An integrated ANN-K-Means algorithm for improved performance assessment of electricity distribution units

This study proposes a non-parametric efficiency frontier analysis method based on artificial neural network (ANN) and K-Means algorithm for measuring efficiency of electricity distribution units (EDUs). Effect of return to scale of EDU on its efficiency is included and EDU used for correction is selected based on its scale. K-Means algorithm is used to cluster EDUs to increase their homogeneousness by handling outlines and noise. Proposed approach was applied to 31 EDUs in Iran. This is first study using integrated ANN-K-Means algorithm for improved performance assessment of EDUs. ANN-K-Means algorithm is compared with earlier models to show its advantages and superiorities in prediction and forecasting.

[1]  Michael G. Pollitt,et al.  Ownership and Performance in Electric Utilities , 1998 .

[2]  B. Golany,et al.  Measuring efficiency of power plants in Israel by data envelopment analysis , 1994 .

[3]  Christopher R. Knittel.  Alternative Regulatory Methods and Firm Efficiency: Stochastic Frontier Evidence from the U.S. Electricity Industry , 2002, Review of Economics and Statistics.

[4]  Ali Azadeh,et al.  Forecasting electrical consumption by integration of Neural Network, time series and ANOVA , 2007, Appl. Math. Comput..

[5]  H. Rudnick,et al.  DEA efficiency for the determination of the electric power distribution added value , 2004, IEEE Transactions on Power Systems.

[6]  Paul L. Joskow,et al.  Incentive Regulation For Electric Utilities , 1986 .

[7]  Soo-Uk Park,et al.  The efficiency of conventional fuel power plants in South Korea: A comparison of parametric and non-parametric approaches , 2000 .

[8]  Wade D. Cook,et al.  Evaluating power plant efficiency: a hierarchical model , 2005, Comput. Oper. Res..

[9]  Tooraj Jamasb,et al.  Benchmarking and incentive regulation of quality of service: an application to the UK electricity distribution networks , 2005 .

[10]  Finn R. Førsund,et al.  Productivity development of Norwegian electricity distribution utilities , 1998 .

[11]  David E. Dismukes,et al.  A data envelopment analysis of the levels and determinants of coal-fired electric power generation performance , 2000 .

[12]  Daniel Santín,et al.  The measurement of technical efficiency: a neural network approach , 2004 .

[13]  Seyed Farid Ghaderi,et al.  An integrated artificial neural network and fuzzy clustering algorithm for performance assessment of decision making units , 2007, Appl. Math. Comput..

[14]  Desheng Dash Wu,et al.  Using DEA-neural network approach to evaluate branch efficiency of a large Canadian bank , 2006, Expert Syst. Appl..

[15]  Alice Shiu,et al.  A data envelopment analysis of the efficiency of China’s thermal power generation , 2001 .

[16]  Mika Goto,et al.  Comparison of Productive and Cost Efficiencies Among Japanese and US Electric Utilities , 1998 .

[17]  L. J. Hill,et al.  A primer on incentive regulation for electric utilities , 1995 .

[18]  Michael Y. Hu,et al.  Two-Group Classification Using Neural Networks* , 1993 .

[19]  Antreas D. Athanassopoulos,et al.  A Comparison of Data Envelopment Analysis and Artificial Neural Networks as Tools for Assessing the Efficiency of Decision Making Units , 1996 .

[20]  Ali Azadeh,et al.  Studying Impact of Decision Making Units Features on Efficiency by Integration of Data Envelopment Analysis and Data Mining Tools , 2007, OR.

[21]  Shouhong Wang,et al.  Adaptive non-parametric efficiency frontier analysis: a neural-network-based model , 2003, Comput. Oper. Res..

[22]  Christian A. Ruzzier,et al.  The Case for International Coordination of Electricity Regulation: Evidence from the Measurement of Efficiency in South America , 2002 .

[23]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

[24]  Marcelo Resende,et al.  Relative efficiency measurement and prospects for yardstick competition in Brazilian electricity distribution , 2002 .

[25]  Tooraj Jamasb,et al.  BENCHMARKING AND REGULATION OF ELECTRICITY TRANSMISSION AND DISTRIBUTION UTILITIES: LESSONS FROM INTERNATIONAL EXPERIENCE , 2001 .

[26]  Ali Azadeh,et al.  Performance assessment of electric power generations using an adaptive neural network algorithm , 2007 .

[27]  Toshiyuki Sueyoshi,et al.  Slack-adjusted DEA for time series analysis: Performance measurement of Japanese electric power generation industry in 1984-1993 , 2001, Eur. J. Oper. Res..

[28]  Parag C. Pendharkar,et al.  Technical efficiency-based selection of learning cases to improve forecasting accuracy of neural networks under monotonicity assumption , 2003, Decis. Support Syst..

[29]  Dag Fjeld Edvardsen,et al.  International benchmarking of electricity distribution utilities , 2003 .