Discovering and labelling of temporal granularity patterns in electric power demand with a Brazilian case study

Abstract

Clustering is commonly used to group data in order to represent the behaviour of a system as accurately as possible by obtaining patterns and profiles. In this paper, clustering is applied with partitioning-clustering techniques, specifically, Partitioning around Medoids (PAM) to analyse load curves from a city of South-eastern Brazil in São Paulo state. A top-down approach in time granularity is performed to detect and to label profiles which could be affected by seasonal trends and daily/hourly time blocks. Time-granularity patterns are useful to support the improvement of activities related to distribution, transmission and scheduling of energy supply. Results indicated four main patterns which were post-processed in hourly blocks by using shades of grey to help final-user to understand demand thresholds according to the meaning of dark grey, light grey and white colours. A particular and different behaviour of load curve was identified for the studied city if it is compared to the classical behaviour of urban cities.