Power Load Curve Clustering Method Based on Singular Spectrum Analysis and Improved Density Peak Clustering Algorithm

Jun ZHAO; PENG LI; Wenchao LI; Shi SU; Junyu LIANG

doi:10.13648/j.cnki.issn1674-0629.2026.07.005

PDF(3489 KB)

South Power Sys Technol ›› 2026, Vol. 20 ›› Issue (7) : 46-57. DOI: 10.13648/j.cnki.issn1674-0629.2026.07.005

System Analysis & Operation

Power Load Curve Clustering Method Based on Singular Spectrum Analysis and Improved Density Peak Clustering Algorithm

Jun ZHAO ¹ ,
PENG LI ¹ ,
Wenchao LI ¹ ,
Shi SU ² ,
Junyu LIANG ²

Author information +

History +

Abstract

To address the misclassification issues in existing density peak clustering algorithms caused by significant local fluctuations in data or uneven distribution of load categories, a power load curve clustering method based on singular spectrum analysis and improved density peak clustering algorithm is proposed. Firstly, singular spectrum analysis is employed to decompose the original power load data into a low-frequency component containing the main contour information and a high-frequency component representing noise. Secondly, the local density of the density peak clustering algorithm is redefined by integrating the ideas of K-nearest neighbors and natural nearest neighbors, followed by clustering the low-frequency component. Finally, applied to real-world power load datasets, the proposed method is compared with other clustering algorithms, and case study results validate its effectiveness in real data.

Key words

power load curve clustering / singular spectrum analysis / density peak clustering / smart grid / data driven

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Jun ZHAO , PENG LI , Wenchao LI , et al . Power Load Curve Clustering Method Based on Singular Spectrum Analysis and Improved Density Peak Clustering Algorithm[J]. Southern Power System Technology. 2026, 20(7): 46-57 https://doi.org/10.13648/j.cnki.issn1674-0629.2026.07.005

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis

[1]	汪际峰，吴小辰，林火华，等. 数字电网的概念、特征与架构［J］. 南方电网技术， 2023， 17（12）： 36 - 41，89. WANG Jifeng， WU Xiaochen， LIN Huohua， et al. Concepts， features and architectures of digital grids［J］. Southern Power System Technology， 2023， 17（12）： 36 - 41，89. Cited in this article [1]

[2]	WANG Y， CHEN Q， HONG T， et al. Review of smart meter data analytics： applications， methodologies， and challenges［J］. IEEE Transactions on Smart Grid. 2018， 10（3）： 3125 - 3148. Cited in this article [1]

[3]	CUI X Y， LIU S Y， LIN Z Z， et al. Two-step electricity theft detection strategy considering economic return based on convolutional autoencoder and improved regression algorithm［J］. IEEE Transactions on Power Systems， 2022， 37（3）： 2346–2359. Cited in this article [1]

[4]

卓映君，周保荣，姚文峰，等. “双碳”目标下南方区域能源电力消费及负荷特性预测［J］. 南方电网技术， 2023， 17（9）： 132 - 140.

ZHUO

Yingjun

， ZHOU

Baorong

， YAO

Wenfeng

， et al. Prediction of energy and electricity consumption and load characteristics in the southern region under the carbon peak and carbon neutrality target［J］. Southern Power System Technology， 2023， 17（9）： 132 - 140.

Cited in this article [1]

[5]

李璐，张泽端，毕贵红，等. “双碳”目标下基于系统动力学的发电行业碳减排政策研究［J］. 电力系统保护与控制， 2024， 52（12）： 69 - 81.

， ZHANG

Zeduan

， BI

Guihong

， et al. Carbon emission reduction policy in the power generation sector based on system dynamics with “dual carbon” targets［J］. Power System Protection and Control， 2024， 52（12）： 69 - 81.

Cited in this article [1]

[6]

李鹏，黄文琦，梁凌宇，等. 人机混合增强决策智能在新型电力系统调控中的应用与展望［J］. 中国电机工程学报， 2024， 44（16）： 6347 - 6367.

Peng

， HUANG

Wenqi

， LIANG

Lingyu

， et al. Application and prospect of hybrid human-machine decision intelligence in the dispatch and control of next-era power systems［J］. Proceedings of the CSEE. 2024， 44（16）： 6347 - 6367.

Cited in this article [1]

[7]	李婧，徐胜蓝，万灿，等. 基于自适应k-means++算法的电力负荷特性分析［J］. 南方电网技术， 2019， 13（2）： 13 - 19. LI Jing， XU Shenglan， WAN Can， et al. Electricity load characteristics analysis based on adaptive k-means++ algorithm［J］. Southern Power System Technology， 2019， 13（2）： 13 - 19. Cited in this article [1]

[8]

谷紫文，李鹏，郎恂，等. 基于变分模态分解和密度峰值快速搜索的电力负荷曲线可控聚类模型［J］. 电力系统保护与控制， 2021， 49（8）： 118 - 127.

Ziwen

， LI

Peng

， LANG

Xun

， et al. A controllable clustering model of the electrical load curve based on variational mode decomposition and fast search of the density peak［J］. Power System Protection and Control， 2021， 49（8）： 118 - 127.

Cited in this article [1]

[9]	RODRIGUEZ A， LAIO A. Clustering by fast search and find of density peaks［J］. Science， 2014， 344（6191）： 1492 - 1496. Cited in this article [2]

[10]	张清华，周靖鹏，代永杨，等. 基于代表点与K近邻的密度峰值聚类算法［J］. 软件学报， 2023， 34（12）： 5629 - 5648. ZHANG Qinghua， ZHOU Jingpeng， DAI Yongyang， et al. Density peaks clustering algorithm based on representative points and K-nearest neighbors［J］. Journal of Software， 2023， 34（12）： 5629 - 5648. Cited in this article [1]

[11]	陈叶旺，申莲莲，钟才明，等. 密度峰值聚类算法综述［J］. 计算机研究与发展， 2020， 57（2）： 378 - 394. CHEN Yewang， SHEN Lianlian， ZHONG Caiming， et al. Survey on density peak clustering algorithm［J］. Journal of Computer Research and Development， 2020， 57（2）： 378 - 394. Cited in this article [1]

[12]	余浩，高镱滈，潘险险，等. 基于改进高斯混合模型的变电站负荷聚类算法［J］. 全球能源互联网， 2024， 7（5）： 591 - 601. YU Hao， GAO Yihao， PAN Xianxian， et al. Substation load clustering algorithm based on improved gaussian mixture model［J］. Journal of Global Energy Interconnection， 2024， 7（5）： 591 - 601. Cited in this article [1]

[13]	LU F， CUI X Y， XING J X， et al. Electricity load profile characterisation for industrial users based on normal cloud model and iCFSFDP algorithm［J］. IEEE Transactions on Power Systems， 2023， 38（4）： 3799 - 3813. Cited in this article [1]

[14]	孙园，李秋雨，黄冬梅，等. 基于粒计算和双尺度相似性的负荷曲线集成聚类算法［J］. 电力建设， 2022， 43（5）： 117 - 126. SUN Yuan， LI Qiuyu， HUANG Dongmei， et al. Clustering ensemble model based on granular computing and dual-scale similarity［J］. Electric Power Construction， 2022， 43（5）： 117 - 126. Cited in this article [1]

[15]	GU Z， LI P， XUN L， et al. A multi-granularity density peak clustering algorithm based on variational mode decomposition［J］. Chinese Journal of Electronics， 2021， 30（4）： 658 - 668. Cited in this article [1]

[16]	郭文熙，李知艺，尹建兵，等. 基于时间序列变密度处理的负荷曲线聚类分析［J］. 电力工程技术， 2024， 43（6）： 21 - 32. GUO Wenxi， LI Zhiyi， YIN Jianbing， et al. Clustering anal⁃ysis of load curve based on time series density changing processing［J］. Electric Power Engineering Technology， 2024， 43（6）： 21 - 32. Cited in this article [1]

[17]	WANG S L， WANG D K， LI C Y， et al. Comment on "Clustering by fast search and find of density peaks"［DB/OL］. （2015 - 01 - 18）［2015 - 01 - 20］. https：//arxiv.org/abs/1501.04267 Cited in this article [1]

[18]	葛阳，郭兰中，牛曙光，等. 基于t-SNE和LSTM的旋转机械剩余寿命预测［J］ . 振动与冲击， 2020， 39（7）： 223 - 231，273. GE Yang， GUO Lanzhong， NIU Shuguang， et al. Prediction of remaining useful life based on t-SNE and LSTM for rotating machinery［J］. Journal of Vibration and Shock， 2020， 39（7）： 223 - 231，273. Cited in this article [1]

[19]

黄雨薇，彭道刚，姚峻，等. 基于SSA和K均值的TD-BP神经网络超短期光伏功率预测［J］. 太阳能学报， 2021， 42（4）： 229 - 238.

HUANG

Yuwei

， PENG

Daogang

， YAO

Jun

， et al. Ultra-short-term photovoltaic power forecast of TD-BP neural network based on SSA and K-means［J］. Acta Energiae Solaris Sinica， 2021， 42（4）： 229 - 238.

Cited in this article [1]

[20]	AFSHAR K， BIGDELI N. Data analysis and short term load forecasting in Iran electricity market using singular spectral analysis （SSA）［J］. Energy， 2011， 36（5）： 2620 - 2627. Cited in this article [1]

[21]	HASSANI H. Singular spectrum analysis： methodology and comparison［J］. RePEc， 2007， 5（2）： 239 - 257. Cited in this article [1]

[22]	PETERSON L E. K-nearest neighbor［J］. Scholarpedia， 2009， 4（2）： 1883. Cited in this article [1]

[23]	ANDREW L R. Analysis of time series structure： SSA and related techniques［J］. Technometrics， 2002， 44（3）： 290. Cited in this article [1]

[24]	GOLYANDINA N E， NEKRUTKIN V V， ZHIGLJAVSKY A A. Analysis of time series structure： SSA and related techniques［J］. Technometrics， 2002， 44（3）： 290. Cited in this article [1]

[25]	彭晓璐，王涛，卢泽钰，等. 基于改进密度峰值聚类算法的典型负荷曲线提取［J］. 南方电网技术， 2025， 19（9）：150 - 161. PENG Xiaolu， WANG Tao， LU Zeyu， et al. Typical load profile extraction based on improved DPC algorithm［J］. Southern Power System Technology， 2025， 19（9）：150 - 161.

[26]	陈仕龙，吴涛，郭成，等. 基于DBSCAN聚类和区间回归的多谐波责任划分［J］. 中国电力， 2024， 57（2）： 138 - 148. CHEN Shilong， WU Tao， GUO Cheng， et al. Division of multi-harmonic responsibilities based on DBSCAN clustering and interval regression［J］. Electric Power， 2024， 57（2）： 138 - 148. Cited in this article [1]

[27]	GUO G， CHEN L， YE Y， et al. Cluster validation method for determining the number of clusters in categorical sequences［J］. IEEE Transactions on Neural Networks and Learning Systems， 2017， 28（12）： 2936 - 2948. Cited in this article [1]

[28]	谢娟英，周颖，王明钊，等. 聚类有效性评价新指标［J］. 智能系统学报， 2017， 12（6）： 873 - 882. XIE Juanying， ZHOU Ying， WANG Mingzhao， et al. New criteria for evaluating the validity of clustering［J］. CAAI Transactions on Intelligent Systems， 2017， 12（6）： 873 - 882.

[29]

李丹，梁云嫣，缪书唯，等. 基于高斯混合聚类和改进条件变分自编码的多风电场功率日场景生成方法［J］. 中国电力， 2024， 57（12）： 17 - 29.

Dan

， LIANG

Yunyan

， MIAO

Shuwei

， et al. Daily power scenario generation method for multiple wind farms based on Gaussian mixture clustering and improved conditional variational autoencoder［J］. Electric Power， 2024， 57（12）： 17 - 29.

Cited in this article [1]