Identifying irregularity electricity usage of customer behaviors using logistic regression and linear discriminant analysis

This study aims to implement a machine learning technique in identifying the irregularities of customer behavior on the use of prepaid electricity pulses. The methods used are Linear Discriminant Analysis and Logistic Regression. The performance of the classification system will be evaluated using the 10-fold cross-validation technique. Validation results are measured using accuracy, precision and recall values. In this research shows that the use of machine learning technique has a good performance in classification of electrical consumption behavior. Experimental results with the different amount of data testing indicate that Logistic Regression method has high accuracy, precision, and recall value when compared with Linear Discriminant Analysis that is 100%. This is due to Logistic Regression method can predict irregularities accurately because the addition of the amount of data does not affect the performance of the method.

[1]  Cheng Li,et al.  Fisher Linear Discriminant Analysis , 2014 .

[2]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[3]  T. Satyanarayana Murthy,et al.  Detecting unusual customer consumption profiles in power distribution systems — APSPDCL , 2013, 2013 IEEE International Conference on Computational Intelligence and Computing Research.

[4]  Vitaly Ford,et al.  Decision Tree Learning for Fraud Detection in Consumer Energy Consumption , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[5]  Neeraj Kumar,et al.  Decision Tree and SVM-Based Data Analytics for Theft Detection in Smart Grid , 2016, IEEE Transactions on Industrial Informatics.

[6]  Lingfeng Wang,et al.  Enhanced encoding technique for identifying abnormal energy usage pattern , 2012, 2012 North American Power Symposium (NAPS).

[7]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[8]  William Eberle,et al.  Smart grid energy fraud detection using artificial neural networks , 2014, 2014 IEEE Symposium on Computational Intelligence Applications in Smart Grid (CIASG).

[9]  S. K. Joshi,et al.  Electricity theft detection techniques for metered power consumer in GUVNL, GUJARAT, INDIA , 2015, 2015 Clemson University Power Systems Conference (PSC).

[10]  Jin-Ho Shin,et al.  Conditional abnormality detection based on AMI data mining , 2016 .

[11]  Pengfei Shi,et al.  A note on two-dimensional linear discriminant analysis , 2008, Pattern Recognit. Lett..

[12]  A. N. de Souza,et al.  Detection and Identification of Abnormalities in Customer Consumptions in Power Distribution Systems , 2011, IEEE Transactions on Power Delivery.

[13]  Subir Sen,et al.  Advanced metering infrastructure analytics — A Case Study , 2014, 2014 Eighteenth National Power Systems Conference (NPSC).