Hohai University

Xi'an Jiaotong University

State Grid Corporation of China

State Grid Jiangsu Electric Power Company

China Electric Power Research Institute

Jiangsu Electric Power Company

Jiangsu Electric Power Company Nanjing Power Supply Company

Nanjinghehai Technology Limited Company

Kun Yu

Xingying Chen

Hong Zhu

Lei Wei

Chunning Wang

Jianguo Yao

Shihai Yang

Kai Chen

Xiaodong Cao

Peifeng Shen

Jing Xiao

Qirui Qiu

Yingchen Liao

Min Cai

Liyin Zhang

Yuxiong Huang

Gengfeng Li

Tingji Chen

Jiangfeng Jiang

A method of a power user classification based on distributed K-means, a storage medium and a classification device are provided. The method includes: obtaining, by N load aggregators, power consumption data of power users managed by respective load aggregators; performing, by each load aggregator, a normalization operation on time series load data of the power users managed by the load aggregator; forming a N&#xd7;N dimensional adjacency matrix A; performing K-means clustering on normalized time series load data, to obtain the respective centroids and user groups characterized by the respective centroids; sharing, by the respective load aggregators, the centroids and the number of users under the respective centroids based on the adjacency matrix A, and obtaining consistent centroids by multiple load aggregators; after an overall iteration ends, obtaining, by the respective load aggregators, the consistent centroids consistent with the K-means centroid based on global data, to realize user classification.

Method of power user classification based on distributed K-means, storage medium and classification device

smart power distribution system and a method to progressively dispatch the power is described. The method steps are all automatic and self-adaptive. The method can be executed in an unattended manner to automatically correlate real time data vs. historical data, planning data vs. operation data. Based on a long cycle periodical variation and short-term random variations in load, and taking into account the temporary load power supply and maintenance needs, a multi-stage progressive multiple time scales optimal dispatching method is developed, including the distributed power, micro-grids, energy storage devices, electric vehicles charge-discharge facility and other elements of the Intelligent power distribution systems, to achieve coordinated operation of the network, power, load resources to ensure a continuous safe and reliable smart power distribution system operated at high quality and efficiency.

Progressive optimization dispatching method of smart distribution system

Growing community of inventors

Nanjing, China

Kun Yu