A new method for pattern recognition in load profiles to support decision-making in the management of the electric sector

Abstract This work presents a method for the selection, typification and clustering of load curves (STCL) capable of recognizing consumption patterns in the electricity sector. The algorithm comprises four steps that extract essential features from the load curve of residential users with an emphasis on their seasonal and temporal profile, among others. The method was successfully implemented and tested in the context of an energy efficiency program carried out by the Energy Company of Maranhao (Brazil). This program involved the replacement of refrigerators in low-income consumers’ homes in several towns located within the state of Maranhao (Brazil). The results were compared with a well known time series clustering method already established in the literature, Fuzzy CMeans (FCM). The results reveal the viability of the STCL method in recognizing patterns and in generating conclusions coherent with the reality of the electricity sector. The proposed method is also useful to support decision-making at management level.

[1]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[2]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[3]  R. E. Abdel-Aal,et al.  Modeling and forecasting electric daily peak loads using abductive networks , 2006 .

[4]  Joseph Janes.  Categorical relationships: chi‐square , 2001 .

[5]  Gregory Piatetsky-Shapiro,et al.  Data mining and knowledge discovery 1996 to 2005: overcoming the hype and moving from “university” to “business” and “analytics” , 2007, Data Mining and Knowledge Discovery.

[6]  A.H. Nizar,et al.  Load profiling and data mining techniques in electricity deregulated market , 2006, 2006 IEEE Power Engineering Society General Meeting.

[7]  A. Seppala,et al.  Statistical distribution of customer load profiles , 1995, Proceedings 1995 International Conference on Energy Management and Power Delivery EMPD '95.

[8]  Jian Pei,et al.  Mining frequent patterns without candidate generation , 2000, SIGMOD 2000.

[9]  Iñigo Monedero,et al.  Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision trees , 2012 .

[10]  Edmilson Moutinho dos Santos,et al.  The risks of an energy efficiency policy for buildings based solely on the consumption evaluation of final energy , 2013 .

[11]  Nabeel Tawalbeh.  Daily load profile and monthly power peaks evaluation of the urban substation of the capital of Jordan Amman , 2012 .

[12]  K.L. Lo,et al.  Application of Fuzzy Clustering to Determine Electricity Consumers' Load Profiles , 2006, 2006 IEEE International Power and Energy Conference.

[13]  S. Chiu,et al.  A cluster estimation method with extension to fuzzy model identification , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[14]  S. Tso,et al.  Study of climatic effects on peak load and regional similarity of load profiles following disturbances based on data mining , 2006 .

[15]  Fábio Gonçalves Jota,et al.  Building load management using cluster and statistical analyses , 2011 .

[16]  N. D. Hatziargyriou,et al.  A database system for power systems customers and energy efficiency programs , 2011 .

[17]  Qinghua Hu,et al.  Dynamic time warping constraint learning for large margin nearest neighbor classification , 2011, Inf. Sci..

[18]  Ashwani Kumar,et al.  Electricity price forecasting in deregulated markets: A review and evaluation , 2009 .

[19]  F. Gubina,et al.  Determining the load profiles of consumers based on fuzzy logic and probability neural networks , 2004 .

[20]  T. Warren Liao,et al.  Clustering of time series data - a survey , 2005, Pattern Recognit..

[21]  James M. Keller,et al.  Fuzzy Models and Algorithms for Pattern Recognition and Image Processing , 1999 .

[22]  Mia Hubert,et al.  An adjusted boxplot for skewed distributions , 2008, Comput. Stat. Data Anal..

[23]  M. K. Soni,et al.  Artificial Neural Network-Based Peak Load Forecasting Using Conjugate Gradient Methods , 2002, IEEE Power Engineering Review.

[24]  Daswin De Silva,et al.  A Data Mining Framework for Electricity Consumption Analysis From Meter Data , 2011, IEEE Transactions on Industrial Informatics.

[25]  F. Gubina,et al.  A methodology to classify distribution load profiles , 2002, IEEE/PES Transmission and Distribution Conference and Exhibition.

[26]  Z. Zakaria,et al.  Cluster validity analysis for electricity load profiling , 2010, 2010 IEEE International Conference on Power and Energy.

[27]  Z. Styczynski,et al.  Application of statistical and neural approaches to the daily load profiles modelling in power distribution systems , 1999, 1999 IEEE Transmission and Distribution Conference (Cat. No. 99CH36333).

[28]  Motomasa Daigo,et al.  Factor analysis and pattern decomposition method , 2005, International Symposium on Multispectral Image Processing and Pattern Recognition.

[29]  Thomas W. O'Gorman,et al.  A comparison of an adaptive two-sample test to the t-test and the rank-sum test , 1997 .

[30]  James C. Bezdek,et al.  Partially supervised clustering for image segmentation , 1996, Pattern Recognit..