Abstract
The electricity sector is essential for the economy. It is also important to improve the quality of life for the population. Evaluating the electricity consumption data helps in the management of crises in the sector and provides useful information for implementing pricing policies. Also, it allows identifying places that most need infrastructure improvement or expansion. As regards the demand side, this data analysis can also indicate how to promote more efficient and conscious consumption. In this way, this study aims to analyze data from units that consume electricity using the Kohonen self-organizing maps (SOM) technique. This technique of artificial neural networks was able to reveal patterns and behaviors in groups of customers of electric power companies. The results show relationships between quality indexes and economic activities, revealing an important space for improvements. The relationship between seasons and the energy consumption of some groups can also assist in making decisions related to energy sources and managing the resources of the electric power network.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ruas, G.I.S. et al.: Previsão de Demanda de energia elétrica utilizando redes neurais artificiais e support vector regression. In: VI Encontro Nacional de Inteligência Artificial, pp. 1262–1271. Rio de Janeiro (2007)
Oseni, M.O., Pollitt, M.G.: The economic costs of unsupplied electricity evidence from backup generation among African firms. Energy Policy Research Group Working Paper 1326, Cambridge Working Papers in Economics 1351, Cambridge University Press, Cambridge (2013)
Bose, R.K., Shukla, M., Srivastava, M., Yaron, G.: Cost of unserved power in Karnataka. India. Energy Policy. 34(12), 1434–1447 (2006)
Horváth, K. H.: The effect of energy prices on competitiveness of energy-intensive industries in the EU. In: International Entrepreneurship and Corporate Growth in Visegrad Countries, pp. 129–146. University of Miskolc, Miskolc (2014)
Griebenow, C., Ohara, A.: Report on the Brazilian Power System. Agora Energiewende and Instituto E+ Diálogos (2019).
Fillho, G.F., Cassula, A.M., Roberts, J.J.: Non-technical losses in Brazil: subsidies for implementation of smart-grid. J. Energy Power Eng. 8(7), 1301–1308 (2014)
Ceaki, O., Seritan, G., Vatu, R., Mancasi, M.: Analysis of power quality improvement in smart grids. In: 10th International Symposium on Advanced Topics in Electrical Engineering (ATEE), pp. 797–801. IEEE, Bucharest (2017)
Kohonen, T.: The self-organizing map. Proc. IEEE 78(9), 1464–1480 (1990)
Cerchiari, S.C., Teurya, A., Pinto, J.O.P., Lambert-Torres, G., Sauer, L., Zorzate, E.H.: Data mining in distribution consumer database using rough sets and self-organizing maps. In: Power Systems Conference and Exposition, pp. 38–43. IEEE, Atlanta (2006)
Oprea, S., Bâra, A.: Electricity load profile calculation using self-organizing maps. In: 20th International Conference on System Theory, Control and Computing (ICSTCC), pp. 860–865. IEEE, Sinaia (2016)
Mingoti, S.A., Lima, J.O.: Comparing SOM neural network with Fuzzy c-means, K-means and traditional hierarchical clustering algorithms. Eur. J. Oper. Res. 174(3), 1742–1759 (2006)
Ultsch, A.: Self-organizing neural networks for visualization and classification. In: Information and Classification, pp. 307–313. Springer, Berlin, Heidelberg (1993). https://doi.org/10.1007/978-3-642-50974-2_31
Ghaseminezhad, M.H., Karami, A.: A novel self-organizing map (SOM) neural network for discrete groups of data clustering. Appl. Soft Comput. 11(4), 3771–3778 (2011)
Strecker, U., Uden, R.: Data mining of 3D poststack seismic attribute volumes using Kohonen self-organizing maps. Lead. Edge 21(10), 1032–1037 (2002)
IBGE, API CNAE - Cadastro Nacional de Atividades Econômicas, https://servicodados.ibge.gov.br/api/docs/CNAE?versao=2. Accessed 04 Jan 2021
Acknowledgments
Research financed by the ANEEL R&D project Nº 05160–1805 / 2018, between CEB and UFU, and with partial support from CNPq, process number 135168/2019–8.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rosa, G.A., de Oliveira Ferreira, D., Pinheiro, A.P., Yamanaka, K. (2022). Analysis of Electricity Customer Clusters Using Self-organizing Maps. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2021. Lecture Notes in Networks and Systems, vol 295. Springer, Cham. https://doi.org/10.1007/978-3-030-82196-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-82196-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82195-1
Online ISBN: 978-3-030-82196-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)