Comparison of artificial neural network models of categorized daily electric load

Year 2021, , 24 - 34, 30.04.2021

Vildan Evren , İlker Ali Ozkan

https://doi.org/10.51354/mjen.828545

Abstract

Comparison of artificial neural network models of categorized daily electric load

Abstract

The efficient operation of power systems and future planning, electricity load forecast is very important. Load estimation is based on predicting future electric load by examining past conditions. Short-term load prediction plays a decisive role in the load sharing of power plants. It also allows to overcome shortcomings caused by sudden load increases and power plant losses. Weather conditions are effective in short-term electrical load estimation. Daily or hourly electricity consumption data is generally used for short-term load estimation. In this study, daily electrical energy consumption of Turkey in the four years of data were used. Short-term load prediction modeling has been carried out. In this modeling, past electrical load values and temperature values were used as input, and in order to increase the prediction accuracy, the characteristics of the days were categorized weekly and classified according to the seasons. Different Artificial Neural Network models have been created according to input data, weekly categorization, and season criteria. In the study, mean absolute percentage error values were calculated. Among the models developed with ANN, the best MAPE value was 2.51% and the worst MAPE value was 4.48%. When the season criterion is added, the MAPE value is more successful.

Keywords

Artificial neural network, Short term electric load forecast, Time series modeling, Daily electric load forecast

References

• Var H., Türkay B. E., "Short term electric load forecasting using artificial neural networks", Elektronics – Computer and Biomedical Engineering Symposium, November 27-29, 2014, Bursa.
• Hong T., “Short Term Electric Load Forecasting”, Doctor of Philosophy, North Carolina State University, 2010.
• Çevik H.H., “Short term electrical load forecasting of Turkey”, Master Thesis, Electrical and Electronics Engineering, Selcuk University Institute of Science and Technology, Konya, 2013.
• Başoğlu B., Bulut M., "Development of a hybrid system based on neural networks and expert systems for shortterm electricity demand forecasting", Journal of the Faculty of Engineering and Architecture of Gazi University, 32.2, (2017), 575-583.
• Akman T., Yılmaz C., Sönmez Y., "Analysis of electrical load forecasting methods", Gazi Journal of Engineering Sciences, 4.3, (2018), 168-175.
• Fan S., Chen L., “Short-term load forecasting based on an adaptive hybrid method”, IEEE Transactions on Power Systems, 21.1, (2006), 392-401.
• Hamzaçebi C., Kutay F., "Electric consumption forecasting of Turkey using articial neural netwoorks up to year 2010", Gazi University Journal of Engineering and Architecture Faculty, 19.3, (2004), 227-233.
• Lee K. Y., Cha Y. T., Park J. H., “ hort-term load forecasting using an artificial neural network”, IEEE transactions on power systems, 7.1 (1992) 124-132.
• Nie H., Liu G., Liu X., Wang Y., “Hybrid of ARIMA and SVMs for short-term load forecasting”, Energy Procedia, 16, (2012), 1455-1460.
• Es H., Kalender F.Y., Hamzaçelebi C., "Forecesting the energy demand of Turkey by artificial neural network", Gazi University Journal of Engineering and Architecture Faculty, 29.3, (2014), 495-504.
• Yavuzdemir M. Y., Gökgöz F.T.D, “Short-term gross annual electriciy demand forecast in Turkey”, Master Thesis, Ankara University Institute of Social Sciences, Department of Business Administration, Ankara, 2014.
• Kaysal K., Kaysal A., Hocaoğlu F.O., “Hybrid Model for Load Forecasting (ANN and Regression)”, Afyon Kocatepe University, Faculty of Engineering, Department of Electric Engineering, Turkey, (2015), 33-39.
• Tümer Abdullah Erdal, Yavuz Cankat, Koçer Sabri (2018). Estimation of Unbalance Cost Due To Demand Prediction Errors Using Artificial Neural Network. Selçuk University Technology Faculty Selçuk- Technical Journal, Special Issue 2018 (ICENTE'17), 27-37.
• Tümer A.E., Koçer S., Koca A. (2016, November). Estimation of the electricity consumption of Turkey trough artificial neural networks. In 2016 IEEE 17th International Symposium on Computational Intelligence and Informatics (CINTI) (pp. 000315-000318). IEEE.
• Haliloğlu E.Y., Tutu B.E., “Short-term electricity power demand forecasting for Turkey”, Journal of Yasar University, 13.51, (2018), 243-255.
• Adepoju G.Y., Ogunjuyigbe S.O.A., Alawode K.O., Application of neural network to load forecasting in Nigerian electrical power system, Ladoke Akintola University of Technology Nigeria, The Pacific Journal of Science and Technology, vol. 8, pp., (2007), 68-72.
• Fan S., Hyndman R.J., Short-term load forecasting based on a semi-parametric additive model, Monash Univ., (2011), Clayton, Australia, Augus.
• Lee Y.S., Tong L.I., Forecasting energy consumption using a grey model improved by incorporating genetic programming, Energy Conversion and Management, (2011), 52 : 147–152.
• Himanshu A.A., Lester C.H., Electricity demand for Sri Lanka: a time series analysis. Energy, (2008), 33, 724-739.
• “EPIAS Transparency Platform”, [Online]. Available: [https://seffaflik.epias.com.tr], [Accessed: September 15, 2019].
• “Weather Turkey”, [Online]. Available: https://www.havaturkiye.com. [Accessed: September 15, 2019].
• “Electricity market 2016 market development report”, T. C. Energy Market Regulatory Authority, Ankara, (2017).
• “Electricity market 2017 market development report”, T. C. Energy Market Regulatory Authority, Ankara, (2018).
• “Electricity market 2018 market development report”, T. C. Energy Market Regulatory Authority, Ankara, (2019).
• Zontul M., Yangın A., "Data Mining on education publishing sector by artificial neural network tecniques”, Aurum Journal of Engineering Systems and Architecture, 1.2, (2017), 1-15.
• Kılıç G., “Refectory Daily demand forecast using artificial neural networks”, Master Thesis, Pamukkale University Institute of Science, Denizli, 2015.