نوع مقاله : مقاله پژوهشی

نویسندگان

1 هیئت علمی و مدیر گروه مدیریت صنعتی دانشگاه سمنان

2 دانشگاه آزاد رشت

3 گروه مدیریت صنعتی، دانشگاه سمنان

4 دانشجوی دانشگاه آزاد رشت

چکیده

انتخاب متغیرهای ورودی و خروجی در تعیین نمرات کارایی تحلیل پوششی داده‌ها از اهمیت فراوانی برخوردار است. در این پژوهش با استفاده از شبکه عصبی مصنوعی به تعیین ورودی‌ها و خروجی‌های‌ شرکت‌های برق منطقه‌ای پرداخته شده است. کاربرد شبکه عصبی در انتخاب ورودی‌ها و خروجی‌های شرکت‌های برق منطقه‌ای امری است که در ادبیات موضوع سابقه نداشته و مزیت اصلی روش پیشنهادی محسوب می‌شود. به‌‌منظور آموزش شبکه عصبی دو لایه MLP، از روش آموزش پس از انتشار خطای ارتجاعی استفاده گردید؛ پس از آموزش شبکه عصبی، عملکرد شبکه عصبی با استفاده از الگوهای تست، مورد بررسی قرار گرفت. مقدار RMSE مریوط به 15 الگوی تست برابر 0269/0 به‌دست آمد که نشان‌دهنده دقت بالای شبکه آموزش داده شده است. تحلیل حساسیت پارامترهای مورد بررسی که همان ورودی‌ها و خروجی‌های تحلیل پوششی داده‌ها هستند، با افزایش ده درصدی پارامترها نسبت به حالت قبل از افزایش انجام شده و میانگین خطای نسبی خروجی برای پارامترهای شبکه عصبی محاسبه شده است. بر اساس میزان میانگین خطای نسبی خروجی، ورودی‌ها و خروجی‌های تحقیق مشخص گردید. مقایسه نمرات کارایی شرکت‌های برق منطقه‌ای قبل و بعد از کاهش تعداد متغیرها، تعداد شرکت‌های کارا در طی شش دوره زمانی فوق از 4/62 درصد به 4/26 درصد کاهش یافته است.

کلیدواژه‌ها

عنوان مقاله [English]

Inputs and Outputs Selection of Data Envelopment Analysis to Evaluate the Performance of Regional Electricity Companies in Iran by Neural Network

نویسنده [English]

  • Akram Oveysiomran 3

1

2

3 Ph.D candidate

4

چکیده [English]

Input and output selection in Data Envelopment Analysis (DEA) has many important. In this research, inputs and outputs of reginal power companies are selected with artifitial neural network. The application of neural network in the selection of inputs and outputs of reginal power companies is not a precedent in the literature and it is considered the main advantage of the proposed method. In order to train two layers MLP neural network, after presenting of error resilience, learning method was used. After neural network training, neural network performance is examined by using the test set. RMSE value for 15 test set equals 0/0269 which reflects the high accuracy of training network. The Sensitivity Analysis of the studied parameters which are the same inputs and outputs of Data Envelopment Analysis, with ten percent increase of parameter, compared to the prior one was carried out and output relative error average for neural network parameters was calculated. Based on the output relative error average, inputs and outputs were determined. By comparing the efficiency scores of regional electricity companies before and after reducing the number of variables, it is noticed that the number of efficient companies during the above four periods decreased from 50 percent to 11 percent. Finally, the neural network application in inputs and outputs selection of the regional electricity companies was unprecedented in the literature and this is the main advantage of this method.

کلیدواژه‌ها [English]

  • Input and Output Selection
  • Data Envelopment Analysis
  • Neural Network
  • Window Analysis
  • Regional Electricity Companies
- بنیادی نائینی، علی، یوسفی، سعید و فائضی‌راد، محمدعلی، (1395)، پویاسازی خوشه‌بندی مشتریان با استفاده از روش DEA-DA در بستر شبکه عصبی مصنوعی SOM، فصلنامه علمی- پژوهشی مطالعات مدیریت صنعتی، سال چهاردهم، شماره 40، صفحات 165-187.
2- [1] رمضانیان، محمد رحیم، اویسی عمران، اکرم و یاکیده، کیخسرو، (1391)، تبیین الگوی ارزیابی عملکرد در طی زمان با تحلیل پنجره‌ای، مدیریت صنعتی تهران، دوره 4: 2، 69-86.
3- Angelidis, D., Lyroudi, K., (2006), Efficiency in the Italian banking industry: Data envelopment analysis and neural networks. International Research Journal of Finance and Economics 1 (5), 155–165.
4- Athanassopoulos, A. D., Curram, S., (1996), A comparison of data envelopment analysis and artificial neural networks as tools for assessing the efficiency of decision making units. Journal of Operational Research Society 47 (8), 1000– 1017.
5- Azadeh, A., Saberi, M., Tavakkoli Moghaddam, R., (2011), Javanmardi, L., An integrated Data Envelopment Analysis–Artificial Neural Network–Rough Set Algorithm for assessment of personnel efficiency, Expert Systems with Applications, (38), pp. 1364–1373.
6- Banker, R.D., (1993). Maximum likelihood, consistency and data envelopment analysis: A statistical foundation. Management Science, 39 (10), 1265–1273.
7- Banker, R.D., (1996). Hypothesis tests using data envelopment analysis. Journal of Productivity Analysis, 7 (23), 139–159.
8- Boussofiane, A., Dyson, R.G., Thanassoulis, E., (1991). Applied data envelopment analysis. European Journal of Operational Research, 52 (1), 1–15.
9- Costa, A., Markellos, R.N., 1997. Evaluating public transport efficiency with neural network models. Transportation Research 5 (5), 301–312.
10- Emrouznejad, A., Shale, E. A., (2009), a combined neural network and DEA for measuring efficiency of large scale data sets.  Computers and Industrial Engineering 56, 249–254.
11- Golany, B., Roll, Y., (1989). An application procedure for DEA. Omega, 17(3), 237–250.
12- Jenkins, L., Anderson, M., (2003). A multivariate statistical approach to reducing the number of variables in data envelopment analysis. European Journal of Operational Research, 147 (1), 51–61.
13- Klimberg, R., Puddicombe, M., (1995). A multiple objective approach to data envelopment analysis, working paper 95-105, School of Management, Boston University, MA.
14- Kwon, H., B., and Lee, J., (2015), Two-stage production modeling of large U.S. banks: a DEA-neural network approach, Expert Systems with Applications, Vol, (42), Issue (19), pp. 6758- 6766.
15- Kwon, H., B., (2017), Exploring the predictive potential of artificial neural networks in conjunction with DEA in railroad performance modeling, Int. J. Production Economics, 183, pp. 159–170.
16- Kwon, H., B., Marvel, J., H., and Roh, J., J., (2017), Three-stage performance modeling using DEA-BPNN for better practice benchmarking, Expert Systems with Applications, 71, pp. 429-441.
17- Ming-Chun, T., Shu-Ping, L., Ching-Chan, C., Yen-Ping, L., (2009), The consumer loan default predicting model – An application of DEA–DA and neural network, Expert Systems with Applications 36, pp. 11682–11690.
18- Misiunas, N., Oztekin, A., Chen, Y. and Chandra, k., (2016), DEANN: A healthcare analytic methodology of data envelopment analysis and artificial neural networks for the prediction of organ recipient functional status, Vol, 58, pp. 46-58.
19- Nunamaker, T.R., (1985). Using data envelopment analysis to measure the leniency of non-profit organizations: A critical evaluation. Managerial and Decision Economics, 6 (1), 50–58.
20- Olanrewaju, O. A., Jimoh, A. A. & Kholopane, P. A., (2016), assessing the energy potential in the South African industry: A combined IDA-ANN-DEA (Index Decomposition Analysis-Artificial Neural Network-Data Envelopment Analysis) model, Energy, (63), pp. 225- 232.
21- Pendharkar, P., Rodger, J., 2003. Technical efficiency-based selection of learning cases to improve forecasting accuracy of neural networks under monotonicity assumption. Decision Support Systems 36 (1), 117–136.
22- Ramezanian, M. R., Oveyssi Omran, A., and Yakideh, K. (2012). Explanation of Performance Evaluation Model over Time by Window Analysis. Industrial Management, 4 (2), 69-86. (In persian)
23- Salinas-Jimenez, J., Smith, P., (1996). Data envelopment analysis applied to quality in primary health care. Annals of Operations Research, 67, 141–161.
24- Shabanpour, H., Yousefi, S. & Farzipoor Saen, R., (2016), Forecasting efficiency of green suppliers by dynamic data envelopment analysis and artificial neural networks, In Press, pp. 1-10.
25- Saghafi, H., and Arabloo, M., (2017), Modeling of CO 2 solubility in MEA, DEA, TEA, and MDEA aqueous solutions using AdaBoost-Decision Tree and Artificial Neural Network, International Journal of Greenhouse Gas Control, 58, pp. 256–265.
26- Sharifian, A., & Sharifian, S., (2015), A new power system transient stability assessment method based on Type-2 fuzzy neural network estimation, Electrical Power and Energy Systems 64, pp. 71–87.
27- Vlontzos, G., and Pardalos, P. M., (2017), Assess and prognosticate green house gas emissions from agricultural production of EU countries, by implementing, DEA Window analysis and artificial neural networks, Renewable and Sustainable Energy Reviews, 76, pp. 155–162.
28- Wang, S., (2003), Adaptive non-parametric efficiency frontier analysis: A neural- network-based model. Computers and Operations Research 30 (2), 279 – 295.
29- Wu, D., (2009), Supplier selection: A hybrid model using DEA, decision tree and neural network. Expert Systems with Applications 36 (5), 9105–9112.
30- Yong-Ming, H., Zhi-Qiang, G. & Qun-Xiong, Z., (2016), Energy optimization and prediction of complex petrochemical industries using an improved artificial neural network approach integrating data envelopment analysis, Energy Conversion and Management, 124, pp. 73–83.