A combined methodology for evaluation of electricity distribution companies in Turkey

被引：5

作者：

Ervural, Beyzanur Cayir ^{[1
]}

机构：

[1] Konya Food & Agr Univ, Fac Engn & Architecture, TR-42080 Meram, Konya, Turkey

来源：

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS | 2020年 / 38卷 / 01期

关键词：

Electricity distribution market; data envelopment analysis; artificial neural network; DATA ENVELOPMENT ANALYSIS; ARTIFICIAL NEURAL-NETWORK; IDA-ANN-DEA; ENERGY EFFICIENCY; POWER-PLANTS; WIND FARMS; PERFORMANCE ASSESSMENT; CHINA; PREDICTION; OPTIMIZATION;

D O I：

10.3233/JIFS-179468

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Energy efficiency initiatives are now more noteworthy due to awareness and sensitivity in the use of resources in rational, optimal and effective ways. The uncertain and dynamic structure of the electricity distribution market requires continuous improvement and efficiency activities/strategic decisions by adding new investments. Energy efficiency assessment plays an important role in improving energy efficiency. In this study, Data Envelopment Analysis (DEA) was employed to investigate the efficiency performance of twenty-one electricity distribution companies in Turkey. The results of DEA revealed that seven of the twenty-one electricity distribution companies were efficiently attempted in Turkey. After utilizing the DEA model, an Artificial Neural Network (ANN) method based on DEA was constructed, and then the efficiency of each company was predicted. According to the proposed integrated model, with incorporating new/alternative electricity companies, investment plans can be easily evaluated from a real perspective, and their performances can be predicted accurately. The study is expected to assist direct energy decision-makers and investors and help them in their investment plans.

引用

页码：1059 / 1069

页数：11

共 52 条

[21]

Jamasb T., 2001, INT BENCHMARKING REG

[22] Improved estimation of electricity demand function by using of artificial neural network, principal component analysis and data envelopment analysis [J].

Kheirkhah, A. ;

Azadeh, A. ;

Saberi, M. ;

Azaron, A. ;

Shakouri, H. .

COMPUTERS & INDUSTRIAL ENGINEERING, 2013, 64 (01) :425-441

[23] Two-stage production modeling of large US banks: A DEA-neural network approach [J].

Kwon, He-Boong ;

Lee, Jooh .

EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (19) :6758-6766

[24] Performance assessment of Alternative Energy Resources in Brazilian power sector using Data Envelopment Analysis [J].

Lins, Marcos Estellita ;

Oliveira, Luciano Basto ;

Moreira da Silva, Angela Cristina ;

Rosa, Luiz Pinguelli ;

Pereira, Amaro Olimpio, Jr. .

RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2012, 16 (01) :898-903

[25]

Ma Z., 2011, GEN DATA ENVELOPMENT, V21

[26] Analysis of wind power generation and prediction using ANN: A case study [J].

Mabel, M. Carolin ;

Fernandez, E. .

RENEWABLE ENERGY, 2008, 33 (05) :986-992

[27] Performance evaluation of thermal power plants considering CO2 emission: A multistage PCA, clustering, game theory and data envelopment analysis [J].

Mahmoudi, Reza ;

Emrouznejad, Ali ;

Khosroshahi, Hossein ;

Khashei, Mehdi ;

Rajabi, Parisa .

JOURNAL OF CLEANER PRODUCTION, 2019, 223 :641-650

[28] Low-carbon economy efficiency analysis of China's provinces based on a range-adjusted measure and data envelopment analysis model [J].

Meng, Ming ;

Fu, Yanan ;

Wang, Lixue .

JOURNAL OF CLEANER PRODUCTION, 2018, 199 :643-650

[29] DEANN: A healthcare analytic methodology of data envelopment analysis and artificial neural networks for the prediction of organ recipient functional status [J].

Misiunas, Nicholas ;

Oztekin, Asil ;

Chen, Yao ;

Chandra, Kavitha .

OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE, 2016, 58 :46-54

[30] Evaluation Of Brazilian Electricity Distributors Using A Network Dea Model With Shared Inputs [J].

Moreno, P. ;

Andrade, G. N. ;

Angulo, L. ;

de Mello, J. C. C. B. S. .

IEEE LATIN AMERICA TRANSACTIONS, 2015, 13 (07) :2209-2216

← 1 2 3 4 5 6 →