| 引用本文: | 苏适,李康平,严玉廷,陆海,汪新康,刘力铭,王飞,董凌.基于密度空间聚类和引力搜索算法的居民负荷用电模式分类模型[J].电力自动化设备,2018,(1): |
| SU Shi,LI Kangping,YAN Yuting,LU Hai,WANG Xinkang,LIU Liming,WANG Fei,DONG Ling.Classification model of residential power consumption mode based on DBSCAN and gravitational search algorithm[J].Electric Power Automation Equipment,2018,(1): |
|
| 本文已被：浏览 5030次 下载 1696次 |
|
|
|
| 基于密度空间聚类和引力搜索算法的居民负荷用电模式分类模型 |
|
苏适1, 李康平2, 严玉廷1, 陆海1, 汪新康2, 刘力铭2, 王飞2,3, 董凌4
|
|
1.云南电网有限责任公司电力科学研究院，云南 昆明 650217;2.华北电力大学 新能源电力系统国家重点实验室，河北 保定 071003;3.美国伊利诺伊大学厄巴纳-香槟分校电气与计算机工程系，美国 厄巴纳 61802;4.国网青海省电力公司，青海 西宁 810008
|
|
| 摘要: |
| 居民用户用电模式分类研究可为需求侧响应方案设计、负荷特性分析及其高精度预测提供支撑。首先，利用基于密度的空间聚类算法提取得到用户的典型用电模式；然后，考虑每天不同时段及季节变换对用户用电行为的影响，提取能够描述用户在不同时间尺度下用电行为的6个特征；在此基础上，提出了一种基于引力搜索算法的用户用电模式分类模型；最后，对实测居民用电数据进行聚类，并对各类用户的用电模式及其参与需求侧响应的潜力进行了分析。 |
| 关键词: 用电模式 聚类算法 特征提取 分类 引力搜索算法 密度空间聚类 |
| DOI：10.16081/j.issn.1006-6047.2018.01.019 |
| 分类号:TM761 |
| 基金项目:云南省新能源重大科技专项(2013ZB005)；云南电网有限责任公司科技项目(YNKJQQ00000280)；华北电力大学新能源电力系统国家重点实验室开放课题资助项目(LAPS15009, LAPS16007, LAPS16015) |
|
| Classification model of residential power consumption mode based on DBSCAN and gravitational search algorithm |
|
SU Shi1, LI Kangping2, YAN Yuting1, LU Hai1, WANG Xinkang2, LIU Liming2, WANG Fei2,3, DONG Ling4
|
|
1.Electric Power Research Institute of Yunnan Power Grid Co.,Ltd.,Kunming 650217, China;2.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Source, North China Electric Power University, Baoding 071003, China;3.Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana 61802, USA;4.State Grid Qinghai Province Electric Power Company, Xining 810008, China
|
| Abstract: |
| The research on the classification of residential power consumption modes can provide support for the design of demand side response scheme, the load characteristic analysis and its high precision prediction. Firstly, the typical power consumption modes of customers are extracted by DBSCAN(Density-Based Spatial Clustering of Applications with Noise). Then, considering the effect of different periods in a day and season change on the power consumption behaviors of customers, six features are extracted, which can describe the power consumption behaviors of customers in different time scales. Based on this, a classification model of residential power consumption mode based on gravitational search algorithm is proposed. Finally, measured residential power consumption data are clustered and the power consumption modes of customers of each cluster and as well as their potentials for participation in demand side response are analyzed. |
| Key words: power consumption mode clustering algorithms feature extraction classification gravitational search algorithm density-based spatial clustering |
