Load Curve Clustering Method Combining Improved Piecewise Linear Representation and Dynamic Time Warping

被引：0
|
作者：
Song J. [1 ]
Cui Y. [2 ]
Li X. [2 ]
Zhong W. [1 ]
Liu T. [1 ]
Li P. [2 ]
机构：
[1] State Grid Hunan Electric Power Company Limited, Changsha
[2] College of Electrical and Information Engineering, Hunan University, Changsha
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2021年 / 45卷 / 02期
基金：
国家重点研发计划;
关键词：
Daily load curve clustering; Dimension reduction and reconstruction; Dynamic time warping distance; Improved piecewise linear representation; Online load modeling; Power system;
D O I：
10.7500/AEPS20200519004
中图分类号：
学科分类号：
摘要：
Clustering analysis is the basic method for the load characteristic classification and synthesis. Aiming at the shortcomings in clustering quality and robustness of existing clustering methods applied to online load modeling based on the power grid big data platform, this paper proposes an improved piecewise linear representation (IPLR) method for daily load curve dimension reduction. Based on the advantages of IPLR for adaptive dimension reduction and reconstruction of data sets, combined with the characteristics of dynamic time warping (DTW) distance which is suitable for measuring the similarity between time series of unequal dimension, a daily load curve clustering method combining IPLR and DTW distance is constructed. Firstly, according to the variation of adjacent and interval sampling points of load curves, the characteristic points of load curves are extracted, and the curves are reconstructed by adaptive dimension reduction. Then, the DTW distance is taken as the similarity measurement index, and the clustering analysis of dimension reduction data is carried out by using Canopy based K-means (CK-means) algorithm. The method proposed is applied to the classification and synthesis of the daily load curves of typical consumers in a provincial power grid of China. The results show that the proposed dimension reduction method matches with the similarity measurement method, has good comprehensive performance, and is suitable for the analysis of the industrial composition ratio of synthesis load in substations. © 2021 Automation of Electric Power Systems Press.
引用
收藏
页码：89 / 96
页数：7
相关论文
共 25 条
  • [1] JI Y, BUECHLER E, RAJAGOPAL R., Data-driven load modeling and forecasting of residential appliances, IEEE Transactions on Smart Grid, 11, 3, pp. 2652-2661, (2020)
  • [2] LI Xinran, LIN Shunjiang, LIU Yanghua, Et al., A new classification method for aggregate load dynamic characteristic based on field measured response, Proceedings of the CSEE, 26, 8, pp. 39-44, (2006)
  • [3] LIU Yang, XU Lixiong, WANG Jian, A high performance extraction method for massive user load typical characteristics considering data class imbalance, Proceedings of the CSEE, 39, 14, pp. 4093-4104, (2019)
  • [4] LI C, CAI W, YU C, Et al., Electricity consumption behaviour analysis based on adaptive weighted-feature K-means-AP clustering, IET Generation, Transmission & Distribution, 13, 12, pp. 2352-2361, (2019)
  • [5] HARB H, MAKHOUL A, COUTURIER R., An enhanced K-means and ANOVA-based clustering approach for similarity aggregation in underwater wireless sensor networks, IEEE Sensors Journal, 15, 10, pp. 5483-5493, (2015)
  • [6] QU Xing, LI Xinran, Synthesis load modeling of power system considering distribution network structure, Automation of Electric Power Systems, 44, 12, pp. 117-125, (2020)
  • [7] SONG Junying, HE Cong, LI Xinran, Et al., Daily load curve clustering method based on feature index dimension reduction and entropy weight method, Automation of Electric Power Systems, 43, 20, pp. 65-72, (2019)
  • [8] WANG Zichen, WU Hao, JIANG Zhengbang, Et al., Singular value decomposition-based load indexes for load profiles clustering, IET Generation, Transmission & Distribution, 14, 19, pp. 4164-4172, (2020)
  • [9] JIANG Z, LIN R, YANG F, Et al., A fused load curve clustering algorithm based on wavelet transform, IEEE Transactions on Industrial Informatics, 14, 5, pp. 1856-1865, (2018)
  • [10] PIAO M, SHON H S, LEE J Y, Et al., Subspace projection method based clustering analysis in load profiling, IEEE Transactions on Power Systems, 29, 6, pp. 2628-2635, (2014)
123