Title :
Electrical Load Pattern Grouping Based on Centroid Model With Ant Colony Clustering
Author :
Chicco, Gianfranco ; Ionel, Octavian-Marcel ; Porumb, Radu
Author_Institution :
Energy Dept., Politec. di Torino, Turin, Italy
Abstract :
Load pattern clustering based on the shape of the electricity consumption is a key tool to provide enhanced knowledge on the nature of the consumption and assist meaningful customer partitioning. This paper presents new developments to group the load patterns using an initial set of centroids specified according to a user-defined centroid model. The original Electrical Pattern Ant Colony Clustering (EPACC) algorithm is illustrated, highlighting its characteristics and parameters, with centroids evolution during the iterative process until stabilization. The EPACC results are compared with those obtained from the classical k-means algorithm to group the representative load patterns taken from a set of non-residential customers in typical weekdays.
Keywords :
ant colony optimisation; iterative methods; load distribution; power consumption; EPACC algorithm; classical k-means algorithm; customer partitioning; electrical load pattern grouping; electrical pattern ant colony clustering algorithm; electricity consumption; iterative process; load pattern clustering; user-defined centroid model; Algorithm design and analysis; Clustering algorithms; Correlation; Electricity; Load modeling; Radiation detectors; Vectors; Ant colony; categorization; centroid model; clustering; customer group; electrical load pattern;
Journal_Title :
Power Systems, IEEE Transactions on
DOI :
10.1109/TPWRS.2012.2220159