Identification of typical load profiles using K-means clustering algorithm
Typical load profile (TLP) describes the hourly values of electricity consumption on a daily basis, and is associated to a certain consumer category, for certain specific operating conditions. TLPs can be defined for residential, small industrial, commercial or services consumers, for warm season an...
| Main Authors: | , , |
|---|---|
| Format: | Conference Paper |
| Published: |
2014
|
| Online Access: | http://hdl.handle.net/20.500.11937/55566 |
| Summary: | Typical load profile (TLP) describes the hourly values of electricity consumption on a daily basis, and is associated to a certain consumer category, for certain specific operating conditions. TLPs can be defined for residential, small industrial, commercial or services consumers, for warm season and cold season, for week days and weekends. In this paper, the daily load curves of a residential feeder are grouped using K-Means clustering algorithm to classify the load curves. The paper further explores the relationship between load profiles and seasonal periods to identify season types. The paper also obtains truncated discrete Fourier transform coefficients for the load curves to reduce the dimensionality of the clustering problem. Application of K-Means clustering on the discrete Fourier coefficients exhibits results that are identical to the clusters of the original load curves. |
|---|