Türkiye'de Elektrik Tüketiminin Zaman Serisiyle Tahmini

Öz

Günümüzde elektrik enerjisi modern yaşamın temel taşıdır ve birçok endüstride, faaliyette ve yaşam alanında büyük bir rol oynamaktadır. Hayatın birçok yönünü kolaylaştırır ve geliştirir ve modern toplumun işleyişini sağlar. Türkiye'de elektrik enerjisi kullanımının yaygınlaşması bir anlamda çağdaş toplum yolunda ilerlemenin göstergesidir. Bu çalışmada Türkiye'de 1965-2022 yılları arasında kişi başına tüketilen elektrik enerjisinin yıllık tahminleri derin öğrenme ve istatistik tabanlı modeller yardımıyla yapılmış ve sonuçlar MAPE metriği ile değerlendirilmiştir. Ayrıca elektrik tüketiminin Türkiye açısından olumlu ve olumsuz yönleri tartışıldı.

Anahtar Kelimeler

• Elektrik enerjisi tüketimi
• zaman serileri
• derin öğrenme modelleri
• istatistiksel tabanlı modeller
• zaman serileri

Prediction of Electricity Consumption in Türkiye with Time Series

Öz

Today, electrical energy is the cornerstone of modern life and plays a large role in many industries, activities and areas of life. It facilitates and improves many aspects of life and enables the functioning of modern society. The widespread use of electrical energy in Türkiye, in a sense, is an indicator of its progress towards a modern society. In this study, annual estimations of the electrical energy consumed per capita in Türkiye between 1965-2022 were made with the help of deep learning and statistics-based models and the results were evaluated with the MAPE metric. In addition, the positive and negative aspects of electricity consumption for Türkiye were discussed.

Anahtar Kelimeler

• Electrical energy consumption
• time series
• deep learning models
• statistical based models
• time-series

Kaynakça

1. Yağmur, A., Kayakuş, M. & Terzioğlu, M. Predicting renewable energy production by machine learning methods: The case of Turkey. Environ. Prog. Sustain. Energy 1–10, 2023.
2. Beyca, O. F., Ervural, B. C., Tatoglu, E., Ozuyar, P. G. & Zaim, S. Using machine learning tools for forecasting natural gas consumption in the province of Istanbul. Energy Econ. 80, 937–949, 2019.
3. Özgüner, E., Tör, O. B. & Güven, A. N. Probabilistic day-ahead system marginal price forecasting with ANN for the Turkish electricity market. Turkish J. Electr. Eng. Comput. Sci. 25, 4923–4935,2017.
4. Luis, A., Maia, S. & De Carvalho, F. D. A. T. Holt’s exponential smoothing and neural network models for forecasting interval-valued time series. Int. J. Forecast. 27, 740–759, 2011.
5. Ak, R., Fink, O. & Zio, E. Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction. IEEE Trans. Neural Networks Learn. Syst. 27, 1734–1747,2016.
6. Moiseev, N. A. Forecasting time series of economic processes by model averaging across data frames of various lengths. J. Stat. Comput. Simul. 87, 3111–3131 (2017).
7. Seymour, L., Brockwell, P. J. & Davis, R. A. Introduction to Time Series and Forecasting. Journal of the American Statistical Association 92, 2016.
8. Es, H. A. Monthly natural gas demand forecasting by adjusted seasonal grey forecasting model. Energy Sources, Part A Recover. Util. Environ. Eff. 43, 54–69, 2021.

9. Pala, Z. Comparative study on monthly natural gas vehicle fuel consumption and industrial consumption using multi-hybrid forecast models. Energy 263, 1–21, 2023.
10. Alsharif, M. H., Younes, M. K. & Kim, J. Time series ARIMA model for prediction of daily and monthly average global solar radiation: The case study of Seoul, South Korea. Symmetry (Basel). 11, 1–17, 2019.
11. Pala, Z. & Atici, R. Forecasting Sunspot Time Series Using Deep Learning Methods. Sol. Phys. 294, 2019.
12. Box, G. E. P., Jenkins, G. M., Reinsel, G. C., Ljung, G. M. & Cookbook, R. Time Series Analaysis Forecasting and Control. (Wiley, 2016).
13. Sobral, M. F. F., Duarte, G. B., da Penha Sobral, A. I. G., Marinho, M. L. M. & de Souza Melo, A. Association between climate variables and global transmission oF SARS-CoV-2. Sci. Total Environ. 729, 138997, 2020.
14. Hyndman, R. J. & Athanasopoulos, G. Forecasting : Principles and Practice. (Monash University, 2018).
15. Yaldız, E. & Pala, Z. Time Series Analysis of Radiological Data of Outpatients and Inpatients in Emergency Department of Mus State Hospital. Int. Conf. Data Sci. Mach. Learn. Stat. - 2019 234–236, 2019.
16. Zhang, Y. et al. Emergency patient flow forecasting in the radiology department. Health Informatics J., 2020. doi:10.1177/1460458220901889.
17. Villani, M. et al. Time series modelling to forecast prehospital EMS demand for diabetic emergencies. BMC Health Serv. Res. 17, 1–9, 2017.
18. Pala, Z. & Pala, A. F. Comparison of ongoing COVID-19 pandemic confirmed cases / deaths weekly forecasts on continental basis using R statistical models. Dicle Univ. J. Eng. 4, 635–644, 2021.
19. Pala, Z., Atıcı, R. & Yaldız, E. Forecasting Future Monthly Patient Volume using Deep Learning and Statistical Models. Wirel. Pers. Commun. 130, 1479–1502, 2023.
20. Montagnon, E. et al. Deep learning workflow in radiology: a primer. Insights into Imaging 11, 1–15, 2020.
21. Atici, R. & Pala, Z. Prediction of the Ionospheric foF2 Parameter Using R Language Forecasthybrid Model Library Convenient Time. Wirel. Pers. Commun. 1–20, 2021.
22. Pala, Z., Ünlük, İ. H. & Yaldız, E. Forecasting of electromagnetic radiation time series: An empirical comparative approach. Appl. Comput. Electromagn. Soc. J. 34, 1238–1241, 2019.
23. Pala, Z. Examining EMF Time Series Using Prediction Algorithms With R. 44, 223–227, 2021.
24. Pala, Z. Using Decomposition-based Approaches to Time Series Forecasting in R Environment. Int. Conf. Data Sci. Mach. Learn. Stat. - 2019 1, 231–233, 2019.
25. Sorkun, M. C. Time Series Forecasting on Solar Radiation using Deep Learning. (Galatasaray University, 2018).
26. Ma, T., Antoniou, C. & Toledo, T. Hybrid machine learning algorithm and statistical time series model for network-wide traffic forecast. Transp. Res. Part C Emerg. Technol. 111, 352–372, 2020.
27. Pala, Z. & Ünlük, İ. H. Comparison of hybrid and non-hybrid models in short-term predictions on time series in the R development environment. DÜMF Mühendislik Derg. 2, 199–204, 2022.
28. Pala, Z. & Pala, A. F. Perform Time-series Predictions in the R Development Environment by Combining Statistical-based Models with a Decomposition-based Approach. J. Muş Alparslan Univ. Fac. Eng. Archit. 1, 1–13, 2020.
29. Ünlük, İ. H. & Pala, Z. Prediction of monthly electricity consumption used in Muş Alparslan University Complex by means of Classical and Deep Learning methods. Int. Conf. Data Sci. Mach. Learn. Stat. - 2019 1, 237–239, 2019.
30. Etem, T., Pala, Z. & Bozkurt, I. Electromagnetic pollution measurement in the system rooms of a university. in 2017 13th International Conference Perspective Technologies and Methods in MEMS Design, MEMSTECH 2017 - Proceedings 2017.
31. Pala, Z. & Şana, M. Attackdet: Combining web data parsing and real-time analysis with machine learning. J. Adv. Technol. Eng. Res. 6, 37–45, 2020.
32. Pala, Z., Yamli, V. & Ünlük, I. H. Deep Learning researches in Turkey: An academic approach. in 2017 13th International Conference Perspective Technologies and Methods in MEMS Design, MEMSTECH 2017 - Proceedings 2017.
33. Pala, Z. & Özkan, O. Artificial Intelligence Helps Protect Smart Homes against Thieves. DÜMF Mühendislik Derg. 11, 945–952, 2020.
34. Pala, Z., Bozkurt, I. & Etem, T. Estimation of low frequency electromagnetic values using machine learning. in 2017 13th International Conference Perspective Technologies and Methods in MEMS Design, MEMSTECH 2017 - Proceedings 2017.
35. Pala, Z. Using forecastHybrid Package to Ensemble Forecast Functions in the R. Int. Conf. Data Sci. Mach. Learn. Stat. - 2019 1, 45–47, 2019.
36. Smyl, S. A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. Int. J. Forecast. 36, 75–85, 2020.
37. Chimmula, V. K. R. & Zhang, L. Time series forecasting of COVID-19 transmission in Canada using LSTM networks. Chaos, Solitons and Fractals 135, 109864, 2020.
38. Shen, Z., Zhang, Y., Lu, J., Xu, J. & Xiao, G. A novel time series forecasting model with deep learning. Neurocomputing 396, 302–313, 2020.
39. Unluk, I. H. Ensembling Time Series Algorithms with Hybrid Models to Predict R Environment Specific Datasets. Muş Alparslan University Natural and Applied Science Department of Nuclear Energy and Energy Systems 1, (Muş Alparslan University, 2022).
40. Hassan, M. A., Salem, H., Bailek, N. & Kisi, O. Random Forest Ensemble-Based Predictions of On-Road Vehicular Emissions and Fuel Consumption in Developing Urban Areas. Sustainability 15, 1503, 2023.
41. Basha, S. M., Zhenning, Y., Rajput, D. S., Caytiles, R. D. & Iyengar, N. C. S. N. Comparative study on performance analysis of time series predictive models. Int. J. Grid Distrib. Comput. 10, 37–48, 2017.
42. Petropoulos, F. & Svetunkov, I. A simple combination of univariate models. Int. J. Forecast. 36, 110–115, 2020.
43. Abotaleb, M. et al. State of the art in wind speed in England using BATS , TBATS , Holt ’ s Linear and ARIMA model. 1, 129–138, 2022.
44. Kim, S. & Kim, H. A new metric of absolute percentage error for intermittent demand forecasts. Int. J. Forecast. 32, 669–679, 2016.