Accounting multiple environmental variables in DEA energy transmission benchmarking modelling: The 2019 Brazilian case

https://doi.org/10.1016/j.seps.2021.101162Get rights and content

Abstract

The non-parametric Data Envelopment Analysis (DEA) benchmarking method is frequently used by regulators to compare companies under natural monopolies. The Brazilian Energy regulator uses such an approach to define the efficient operational costs of the transmission companies. In 2019, a second-stage procedure was applied to include the effects of environmental variables on operational cost efficiency. However, only a few environmental variables were used to estimate efficient costs. This study proposes a new methodology for adjusting cost efficiencies using multiple contextual variables. Our proposal aims to adjust the input variable, using different environmental variables, before estimating the cost efficiencies. Therefore, multiple cost efficiencies are estimated, one for each environmental variable. Our proposal is based on the linear regression Analysis-of-Variance property. Results indicate that due to environmental heterogeneity of Brazilian transmission companies, cost efficiencies adjusted using multiple environmental variables are of utmost importance. Thus, our proposal manages to successfully include multiple environmental variables in the model, generating fair adjustments in the efficiency scores, and avoiding the effects of DEA modeling biases that are common in second-stage analyses.

Keywords

Energy transmission regulation
Data envelopment analysis
Environmental variables
Input variable correction

Dra. Aline V. da Silva is a management consultant and researcher. She holds a degree in Production Engineering from the Federal University of Rio Grande do Sul (UFRGS, 2008), a Ph.D., and a Master's degree in Industrial Engineering from the Federal University of Minas Gerais (UFMG, in 2020 and 2015). She has worked as a researcher on a cooperation project between UFMG and Technische Universität Braunschweig (Germany), regarding the regulation of Brazilian Transmission Service Operators. She has also worked for companies of the electric sector in Brazil and had been a collaborating professor at private and public universities.Selected Publications (In English)

1. DA SILVA, Aline Veronese; COSTA, Marcelo Azevedo; AHN, Heinz; LOPES, Ana Lúcia Miranda. Performance benchmarking models for electricity transmission regulation: caveats concerning the Brazilian case. Utilities Policy, 60 (2019) 100960. 2019

2. DA SILVA, Aline Veronese; COSTA, Marcelo Azevedo; LOPES, Ana Lúcia Miranda; MIRANDA, Gabriela. A close look at second stage data envelopment analysis using compound error models and the tobit model. Socio-Economic Planning Sciences, 65 (2019) 111–126, 2019.]

3. DA SILVA, Aline Veronese; ALMEIDA, Matheus Machado; COSTA, Marcelo Azevedo. An empirical analysis of the Brazilian Transmission Service Operators Incentive Regulation. Journal of Energy Markets, 13(04), 1–21, 2021.

Books and Chapters in Books (in English)

1. ASSUNÇÃO, Renato Martins; Costa, Marcelo A.; Prates, M. O.; Silva e Silva. Spatial analysis. In: Arthur Charpentier. (Org.). Computational Actuarial Science with R. 1ed.: Chapman & Hall, 2014, v. 1, p. 207-255.

2. Costa, M. A.; KULLDORFF, Martin. Applications of Spatial Scan Statistics: A Review. In: Joseph Glaz; Vladimir Pozdnyakov; Sylvan Wallenstein. (Org.). Scan Statistics: Methods and Applications. Boston: Birkhäuser, 2009, v., p. 133-147.

3. Costa, M. A.; Rodrigues, Thiago de Souza; Horta, E. G.; BRAGA, A. P.; Pataro, Carmen Déa Moraes; Natowicz, R.; Incitti, R.; Rouzier, R. . New Multi-Objective Algorithms for Neural Networks Training applied to Genomic Classification Data. In: Aboul-Ella Hassanien; Ajith Abraham; Athanasios V. Vasilakos; Witold Pedrycz. (Org.). Foundations of Computational Intelligence.: Springer, 2009, v. 1, p. 63–82.

Prof. Marcelo A Costa is a full professor of Applied Statistical Methods in the Department of Production Engineering at the Federal University of Minas Gerais (UFMG) and faculty member of the Graduate Program in Production Engineering (Stochastic Modeling and Simulation) at the same institution. He holds a degree in Electrical Engineering from the Federal University of Minas Gerais (1999), a PhD in Electrical Engineering from the Federal University of Minas Gerais (2002) in Computational Intelligence. He has done post-doctorate from Harvard Medical School & Harvard Pilgrim Health Care (2007) in Spatial Statistics and Epidemiological Surveillance, and post-doctorate from Linköping University (2018/Sweden) in Statistical Analysis, Diagnosis and Fault Detection in Industrial Environments. He is currently a collaborating professor in the Laboratory of Intelligence and Computational Technology (LITC/UFMG), developing research projects in artificial neural networks. He is also a collaborating professor at the Center of Research in Efficiency, Sustainability and Productivity (NESP/UFMG), developing research projects in economic regulation in the electricity sector. He has published several papers in international journals such as Socio-Economic Planning Sciences, IEEE Transactions on Power Delivery, Statistical Methods in Medical Research, PLOS One, Measurement, among others. He is a reviewer of international and national journals, as well as the author of book chapters published in English. He is a CEMIG/FAPEMIG R&D project coordinator and researcher in R&D projects. He supervises undergraduate, specialization, masters and doctoral students in the following areas: statistical models applied to the electrical sector, applied statistics, network analysis, spatial statistics, time series analysis, artificial neural network theory and applications. He is enthusiastic about using R language programming, which he has applied to solve many practical statistical problems including Big Data analysis.Selected Publications (In English)

1. Coelho, Frederico; Costa, Marcelo; Verleysen, Michel; Braga, Antônio P. LASSO multi-objective learning algorithm for feature selection. Soft Computing, v. 24, p. 13209–13217, 2020.

2. Correa, Juliano; Cisneros, Elías; Börner, Jan; Pfaff, Alexander; Costa, Marcelo; Rajão, Raoni. Evaluating REDD + at subnational level: Amazon fund impacts in Alta Floresta, Brazil. Forest Policy and Economics, v. 116, p. 102178, 2020.

3. Silveira Gontijo, Tiago; Azevedo Costa, Marcelo. Forecasting Hierarchical Time Series in Power Generation. Energies, v. 13, p. 3722, 2020.

4. de Santis, Rodrigo Barbosa; Costa, Marcelo Azevedo. Extended Isolation Forests for Fault Detection in Small Hydroelectric Plants. Sustainability, v. 12, p. 6421-1, 2020.

5. Gontijo, Tiago Silveira; Costa, Marcelo Azevedo; de Santis, Rodrigo Barbosa. Similarity search in electricity prices: An ultra-fast method for finding analogs. Journal of Renewable and Sustainable Energy, v. 12, p. 056103, 2020.

6. Rocha, Honovan P.; Costa, Marcelo A.; Braga, Antonio P.. Neural Networks Multiobjective Learning With Spherical Representation of Weights. IEEE Transactions on Neural Networks and Learning Systems, v. 31, p. 1–15, 2020.

7. Costa, Marcelo Azevedo; Mineti, Leandro Brioschi; Mayrink, Vinícius Diniz; Lopes, Ana Lúcia Miranda. Bayesian detection of clusters in efficiency score maps: An application to Brazilian energy regulation. Applied Mathematical Modelling, v. 68, p. 66–81, 2019.

8. Da Silva, Aline Veronese; Costa, Marcelo Azevedo; Lopes, Ana Lúcia Miranda; Do Carmo, Gabriela Miranda. A close look at second stage data envelopment analysis using compound error models and the Tobit model. Socio-Economic Planning Sciences, v. 65, p. 111–126, 2019.

9. Oliveira, A. S.; Soares-Filho, B. S.; Costa, M. A.; Lima, L.; Garcia, R.A.; Rajão, R.; Carvalho-Ribeiro, S. M. Bringing economic development for whom? An exploratory study of the impact of the Interoceanic Highway on the livelihood of smallholders in the Amazon. Landscape and Urban Planning, v. 188, p. 171179, 2019.

10. Costa, M. A.; Rajao, R. G. L.; Stabile, M.; Azevedo, A. A.; Correa, J. . Epidemiologically inspired approaches to land-use policy evaluation: The influence of the Rural Environmental Registry (CAR) on deforestation in the Brazilian Amazon. Elementa: Science Of The Anthropocene, v. 6, p. 1, 2018.

11. Pena, Carolina Silva.; Costa, M. A.; Oliveira, R. P. B. . A new item response theory model to adjust data allowing examinee choice. PLoS One, v. 13, p. 1–23, 2018.

12. Kano, Flora Satiko; De Souza, Aracele Maria; De Menezes Torres, Leticia; Costa, Marcelo Azevedo; Souza-Silva, Flávia Alessandra; Sanchez, Bruno Antônio Marinho; Fontes, Cor Jesus Fernandes; Soares, Irene Silva; De Brito, Cristiana Ferreira Alves; Carvalho, Luzia Helena; Sousa, Tais Nobrega. Susceptibility to Plasmodium vivax malaria associated with DARC (Duffy antigen) polymorphisms is influenced by the time of exposure to malaria. Scientific Reports, v. 8, p. 1–14, 2018.

13. Gil, G. D. R., Costa, M. A., Lopes, A. L. M., & Mayrink, V. D. (2017). Spatial statistical methods applied to the 2015 Brazilian energy distribution benchmarking model: Accounting for unobserved determinants of inefficiencies. Energy Economics.

14. Azevedo, A. A.; Rajão, R.; Costa, M. A.; Stabile, M.; Macedo, M.; Reis, T.; Alencar, A.; Soares-Filho, B.; Pacheco, R. . Limits of Brazil?s Forest Code as a means to end illegal deforestation. Proceedings Of The National Academy Of Sciences Of The United States Of America, v. 115, p. 1–6, 2017.

15. ROSA, G.; COSTA, M. A. Robust functional analysis for fault detection in power transmission lines. Applied Mathematical Modelling, p. 9067–9078, 2016.

16. Lopes, A. L. M; VILELA, B. A.; COSTA, M. A.; Lanzer, E. A. . Critical evaluation of the performance assessment model of Brazilian electricity distribution companies. Revista Gestão & Tecnologia, v. 16, p. 5, 2016.

17. Santos, Izabella A. R. A.; Duarte, Denise; Costa, Marcelo Azevedo. Use of jump process to model mobility in massive multiplayer on-line games. Journal of Applied Statistics, v. *, p. 1–23, 2016.

18. COSTA, M. A.; Lopes, A. L. M; Matos, G. B. B. P. . Statistical evaluation of Data Envelopment Analysisversus COLS Cobb-Douglas benchmarking models forthe 2011 Brazilian tariff revision. Socio-Economic Planning Sciences, v. 49, p. 47–60, 2015

19. Costa, M. A.; Colosimo, Enrico Antônio; Carolina G Miranda. Selecting Profiles Of In Debt Clients Of A Brazilian Telephone Company: New Lasso And Adaptive Lasso Algorithms In The Cox Model. Pesquisa Operacional (Online), v. 35, p. 401–421, 2015.

20. Ferreira, Jacqueline A.; Loschi, Rosangela H.; Costa, Marcelo A.. Detecting changes in time series: A product partition model with across-cluster correlation. Signal Processing (Print), v. 96, p. 212–227, 2014.

21. Costa, M. A.; Kulldorff, Martin. Maximum Linkage Space-Time Permutation Scan Statistics for Disease Outbreak Detection. International Journal of Health Geographics, v. 13, p. 1–31, 2014.

22. Gomes, André de Souza; Costa, M. A.; de Faria, T. G. A.; CAMINHAS, Walmir Matos. Detection and Classification of Faults in Power Transmission Lines Using Functional Analysis and Computational Intelligence. IEEE Transactions on Power Delivery, v. 28, p. 1402–1413, 2013.

Books and Chapters in Books (in English)

1. ASSUNÇÃO, Renato Martins; Costa, Marcelo A.; Prates, M. O.; Silva e Silva. Spatial analysis. In: Arthur Charpentier. (Org.). Computational Actuarial Science with R. 1ed.: Chapman & Hall, 2014, v. 1, p. 207-255.

2. Costa, M. A.; KULLDORFF, Martin. Applications of Spatial Scan Statistics: A Review. In: Joseph Glaz; Vladimir Pozdnyakov; Sylvan Wallenstein. (Org.). Scan Statistics: Methods and Applications. Boston: Birkhäuser, 2009, v., p. 133-147.

3. Costa, M. A.; Rodrigues, Thiago de Souza; Horta, E. G.; BRAGA, A. P.; Pataro, Carmen Déa Moraes; Natowicz, R.; Incitti, R.; Rouzier, R. . New Multi-Objective Algorithms for Neural Networks Training applied to Genomic Classification Data. In: Aboul-Ella Hassanien; Ajith Abraham; Athanasios V. Vasilakos; Witold Pedrycz. (Org.). Foundations of Computational Intelligence.: Springer, 2009, v. 1, p. 63–82.

View full text