Short-term Electric Energy Load Forecasting of Ankara Region Using Artificial İntelligence Methods

Öz

While energy, which is an indispensable part of everyday life, maintains its importance and place in socio-economic structures of countries, importance of electricity energy, as an important component of energy, is increasing its gravity exponentially. Importance of electricity energy demand maintains its increasing trend in line with growing population, urbanization, industrialization, becoming widespread of technology and welfare. While meeting electricity energy demand, correct and effective load forecasting is needed in order to ensure operational safety without losing the stability of voltage, frequency and power flows within the limits determined under the real time conditions of electric power systems, operate and plan secure and low-cost electricity transmission systems and supply sustainable, reliable, high quality and affordable electricity to consumers. In recent years, use of the artificial intelligence models are quite common in many areas of the power system analysis and control, static and dynamic security analysis, dynamic load modelling and alarm processing and error diagnostics. Therefore, in this study, hybrid artificial neural network model optimized with genetic algorithm has been proposed to perform short-term load forecast since fairly good forecasting results are being obtained especially for non-linear complex problems. The proposed short-term load forecasting model has been tested by making 24 hours load forecasting using actual load data of Ankara Region in Turkey. The results obtained from the proposed model have been compared with classical ANN. In this study, for short-term electric load forecasting based on artificial neural networks and genetic algorithm an adaptive hybrid system has been proposed. Using artificial neural network based on Genetic Algorithm (GA) a new approach for short-term electric load forecasting has been developed. This proposed hybrid algorithm has been implemented for short-term load forecasting. In the proposed model, the actual forecast was made by ANN, Genetic Algorithm is used to select the most appropriate activation function for each node of ANN. Thus, it has been observed that network error decreased even more than classical ANN. The results show that hybrid ANN gives better result than classical ANN. So, the accuracy of the proposed model for short-term load forecasting has been increased. These results showed that the proposed model has a higher accuracy rate than the classical ANN in the short-term load forecasting. 

Anahtar Kelimeler

• Hybrid Forecast Model
• Short-term load forecasting
• power systems
• artificial neural networks
• genetic algorithm
• hybrid forecast model

Kaynakça

1. [1] Turkish Electricity Transmission Co. Energy Efficiency Strategy Paper (2010 - 2023). Ankara: Turkish Electricity Transmission Co. 1-16, (2010) .
2. [2] Internet: Turkish electricity transmission sector report (2016), URL:www.teias.gov.tr/en/ Last Accessed: 15.11.2016.
3. [3] Internet: Republic of Turkey Ministry of Energy and Natural Resources strategic plan (2015-2019),URL: www.enerji.gov.tr/en-US/Mainpage Last Accessed: 15.09.2018.
4. [4] Internet: Regulation on supply reliability and quality of electric transmission system URL: www.teias.gov.tr/en/node/13 Last Accessed: 15.11.2018.
5. [5] Akman T, Yılmaz C Sönmez Y. Analysis of electric load forecasting methods. Gazi Journal of Engineering Sciences; 4(3): 65-73, (2018).
6. [6] Başoğlu B, Bulut M. Development of hybrid systems based on artificial neural networks and expert systems for short-term electric demand forecasts. Gazi University, Journal of Faculty of Engineering and Architecture. pp. 575-583, (2016).
7. [7] Fan S, Hyndman RJ. Short-term load forecasting based on a semi-parametric additive model. IEEE Transactions on Power Systems, 27(1): 134-141, (2010).
8. [8] Moturi C, Kiako, FK. Use of artificial neural networks for short-term electricity load forecasting of Kenya national grid power system. International Journal of Computer Applications; 63(2): 0975 – 8887, (2013).

9. [9] Senjyu T, Sakihara H, Tamaki Y, Uezato K. Next day peak load forecasting using neural network with adaptive learning algorithm based on similarity. Electric Machines & Power Systems; 28(1): 613– 624, (2010).
10. [10] Adepoju GA, Ogunjuyigbe, SOA, Alawode KO. 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; 8(1): 68-72, (2007)
11. [11] Ceylan G. Short-term load forecasting with artificial neural networks, Istanbul Technical University, Graduate School of Natural And Applied Sciences Istanbul, (2004).
12. [12] Abdoos A, Hemmati M. Short-term load forecasting using a hybrid intelligent method. Knowledge-Based Systems; 76(2): 139-147, (2015)
13. [13] Chogumaira EN, Hiyama T. Short-term electricity price forecasting using a combination of neural networks and fuzzy inference. Energy and Power Engineering; vol. 3, pp. 9-16, (2011)
14. [14] Kaytez F. Turkey's long-term electric consumption forecasting by the least squares support vector machines and modeling. Gazi University, Graduate School of Natural and Applied Sciences Ankara, (2012).
15. [15] Oğurlu H. Using mathematical modeling long-term electric load forecasting of Turkey, Selçuk University, Graduate School of Natural And Applied Sciences Konya, (2011).
16. [16] Kargar, M. C. ve Charsoghi K. Predıctıng annual electrıcıty consumptıon ın Iran usıng artıfıcıal neural networks (narx). Indian Journal of Scientific Research, 5(1), 231-242, (2014).
17. [17] Khwaja AS, Naeem M, Anpalagan A, Venetsanopoulos A, Venkatesh B. Improved short-term load forecasting using bagged neural networks. Ryerson University, Toronto, Canada. Electric Power Systems Research; 125(2): 109–115, (2015).
18. [18] Elmas Ç. Artificial Intelligence Applications. Seçkin Publishing, pp. 230-240, (2016)
19. [19] Öztemel E. Artificial neural networks. Papatya Publishing, pp. 34-140, (2003).
20. [20] Sönmez Y, Özden S. Modelling of thermodynamic properties of a refrigerant gas (r404a) using hybrid algorithm artificial bee colony-artificial neural network (abc-ann). International Journal of Refrigeration; 18(1): 183-187, (2017).
21. [21] Sheikh SK Unde MG. Short-term load forecastıng usıng ann technıque. International Journal of Engineering Sciences & Emerging Technologies; 1(2): 97-107, (2012).
22. [22] Nkachukwu CC. Short-term load forecasting using neural network for a residential building. Eastern Mediterranean University Gazimagusa, North Cyprus, (2014).
23. [23] Internet: Middle Anatolia Load Dispatch Center Hourly load data for the years 2009-2018. URL:https://ytbs.teias.gov.tr/ytbs/frm_login.jsf Last Accessed: 15.08.2018.
24. [24] Internet: Turkish State Meteorological Service The maximum and minimum daily air temperature data for the cities of Ankara, Kayseri and Konya between 2009-2015.URL: https://mgm.gov.tr/eng/forecast-cities.aspx, Last Accessed: 15.08.2018.
25. [25] Inc E. Electrical load forecasting: modeling and model construction, pp. 79-97, (2010).
26. [26] Karaboğa D. Artificial Intelligence Optimization Algorithms. Nobel Academic Publishing, pp. 75-95, (2017).
27. [27] 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; 40(1): 167-187, (2013).
28. [28] Oğurlu H. Using mathematical modeling long-term electric load forecasting in Turkey, Selçuk University, Graduate School of Natural And Applied Sciences, Konya, (2011).
29. [29] Internet: Turkey 5-year electric generation capacity projection(2017-2021).URL: www.teias.gov.tr/en/node/13 Last Accessed: 15.11.2018.