Electric load pattern classification using parameter estimation, clustering and artificial neural networks

Jaime Buitrago, Ahmed Abdulaal, Shihab Asfour

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


The smart grid allows for capturing vital information about consumer demand patterns through smart metering. This enables utilities to effectively plan new tariffs, demand-side management programs, energy production and transmission, as well as improve the overall grid security. However, the immense amount of data makes the analysis process increasingly difficult. Therefore, grouping of consumer data with similar demand patterns is necessary. In this paper, we propose a hybrid framework for the unbiased classification of consumer demand patterns. The hybrid system consists of a parameter estimation model, a clustering model, and an artificial neural network (ANN). The smart metering data are first processed through a parameter estimation model and a clustering algorithm producing distinct impartial classification clusters. The results are then fed to an ANN as training data for learning. Once the load patterns are learned, the model can be used to further classify new consumers into a demand pattern. The ANN provides fast and accurate clustering performance without underlying assumptions about shape or class. An analysis of the optimal number of clusters is presented. Results indicate that clusters with distinguishable characteristics are achieved and we demonstrate how regulators can make use of this method in demand curtailment planning.

Original languageEnglish (US)
Pages (from-to)167-174
Number of pages8
JournalInternational Journal of Power and Energy Systems
Issue number4
StatePublished - 2015


  • ANN
  • Clustering
  • Demand
  • Framework
  • Parameter estimation
  • Pattern recognition

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Applied Mathematics


Dive into the research topics of 'Electric load pattern classification using parameter estimation, clustering and artificial neural networks'. Together they form a unique fingerprint.

Cite this