Fuzzy C-means clustering based on micro-spatial analysis for electricity load profile characterization.
As the rising of electricity demand, electricity load profile characterization (ELPC) is the integral aspect in planning, operating system, and distribution network development. The approach in the existing ELPC is still relatively macro in nature and does not involve other aspects outside the elect...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Advanced Engineering and Science
2023
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/104976/1/JasrulJamaniJamian2023_FuzzyCMeansClusteringBasedonMicroSpatial.pdf http://eprints.utm.my/104976/ http://dx.doi.org/10.11591/ijeecs.v30.i1.pp33-45 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | As the rising of electricity demand, electricity load profile characterization (ELPC) is the integral aspect in planning, operating system, and distribution network development. The approach in the existing ELPC is still relatively macro in nature and does not involve other aspects outside the electricity variable, so the results tend to be biased for areas experiencing rapid land use changes. Therefore, this paper proposes an ELPC approach based on micro-spatial. Microspatial analysis is done by dividing area in the form of the smallest grids involving various electrical, demographic, geographic and socio-economic variables, which are then grouped using adaptive clustering based on fuzzy C-means (FCM). The adaptive clustering algorithm is proven to be able to determine the degree of membership of each grid data against each cluster with the ability to determine the number of clusters automatically according to the attribute data provided. The ELPC results which consist of 5 clusters are then analyzed using descriptive statistic, plotted, and mapped to obtain more accurate and realistic load characteristics in accordance with the pattern and geographical conditions of the region, so that the results can be used as a reference in load forecasting, network development, and distributed generation (DG) integration. |
|---|