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

Jaime Buitrago, Ahmed Abdulaal, Shihab S Asfour

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

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
Volume35
Issue number4
DOIs
StatePublished - 2015

Fingerprint

Electric loads
Pattern Classification
Parameter estimation
Pattern recognition
Artificial Neural Network
Parameter Estimation
Clustering
Neural networks
Hybrid systems
Clustering algorithms
Smart Grid
Number of Clusters
Hybrid Systems
Planning
Regulator
Model
Grouping
Clustering Algorithm
Demand
Classify

Keywords

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

ASJC Scopus subject areas

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

Cite this

Electric load pattern classification using parameter estimation, clustering and artificial neural networks. / Buitrago, Jaime; Abdulaal, Ahmed; Asfour, Shihab S.

In: International Journal of Power and Energy Systems, Vol. 35, No. 4, 2015, p. 167-174.

Research output: Contribution to journalArticle

@article{07d6478d729343a1b2ea8629f9cf62ff,
title = "Electric load pattern classification using parameter estimation, clustering and artificial neural networks",
abstract = "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.",
keywords = "ANN, Clustering, Demand, Framework, Parameter estimation, Pattern recognition",
author = "Jaime Buitrago and Ahmed Abdulaal and Asfour, {Shihab S}",
year = "2015",
doi = "10.2316/Journal.203.2015.4.203-6216",
language = "English (US)",
volume = "35",
pages = "167--174",
journal = "International Journal of Power and Energy Systems",
issn = "1078-3466",
publisher = "ACTA Press",
number = "4",

}

TY - JOUR

T1 - Electric load pattern classification using parameter estimation, clustering and artificial neural networks

AU - Buitrago, Jaime

AU - Abdulaal, Ahmed

AU - Asfour, Shihab S

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - ANN

KW - Clustering

KW - Demand

KW - Framework

KW - Parameter estimation

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=84958249200&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958249200&partnerID=8YFLogxK

U2 - 10.2316/Journal.203.2015.4.203-6216

DO - 10.2316/Journal.203.2015.4.203-6216

M3 - Article

AN - SCOPUS:84958249200

VL - 35

SP - 167

EP - 174

JO - International Journal of Power and Energy Systems

JF - International Journal of Power and Energy Systems

SN - 1078-3466

IS - 4

ER -