聚类算法在用户电力负荷分类中的应用
Application of Clustering Algorithm in User Power Load Classification
DOI: 10.12677/SG.2018.82022, PDF,  被引量    科研立项经费支持
作者: 李康宇, 吴青娥*, 陈 虎, 华智力：郑州轻工业学院电气信息工程学院，河南 郑州；刘 磊：郑州轻工业学院建筑环境工程学院，河南 郑州
关键词: 大数据；用户负荷；降维处理；聚类算法；Big Data； User Power Load； Dimensionality Reduction； Clustering Algorithm
摘要: 随着电力系统大数据时代的到来，因此对电力负荷量测数据进行聚类分析显得尤为重要，它是我们整个电力系统电力建模，需求侧管理，乃至整体规划等工作的基石，对电力系统安全，经济，稳定运行具有重大意义。对电力负荷的聚类分析，可以精确的提炼出负荷的共性以及差别。对用户侧的负荷聚类分析可以提取出用户的用电习惯及用电模式，精确把握用户用电规律，从而优化电力调度，调控整个电网的运行。作为本文的主要工作，首先对复杂高维的原始样本数据进行降维处理，然后进行聚类分析，通过对比常用的几种聚类算法结果，选择较优算法对用户用电负荷属性进行分类。
Abstract: With the advent of electric power system big data era, the power load test data clustering analysis is particularly important; it is the whole electric power system modeling, demand side management, and the foundation of overall planning, etc., to power system security, economy and stable operation is of great significance. The clustering analysis of power load can accurately extract the commonness and difference of load. The load clustering analysis on the user side can extract the user’s electricity usage and power mode, and accurately grasp the user’s power law, thus optimize the power dispatching and regulating the operation of the entire power grid. As the main work of this paper, firstly the complex high-dimensional original sample data are reduced dimensionally, and then the cluster analysis is performed. By comparing the results of several commonly used clustering algorithms, the optimal algorithm is used to classify the user power load attributes.
文章引用：李康宇, 吴青娥, 刘磊, 陈虎, 华智力. 聚类算法在用户电力负荷分类中的应用[J]. 智能电网, 2018, 8(2): 189-203. https://doi.org/10.12677/SG.2018.82022

参考文献

[1] 李欣然, 姜学皎, 钱军, 陈辉华, 宋军英, 黄良刚. 基于用户日负荷曲线的用电行业分类与综合方法[J]. 电力系统自动化, 2010, 34(10): 56-61.
[2] Zheliznyak, I., Rybchak, Z. and Zavuschak, I. (2017) Analysis of Clustering Algorithms. Advances in Intel-ligent Systems and Computing, Springer International Publishing.
[3] Wang, X., Zhang, J., Xue, H., et al. (2016) K-Means Clustering Algorithm Based on Bat Algorithm. Journal of Jilin University.
[4] Alsayat, A. and El-Sayed, H. (2016) Social Media Analysis Us-ing Optimized K-Means Clustering. IEEE International Conference on Software Engineering Research, Management and Applications, 61-66.
[5] Meng, J.N., Deng, L.L., Yu, H.Y, et al. (2011) An Improved K-Means Clustering Algorithm. Journal of Dalian National-ities University, 13, 1-3.
[6] 李智勇, 吴晶莹, 吴为麟, 宋保明. 基于自组织映射神经网络的电力用户负荷曲线聚类[J]. 电力系统自动化, 2008(15): 66-70, 78.
[7] Kwac, J., Flora, J. and Rajagopal, R. (2014) Household Energy Consumption Segmentation Using Hourly Data. IEEE Transactions on Smart Grid, 5, 420-430. [Google Scholar] [CrossRef] 
[8] Chicco, G., Napoli, R. and Piglione, F. (2006) Comparisons among Clustering Techniques for Electricity Customer Classification. IEEE Transac-tions on Power Systems, 21, 933-940. [Google Scholar] [CrossRef] 
[9] Albert, A. and Rajagopal, R. (2013) Smart Meter Driven Segmentation: What Your Consumption Says about You. IEEE Transactions on Power Systems, 28, 4019-4030. [Google Scholar] [CrossRef] 
[10] Frigui, H. (2007) Advances in Fuzzy Clustering and Its Applications.
[11] 王兵. 密度聚类算法的研究与应用[D]: [硕士学位论文]. 西安: 西安电子科技大学, 2012.

为你推荐