The estimation of electrical energy consumption using Artificial Neural Networks

Year 2022, Volume: 2 Issue: 1, 14 - 20, 31.12.2022

Fatih Baltacı , Ali Öter

Abstract

In today’s world, as a result of technological developments, electrical energy occupies a vital position in daily human life and industrial applications. In recent years, various methods have been used for the estimation of electrical energy generation and consumption. Similarly, the present study benefits from artificial neural networks for the estimation of electrical energy consumption. Artificial neural networks are one of the most widely applied and studied methods in many different fields. In the present study, electrical energy consumption values of a public institution for 6 years between 2016 and 2021 were used to compare the performances of different artificial neural network structures based on two criteria: mean absolute percent error and mean squared error. In addition, prospective electrical energy consumption values in 2022 and 2023 were also estimated.

Keywords

ANN, Electrical energy, Estimation of electrical energy consumption, Mean Absolute Percent Error, Mean Squared Error

References

• Karacasu, Ö. & Hocaoğlu, M. H. Load estimation analysis for Gaziantep region with Artificial Neural Networks. 2003 TAINN’03 XII. International Turkish Symposium on Artificial Intelligence and Neural Networks.
• Toker, A. C. & Korkmaz, O. Hourly forecast of Turkey's short-term electricity demand in Proceedings. 2010, 32-35.
• Tekin, İ., Erat, S., & Zeren, Y. Calculation of electrical energy needs for Mersin province until 2023. Çukurova University Journal of the Faculty of Engineering and Architecture 2017, 32(1), 187-195.
• Kocadayı, Y., Erkaymaz, O., & Uzun, R. Estimation of Tr81 area yearly electric energy consumption by Artificial Neural Networks. Bilge International Journal of Science and Technology Research 2017, 1(Special Issue), 59-64.
• Dondurmacı, G. A. & Çınar, A. A. Data mining application in financial sector. The Journal of Academic Social Science 2014, 2(1), 258-271.
• Yavuz, S. & Deveci, M. The effect of statistical normalization techniques on the performance of Artificial Neural Network. Erciyes University Journal of Faculty of Economics and Administrative Sciences 2015, 40, 167-187.
• Jayalakshmi, T. & Santhakumaran, A. Statistical normalization and back propagation for classification. International Journal of Computer Theory and Engineering 2011, 3(1), 89-93.
• Soysal, M. & Ömürgönülşen, M. An application on demand forecasting in the Turkish tourism industry Anatolia. A Journal of Tourism Research 2010, 128-136.
• Werbos, P. J. Beyond regression: New tools for prediction and analysis in the behavioral sciences. Ph.D. Thesis 1974, Harvard University, Cambridge.
• Rumelhart, D. E. & McClelland J. L., Parallel Distributed Processing: Explorations in the microstructure of cognition, vol. 1, Cambridge, MA: MIT Press, 1986.
• Öter, A., Aydoğan, O., & Tuncel, D. Automatic sleep stage classification using Artificial Neural Networks with Wavelet Transform. Nigde Omer Halisdemir University Journal of Engineering Sciences 2019, 8(1), 59-68. doi: 10.28948/ngumuh.516809
• Lewis, C. D. Industrial and Business Forecasting Methods: A Practical Guide to Exponential Smoothing and Curve Fitting: Butterworth-Heinemann, 1982.
• Witt, S. F. & Witt, C. A. Modeling and Forecasting Demand in Tourism: Academic Press Ltd. 1992
• Web, https://mertricks.com/2015/05/30/ (Date of Access: 17.03.2020)
• Karlık, B. & Hayta, Ş. B. Comparison Machine Learning Algorithms for Recognition of Epileptic Seizures in EEG. Proceedings IWBBIO 2014, 1-12.