PP: Data-driven classification of residential energy consumption patterns by means of functional connectivity networks
2024-09-05 17:56:44
Purpose
Implement a good user aggregation and classification.
or to assess the interrelation patterns between user profiles.
Data
i. daily temperature and load profiles sampled at hourly for one year.
ii. 2201 customers
iii.
Methodology
1. correlation matrix R of all pairs of users;
2. transform the correlation matrix R into a distance matrix D;
?? why?因为相似度和距离是反的, 相似度越大,距离越近, 显然以距离作为边权重更合适.
3. network construction;
each user is a node; the weighted connections are established between all of them; weight eij = Dij.
4. extract the MST network
5. community detection
Newman.
Results
1. raw data: 各种distribution; average curve.
2. distance matrix: 热度图;
3. peak time??
4. 缺少与其他方法的比较,也没有说明具体分为了多少类,每个类的实际time series pattern是啥.反正乱七八糟的,生气.
最新文章
- test1.xlsx
- Pegasos: Primal Estimated sub-GrAdient Solver for SVM
- Linux远程传输命令之scp使用方法
- hibernate的save()和persit()之间的区别
- java复习-多线程
- Debian 安装 vmware-tools 手记
- BZOJ4424: Cf19E Fairy
- MySQL 中基于 XA 实现的分布式事务
- SpringBoot整合Jsp和Thymeleaf (附工程)
- Hybrid App—Hybrid App开发模式介绍和各种开发模式对比
- Jenkins redeploy artifacts
- HDU 2075 A|B?
- Android x86 下运行纯ARM版APP
- 【svn】svn的使用
- WEB UI 界面打印PDF
- DevExpress DateEdit控件选择精确到秒
- 全面认识一下.NET 4.0的缓存功能 (转)
- NGINX宏观手记(变量|配置)
- Oracle如何实现跨库查询
- sencha touch JsonP 自动提示消息 masked