基于改进蚁群算法的电力负荷半监督聚类

doi:10.12204/j.issn.1000-7229.2020.10.009

电力建设 ›› 2020, Vol. 41 ›› Issue (10): 81-89.doi: 10.12204/j.issn.1000-7229.2020.10.009

基于改进蚁群算法的电力负荷半监督聚类

段秦刚¹, 王浩浩¹, 伍子东², 王一¹, 朱涛¹, 董萍², 刘明波²

1.广东电力交易中心有限责任公司,广州市 510030
2.华南理工大学电力学院,广州市 510640

收稿日期:2020-05-18 出版日期:2020-10-01 发布日期:2020-09-30
通讯作者: 伍子东
作者简介:段秦刚(1988),男,硕士,高级工程师,研究方向为电力市场策划运行与分析;|王浩浩(1986),男,硕士,研究方向为电力市场、电网运行与调度;|王一(1979) ,男,博士,高级工程师,研究方向为电力市场、节能发电调度;|朱涛(1994),男,硕士,研究方向为电力市场、电力系统优化与控制;|董萍(1978),女,博士,副教授,研究方向为电力市场需求响应、柔性交流输电系统技术及电力系统控制;|刘明波(1964),男,博士,教授,研究方向为电网无功优化调度及最优潮流计算、电力系统电压稳定性分析、地理信息系统及配网自动化技术。
基金资助:
广东电力交易中心科技项目(GDKJXM20172986)

Research on Power Load Semi-supervised Clustering Based on Improved Ant Colony Algorithm

DUAN Qingang¹, WANG Haohao¹, WU Zidong², WANG Yi¹, ZHU Tao¹, DONG Ping², LIU Mingbo²

1. Guangdong Power Exchange Company with Limited Liability, Guangzhou 510030, China
2. School of Electrical Engineering, South China University of Technology, Guangzhou 510640, China

Received:2020-05-18 Online:2020-10-01 Published:2020-09-30
Contact: WU Zidong
Supported by:
Guangdong Power Exchange Company with Limited Liability(GDKJXM20172986)

摘要/Abstract

摘要：

计量通信技术的发展使收集的用户负荷信息越来越准确,从而提供了负荷用电特性聚类分析的数据基础。为了解决电力负荷聚类应用场景中需要聚类结果与典型负荷类别尽可能相似的问题,以蚁群聚类算法为基础,采用典型负荷曲线作为先验信息,将评估聚类效果的指标和聚类中心与典型负荷曲线的距离2个因素构成优度指标来代替传统的均方误差,以此来更新信息素矩阵,设计了一种基于改进蚁群聚类的半监督聚类算法。通过某省工业用户2017年的日负荷数据分析验证了聚类结果不仅向原有的标识样本类型靠近,而且兼顾同类型样本差异小、不同类型样本差异大,具有良好的聚类效果。

关键词: 电力负荷, 聚类分析, 蚁群算法, 半监督聚类

Abstract:

The development of metrology communication technology enables the user’s load information to be accurately collected, and the clustering analysis of the power consumption characteristics of the load can be performed. In order to solve the problem that load clustering application scenarios need clustering results as similar as possible to initial cluster center, two improved ant colony clustering algorithms are designed on the basis of the ant colony clustering algorithm. The two factors that determine the clustering effect and the distance between the cluster center and the initial cluster center constitute the fitness index instead of the traditional mean square error for updating pheromone matrix. The example analysis shows that the algorithm can solve this kind of application scenario well and has good clustering effect.

Key words: power load, cluster analysis, ant colony algorithm, semi-supervised clustering

中图分类号:

TM714

段秦刚, 王浩浩, 伍子东, 王一, 朱涛, 董萍, 刘明波. 基于改进蚁群算法的电力负荷半监督聚类[J]. 电力建设, 2020, 41(10): 81-89.

DUAN Qingang, WANG Haohao, WU Zidong, WANG Yi, ZHU Tao, DONG Ping, LIU Mingbo. Research on Power Load Semi-supervised Clustering Based on Improved Ant Colony Algorithm[J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(10): 81-89.

图/表 10

图1 改进蚁群聚类算法计算步骤

Fig.1 Calculation steps of improved ant colony clustering algorithm

图2 不同聚类数量和蚂蚁数量下改进蚁群聚类算法的SI指标

Fig.2 SI of index improved ant colony clustering algorithms under different cluster numbers and ant numbers

图3 不同聚类数量和蚂蚁数量下改进蚁群聚类算法的DBI指标

Fig.3 DBI of index improved ant colony clustering algorithms under different cluster numbers and ant numbers

图4 SIp改进蚁群算法SI与距离取不同权数时的聚类效果

Fig.4 Clustering effect of SI and distance with different weights in SIp improved ant colony clustering algorithm

图5 DBIp改进蚁群算法DBI与距离取不同权数时的聚类效果

Fig.5 Clustering effect of DBI and distance with different weights in DBIp improved ant colony clustering algorithm

图6 各算法的SI指标对比

Fig.6 SI index comparison of the algorithms

图7 各算法的DBI指标对比

Fig.7 DBI index comparison of the algorithms

图8 各种算法的聚类结果与初始聚类中心的距离对比

Fig.8 Distance between clustering result and initial clustering center comparison of the algorithms

表1 6种算法的3项指标对比

Table 1 Comparison of three indices of six algorithms

图9 3条初始聚类中心负荷曲线和各种聚类算法的聚类中心

Fig.9 Initial three pretended clustering centers and clustering centers of the clustering algorithms

参考文献 33

[1]	MAHMOUDI-KOHAN N, MOGHADDAM M P, SHEIKH-EL-ESLAMI M K , et al. A three-stage strategy for optimal price offering by a retailer based on clustering techniques[J]. International Journal of Electrical Power & Energy Systems, 2010,32(10):1135-1142.
[2]	MAHMOUDI-KOHAN N, MOGHADDAM M P, SHEIKH-EL-ESLAMI M K . An annual framework for clustering-based pricing for an electricity retailer[J]. Electric Power Systems Research, 2010,80(9):1042-1048.
[3]	宗柳, 李扬, 王蓓蓓 . 计及需求响应的多维度用电特征精细挖掘[J]. 电力系统自动化, 2012,36(20):54-58.
	ZONG Liu, LI Yang, WANG Beibei . Fine-mining of multi-dimension electrical characteristics considering demand response[J]. Automation of Electric Power Systems, 2012,36(20):54-58.
[4]	刘莉, 王刚, 翟登辉 . K-means聚类算法在负荷曲线分类中的应用[J]. 电力系统保护与控制, 2011,39(23):65-68.
	LIU Li, WANG Gang, ZHAI Denghui . Application of K-mans clustering algorithm in load curve classification[J]. Power System Protection and Control, 2011,39(23):65-68.
[5]	李小燕, 丁明, 徐宁舟 . 面向运行规划可靠性的综合聚类负荷模型[J]. 电力系统自动化, 2010,34(8):56-60.
	LI Xiaoyan, DING Ming, XU Ningzhou . Integrative K-mans clustering based load model for operational planning reliability evaluation[J]. Automation of Electric Power Systems, 2010,34(8):56-60.
[6]	李培强, 李欣然, 陈辉华 , 等. 基于模糊聚类的电力负荷特性的分类与综合[J]. 中国电机工程学报, 2005,25(24):73-78.
	LI Peiqiang, LI Xinran, CHEN Huihua , et al. The characteristics classification and synjournal of power load based on fuzzy clustering[J]. Proceedings of the CSEE, 2005,25(24):73-78.
[7]	蒋雯倩, 李欣然, 钱军 . 改进FCM算法及其在电力负荷坏数据处理的应用[J]. 电力系统及其自动化学报, 2011,23(5):1-5.
	JIANG Wenqian, LI Xinran, QIAN Jun . Application of improved FCM algorithm in outlier processing of power load[J]. Proceedings of the Chinese Society of Universities, 2011,23(5):1-5.
[8]	WANG Y, CHEN Q X, KANG C Q , et al. Clustering of electricity consumption behavior dynamics toward big data applications[J]. IEEE Transactions on Smart Grid, 2016,7(5):2437-2447.
[9]	ALBERT A, RAJAGOPAL R . Smart meter driven segmentation: What your consumption says about you[J]. IEEE Transactions on Power Systems, 2013,28(4):4019-4030.
[10]	KWAC J, FLORA J, RAJAGOPAL R . Household energy consumption segmentation using hourly data[J]. IEEE Transactions on Smart Grid, 2014,5(1):420-430.
[11]	MAIGHA, M L . Clustering-based methodology for optimal residential time of use design structure [C]//2014 North American Power Symposium (NAPS). IEEE, 2014: 1-6.
[12]	程祥 . 基于负荷量测数据的电力负荷聚类方法研究[D]. 杭州: 浙江大学, 2017.
	CHENG Xiang . The study of clustering method for power load based on measured data[D]. Hangzhou: Zhejiang University, 2017.
[13]	贾慧敏, 何光宇, 方朝雄 , 等. 用于负荷预测的层次聚类和双向夹逼结合的多层次聚类法[J]. 电网技术, 2007,31(23):33-36.
	JIA Huimin, HE Guangyu, FANG Chaoxiong , et al. Load forecasting by multi-hierarchy clustering combining hierarchy clustering with approaching algorithm in two directions[J]. Power System Technology, 2007,31(23):33-36.
[14]	KOIVISTO M, HEINE P, MELLIN I , et al. Clustering of connection points and load modeling in distribution systems[J]. IEEE Transactions on Power Systems, 2013,28(2):1255-1265.
[15]	ZHOU K L, YANG S L, SHEN C . a review of electric load classification in smart grid environment[J]. Renewable and Sustainable Energy Reviews, 2013,24:103-110.
[16]	王茜, 李皓然, 王新娜 , 等. 基于混沌类电磁算法优化支持向量机的短期负荷预测[J]. 计算技术与自动化, 2019,38(4):15-18.
	WANG Qian, LI Haoran, WANG Xinna , et al. Short term load forecasting based on SVM and chaos electromagnetic algorithm[J]. Computing Technology and Automation, 2019,38(4):15-18.
[17]	林顺富, 田二伟, 符杨 , 等. 基于信息熵分段聚合近似和谱聚类的负荷分类方法[J]. 中国电机工程学报, 2017,37(8):2242-2252.
	LIN Shunfu, TIAN Erwei, FU Yang , et al. Power load classification method based on information entropy piecewise aggregate approximation and spectral clustering[J]. Proceedings of the CSEE, 2017,37(8):2242-2252.
[18]	LE RAY G, PINSON P . Online adaptive clustering algorithm for load profiling[J]. Sustainable Energy, Grids and Networks, 2019,17:100181.
[19]	孙雅明, 王晨力, 张智晟 , 等. 基于蚁群优化算法的电力系统负荷序列的聚类分析[J]. 中国电机工程学报, 2005,25(18):40-45.
	SUN Yaming, WANG Chenli, ZHANG Zhisheng , et al. Clustering analysis of power system load series based on ant colony optimization algorithm[J]. Proceedings of the CSEE, 2005,25(18):40-45.
[20]	张江林, 张亚超, 洪居华 , 等. 基于离散小波变换和模糊K-modes的负荷聚类算法[J]. 电力自动化设备, 2019,39(2):100-106, 122.
	ZHANG Jianglin, ZHANG Yachao, HONG Juhua , et al. A load clustering algorithm based on discrete wavelet transform and fuzzy K-modes[J]. Electric Power Automation Equipment, 2019,39(2):100-106, 122.
[21]	彭显刚, 赖家文, 陈奕 . 基于聚类分析的客户用电模式智能识别方法[J]. 电力系统保护与控制, 2014,42(19):68-73.
	PENG Xiangang, LAI Jiawen, CHEN Yi . Application of clustering analysis in typical power consumption profile analysis[J]. Power System Protection and Control, 2014,42(19):68-73.
[22]	SIDERATOS G, IKONOMOPOULOS A, HATZIARGYRIOU N D . A novel fuzzy-based ensemble model for load forecasting using hybrid deep neural networks[J]. Electric Power Systems Research, 2020,178:106025.
[23]	刘全明, 辛阳阳 . 基于卷积神经网络特征图聚类的人脸表情识别[J]. 计算技术与自动化, 2020,39(1):106-111.
	LIU Quanming, XIN Yangyang . Facial expression recognition based on convolutional neural network feature map clustering[J]. Computing Technology and Automation, 2020,39(1):106-111.
[24]	李龙龙 . 半监督聚类算法研究及植物叶片识别应用[D]. 杨凌: 西北农林科技大学, 2017.
	LI Longlong . Semi-supervised clustering and its application on plant leaf image recognition[D]. Yangling: Northwest A & F University, 2017.
[25]	NAN F, LI Y, JIA X Y , et al. Application of improved SOM network in gene data cluster analysis[J]. Measurement, 2019,145:370-378.
[26]	SAHA S, KAUSHIK K, ALOK A K , et al. Multi-objective semi-supervised clustering of tissue samples for cancer diagnosis[J]. Soft Computing, 2016,20(9):3381-3392.
[27]	OROZCO-DUQUE A, BUSTAMANTE J, CASTELLANOS-DOMINGUEZ G . Semi-supervised clustering of fractionated electrograms for electroanatomical atrial mapping[J]. BioMedical Engineering OnLine, 2016,15(1):1-19.
[28]	李巧兰 . 基于约束的半监督聚类的图像分割算法研究[D]. 西安: 西安电子科技大学, 2014.
	LI Qiaolan . Semi-supervised clustering based on constraints for images segmentation[D]. Xi’an: Xidian University, 2014.
[29]	李亚文 . 鲁棒半监督模糊聚类分割算法研究[D]. 西安: 西安邮电大学, 2018.
	LI Yawen . Research on robust segmentation algorithm based on semi-supervised fuzzy clustering[D]. Xi’an: Xi’an University of Posts and Telecommunications, 2018.
[30]	梁辰, 李成海 . 一种新的半监督入侵检测方法[J]. 计算机科学, 2016,43(5):87-90.
	LIANG Chen, LI Chenghai . Novel intrusion detection method based on semi-supervised clustering[J]. Computer Science, 2016,43(5):87-90. doi: 10.1063/1.31324 URL
[31]	文翰, 肖南峰 . 基于强类别特征近邻传播的半监督文本聚类[J]. 模式识别与人工智能, 2014,27(7):646-654.
	WEN Han , XIAO NanFeng. A semi-supervised text clustering based on strong classification features affinity propagation[J]. Pattern Recognition and Artificial Intelligence, 2014,27(7):646-654.
[32]	CHICCO G . Overview and performance assessment of the clustering methods for electrical load pattern grouping[J]. Energy, 2012,42(1):68-80. doi: 10.1016/j.energy.2011.12.031 URL
[33]	邱东 . 多指标综合评价方法[J]. 统计研究, 1990,7(6):43-51.
	QIU Dong . Multi index comprehensive evaluation method[J]. Statistical Research, 1990,7(6):43-51.

基于改进蚁群算法的电力负荷半监督聚类

Research on Power Load Semi-supervised Clustering Based on Improved Ant Colony Algorithm

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 33

相关文章 11

编辑推荐

Metrics

本文评价

[1]	芮松华，刘海璇，王洪波，尹德扬，梅飞. 基于遗传-蚁群算法的交直流配电网分布式电源优化配置[J]. 电力建设, 2019, 40(4): 9-17.
[2]	周冰钰，刘博，王丹，兰宇，马喜然，孙冬冬，霍秋屹. 基于自组织中心K-means算法的用户互动用电行为聚类分析[J]. 电力建设, 2019, 40(1): 68-76.
[3]	刘琪琛, 雷景生, 郝珈玮,黄燕刚,李强,罗海波. 基于Spark平台和并行随机森林回归算法的短期电力负荷预测[J]. 电力建设, 2017, 38(10): 84-.
[4]	雷景生,郝珈玮,朱国康. 基于“分层-汇集”模型的短期电力负荷预测[J]. 电力建设, 2017, 38(1): 68-.
[5]	任炳俐，张振高，王学军，李慧，闫大威，张沛. 基于用电采集数据的需求响应削峰潜力评估方法[J]. 电力建设, 2016, 37(11): 64-.
[6]	周海强, 钱礼明, 吴水军, 陈晶, 杨杨, 万雄彪. 计及励磁电压变化的同步发电机抛载试验参数辨识方法[J]. 电力建设, 2015, 36(8): 130-134.
[7]	刘吉成,常昊,王素花. 基于Pareto蚁群算法的风电项目工期-成本-质量均衡优化[J]. 电力建设, 2014, 35(4): 127-131.
[8]	林子钊 . 基于数据挖掘技术的电力网络参数估计方法[J]. 电力建设, 2007, 28(1): 0-0.
[9]	梁平,樊福梅,曾东平 . 电力负荷非线性预报与分析[J]. 电力建设, 2004, 25(3): 4-0.
[10]	罗维平 . 一种新型电力负荷微机监测系统[J]. 电力建设, 2001, 22(11): 52-0.
[11]	叶舟,陈康民 . 温斯特线性与季节性指数平滑法在电力负荷预测中的应用及改进[J]. 电力建设, 2000, 21(8): 0-0.