Name
Abstract | ||
|---|---|---|
With abundant availability of electricity customers load data, and the growing trend toward smart distribution grid, there is a need for more efficient approaches to exploit the valuable customer load information from the high-resolution data collected from customers by automatic meter reading (AMR). New effective clustering methods such as affinity propagation are one of the ways to tackle this issue by improving load prediction techniques and devising efficient pricing schemes. In this paper, an affinity propagation (AP) algorithm is used to cluster customer load data and generate typical load profiles (TLP) for clusters. AP is a new algorithm and has no need to have a predefined number of clusters. Clustering results are compared with some traditional methods such as k-mean, k-medoid, and spectral clustering. Also, the AP results are evaluated by computing a range of well-known clustering performance indices. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/EIT.2019.8833693 | 2019 IEEE International Conference on Electro Information Technology (EIT) |
Keywords | Field | DocType |
Affinity Propagation,Clustering,TLP,K-means,K-medoids,Spectral Clustering | Data mining,k-means clustering,Spectral clustering,Affinity propagation,Computer science,Computer network,Exploit,Load profile,Automatic meter reading,Cluster analysis,k-medoids | Conference |
ISSN | ISBN | Citations |
2154-0357 | 978-1-7281-0928-2 | 0 |
PageRank | References | Authors |
0.34 | 5 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ahmad Khaled Zarabie | 1 | 0 | 1.35 |
| Sahar Lashkarbolooki | 2 | 0 | 0.34 |
| Sanjoy Das | 3 | 226 | 39.18 |
| Kumarsinh Jhala | 4 | 3 | 1.51 |
| Anil Pahwa | 5 | 59 | 12.26 |