMD). A multivariate time series clustering algorithm is applied to quantify correlations between variable dimensions, enabling the classification of microgrid operation modes. Second, a sourceload probabilistic forecasting model for the target day is established using similar-day data under the same operation mode, and typical source-load forecasting scenarios are obtained through scenario generation and reduction. Finally, the adaptive weighted particle swarm optimization(AW-PSO) is employed to solve the stochastic optimization model for microgrid operations. Case study results show that the proposed method effectively handles sourceload uncertainties while reducing operational costs.

关键词(KeyWords)： 源荷不确定性;多变量时间序列聚类;自适应权重粒子群优化算法;微电网经济运行
source-load uncertainty;multivariate time series clustering;AW-PSO;economic microgrid operation

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划（2021YFB1507100）;; 中国南方电网有限责任公司科技项目（070000KK52210030）

作者(Author): 周航,马立红,李中中,王海生,李思凡,张昌俊,符林贝
ZHOU Hang,MA Lihong,LI Zhongzhong,WANG Haisheng,LI Sifan,ZHANG Changjun,FU Linbei

DOI: 10.19585/j.zjdl.202506007

参考文献(References)：

• [1]国家能源局.国家能源局2023年四季度新闻发布会文字实录[EB/OL].(2023-10-31)[2024-8-12].https：//www.nea.gov.cn/2023-10/31/c_1310748132.html.
• [2] ISHAQ S,KHAN I,RAHMAN S,et al.A review on recent developments in control and optimization of micro grids[J].Energy Reports,2022,8:4085-4103.
• [3] TAJJOUR S,CHANDEL S S.A comprehensive review on sustainable energy management systems for optimal operation of future-generation of solar microgrids[J].Sustainable Energy Technologies and Assessments,2023,58:103377.
• [4]吉祥，谢敏，曾东，等.考虑风光互补特征的多微网系统自治经济调度模型[J].浙江电力，2022,41(10):97-105.JI Xiang,XIE Min,ZENG Dong,et al.Autonomous economic dispatch of multi-microgrid systems considering complementarity between wind and solar power[J].Zhejiang Electric Power,2022,41(10):97-105
• [5]聂涌泉，彭超逸，胡亚平，等.基于边缘计算的高渗透率微电网并行分布式优化经济调度[J].南方电网技术，2023,17(1):114-124.NlE Yongquan,PENG Chaoyi,HU Yaping,et al.Parallel distributed optimal economic dispatch of high penetration microgrid based on edge computing[J]. Southern Power System Technology,2023,17(1):114-124.
• [6] VELASQUEZ M A,BARREIRO-GOMEZ J,QUIJANO N,et al.Intra-hour microgrid economic dispatch based on model predictive control[J].IEEE Transactions on Smart Grid,2020,11(3):1968-1979.
• [7]李雪玲，刘洋，李振伟，等.基于气象分型改进构造不确定集的多微网低碳鲁棒经济调度[J].电力建设，2023,44(8):142-156.LI Xueling,LIU Yang,LI Zhenwei,et al. Robust lowcarbon economic dispatch of multiple microgrids based on improved uncertainty set of meteorological classification[J].Electric Power Construction,2023,44(8):142-156.
• [8]季玉琦，严亚帮，和萍，等.基于K-Medoids聚类与栅格法提取负荷曲线特征的CNN-LSTM短期负荷预测[J].电力系统保护与控制，2023,51(18):81-93.JI Yuqi,YAN Yabang,HE Ping,et al.CNN-LSTM shortterm load forecasting based on the K-Medoids clustering and grid method to extract load curve features[J].Power System Protection and Control,2023,51(18):81-93.
• [9]宋军英，何聪，李欣然，等.基于特征指标降维及熵权法的日负荷曲线聚类方法[J].电力系统自动化，2019,43(20):65-72.SONG Junying,HE Cong,LI Xinran,et al. Daily load curve clustering method based on feature index dimension reduction and entropy weight method[J]. Automation of Electric Power Systems,2019,43(20):65-72.
• [10] WANG Y,CHEN Q X,KANG C Q,et al.Sparse and redundant representation-based smart meter data compression and pattern extraction[J]. IEEE Transactions on Power Systems,2017,32(3):2142-2151.
• [11]徐胜蓝，司曹明哲，万灿，等.考虑双尺度相似性的负荷曲线集成谱聚类算法[J].电力系统自动化，2020,44(22):152-160.XU Shenglan,SI Caomingzhe,WAN Can,et al.Ensemble spectral clustering algorithm for load profiles considering dual-scale similarities[J]. Automation of Electric Power Systems,2020,44(22):152-160.
• [12]周思思，李勇，郭钇秀，等.考虑时序特征提取与双重注意力融合的TCN超短期负荷预测[J].电力系统自动化，2023,47(18):193-205.ZHOU Sisi,LI Yong,GUO Yixiu,et al. Ultra-short-term load forecasting based on temporal convolutional network considering temporal feature extraction and dual attention fusion[J].Automation of Electric Power Systems,2023,47(18):193-205.
• [13]徐昊，王永生，许志伟，等.基于生成对抗网络多变量风电时间序列异常值处理[J].太阳能学报，2022,43(12):300-311.XU Hao,WANG Yongsheng,XU Zhiwei,et al. Outlier processing of multivariable wind power time series based on generative adversarial network[J]. Acta Energiae Solaris Sinica,2022,43(12):300-311.
• [14]张弛，陈梅，张锦宏.紧凑性约束下的形状提取多元时序聚类[J].计算机科学与探索，2024,18(5):1243-1258.ZHANG Chi,CHEN Mei,ZHANG Jinhong. Clustering multivariate time series data based on shape extraction with compactness constraint[J]. Journal of Frontiers of Computer Science&Technology,2024,18(5):1243-1258.
• [15] PEDRYCZ W,HOMENDA W. Building the fundamentals of granular computing:a principle of justifiable granularity[J]. Applied Soft Computing,2013,13(10):4209-4218.
• [16]卢伟.基于粒计算的时间序列分析与建模方法研究[D].大连：大连理工大学，2015.LU Wei. Research on time series analysis and modeling method based on granular computing[D]. Dalian:Dalian University of Technology,2015.
• [17] SANHUDO L,RODRIGUES J,FILHOêV.Multivariate time series clustering and forecasting for building energy analysis:application to weather data quality control[J].Journal of Building Engineering,2021,35:101996.
• [18] HE H,TAN Y H.Unsupervised classification of multivariate time series using VPCA and fuzzy clustering with spatial weighted matrix distance[J]. IEEE Transactions on Cybernetics,2020,50(3):1096-1105.
• [19] FREY B J,DUECK D. Clustering by passing messages between data points[J]. Scientific Reports,2007,315(5814):972-976.
• [20]赵书强，要金铭，李志伟.基于改进K-means聚类和SBR算法的风电场景缩减方法研究[J].电网技术，2021,45(10):3947-3954.ZHAO Shuqiang,YAO Jinming,LI Zhiwei.Wind power scenario reduction based on improved K-means clustering and SBR algorithm[J].Power System Technology,2021,45(10):3947-3954.
• [21]张延宇，曾鹏，李忠文，等.智能电网环境下空调系统多目标优化控制算法[J].电网技术，2014,38(7):1819-1826.ZHANG Yanyu,ZENG Peng,LI Zhongwen,et al. A multi-objective optimal control algorithm for air conditioning system in smart grid[J].Power System Technology,2014,38(7):1819-1826.
• [22] MAKONIN S,ELLERT B,BAJI?I V,et al.Electricity,water,and natural gas consumption of a residential house in Canada from 2012 to 2014[J].Scientific Data,2016,3:160037.
• [23] SINGHAL A,SEBORG D.Pattern matching in historical batch data using PCA[J].IEEE Control Systems,2002,22(5):53-63.