• icon+90(535) 849 84 68
  • iconnwsa.akademi@hotmail.com
  • icon Fırat Akademi Samsun-Türkiye

> Detaylı Arama

Article Details

Article Details

  • Article Code : FIRAT-AKADEMI-14733-5813
  • Article Type : Araştırma Makalesi
  • Publication Number : 1A0504
  • Page Number : 15-26
  • Doi : 10.12739/NWSA.2026.21.2.1A0504
  • Abstract Reading : 48
  • Download : 16
  • Atıf Sayısı : 0
  • Share :

  • PDF Download

Issue Details

  • Year : 2026
  • Volume : 21
  • Issue : 2
  • Number of Articles Published : 1
  • Published Date : 1.04.2026

Cover Download Context Page Download
Dergi Kapağı
Engineering Sciences

Serial Number : 1A
ISSN No. : 1308-7231
Release Interval (in a Year) : 4 Issues

MAKİNE ÖĞRENMESİ YÖNTEMLERİ KULLANILARAK YAPI GRUPLARININ ELEKTRİK TALEP GÜCÜNÜN BÖLGESEL DİVERSİTE İLE TAHMİN EDİLMESİ

Oğuz Mert Çelebi1

Bu çalışmanın amacı, yapı gruplarının elektrik güç ihtiyacının daha gerçekçi biçimde tahmin edilmesine yönelik veri temelli bir model geliştirmektir. Türkiye’de yapıların elektriksel güç gereksinimi mevcut mevzuatta yer alan diversite katsayılarına dayalı hesaplama yöntemleri ile belirlenmektedir. Ancak teknolojik gelişmeler, değişen kullanım alışkanlıkları ve bölgesel farklılıklar nedeniyle projelendirme aşamasında öngörülen güç değerleri ile işletme sürecinde gerçekleşen puant güç arasında önemli sapmalar oluşabilmektedir. Bu durum, gereğinden yüksek kapasiteli transformatör ve ekipman seçimine yol açarak enerji dağıtım altyapısında kapasite kullanım verimliliğini azaltmaktadır. Çalışmada farklı bölgesel özelliklere sahip transformatörlerden elde edilen maksimum güç verileri analiz edilmiş ve demografik, bölgesel ve kullanıcı tipine ilişkin değişkenleri içeren bir veri seti oluşturulmuştur. Oluşturulan veri seti kullanılarak çeşitli makine öğrenmesi modelleri geliştirilmiş ve model performansları karşılaştırılmıştır. Elde edilen bulgular, önerilen yaklaşımın enerji talep tahminlerinde daha dengeli kapasite planlamasına olanak sağlayabileceğini göstermektedir.

Keywords
Elektrik Talep Tahmini, Yapı Grupları, Diversite Katsayısı, Makine Öğrenmesi, Elektrik Dağıtım Sistemleri,

ESTIMATION OF ELECTRICAL DEMAND OF BUILDING GROUPS USING REGIONAL DIVERSITY-BASED MACHINE LEARNING METHODS

Oğuz Mert Çelebi1

This study aims to develop a data-driven model for more realistic estimation of the electrical power demand of building groups. In Turkey, the electrical power requirements of buildings are determined using calculation methods based on diversity coefficients defined in existing regulations. However, due to technological developments, changing consumption habits, and regional differences, significant discrepancies may occur between the power values estimated during the project design phase and the peak power observed during operation. This situation leads to the selection of transformers and equipment with capacities higher than required and reduces capacity utilization efficiency in the electricity distribution infrastructure. In this study, maximum power data obtained from transformers located in regions with different characteristics were analyzed, and a dataset including demographic, regional, and user-type variables was created. The dataset used in this study consists of maximum power measurements obtained from 780 distribution transformers located in seven different regions. Various machine learning models were developed using this dataset, and their performances were compared. The findings indicate that the proposed approach can enable more balanced capacity planning in electricity demand estimation, improve infrastructure investment efficiency and support data-driven capacity planning in electricity distribution systems.

Keywords
Electricity Demand Forecasting, Building Groups, Diversity Coefficient, Machine Learning, Electricity Distribution Systems,

Details
   

Authors

Oğuz Mert Çelebi (1) (Corresponding Author)
Enerjisa
celebiom@hotmail.com | 0009-0003-4617-695X

Supporting Institution

 :

Project Number

 :

Thanks

 :
References
1. Ceylan, O. ve Ozturk, B., (2020). Application of artificial neural networks in power distribution systems for load prediction. International Journal of Electrical Power & Energy Systems, 117:1-9.

2. Diaz-Acevedo, J.A., Grisales-Noreña, L.F., and Escobar, A., (2019). A method for estimating electricity consumption patterns of buildings to implement energy management systems. Journal of Building Engineering, 25:1-10.

3. Hahn, H., Meyer-Nieberg, S., and Pickl, S., (2009). Electric load forecasting methods: Tools for decision making. European Journal of Operational Research, 199(3):902-907.

4. Wang, X., Zhang, C., and Li, Y., (2018). Neural network approaches for electric load forecasting in smart grids. IEEE Transactions on Smart Grid, 9(3):1983-1993.

5. McLoughlin, F., Duffy, A., and Conlon, M., (2015). A clustering approach to domestic electricity load profile characterisation using smart metering data. Applied Energy, 141:190-199.

6. Wang, Z. and Hong, T., (2020). Generating realistic building electrical load profiles through generative adversarial networks. Energy and Buildings, 224:1-12.

7. Willis, H.L., (2002). Power distribution planning reference book. New York: Marcel Dekker.

8. Hong, T. and Fan, S., (2016). Probabilistic electric load forecasting: A tutorial review. International Journal of Forecasting, 32(3):914-938.

9. Deb, C., Zhang, F., Yang, J., Lee, S., and Shah, K., (2017). Time series forecasting techniques for building energy consumption. Renewable and Sustainable Energy Reviews, 74:902-924.

10. Fan, C., Xiao, F., and Wang, S., (2014). Development of prediction models for building energy consumption. Energy and Buildings, 75:17-26.

11. Zhang, G., Patuwo, B.E., and Hu, M.Y., (1998). Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting, 14(1):35-62.

12. Dong, B., Cao, C., and Lee, S.E., (2005). Applying support vector machines to predict building energy consumption in tropical region. Energy and Buildings, 37(5):545-553.

13. Khosravi, A., Nahavandi, S., Creighton, D., and Atiya, A., (2013). Comprehensive review of neural network-based prediction intervals and new advances. IEEE Transactions on Neural Networks and Learning Systems, 22(9):1341-1356.

14. Breiman, L., (2001). Random forests. Machine Learning, 45(1):5-32.

15. Chen, T. and Guestrin, C., (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794.

16. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A., (2018). CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems, 31: 6638-6648.

17. Hyndman, R.J. and Koehler, A.B., (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4):679-688.

18. Li, K., Hu, C., Liu, G., and Xue, W., (2015). Building electricity consumption prediction using optimized artificial neural networks and principal component analysis. Energy and Buildings, 108:106-113.

19. Zhang, C., Ma, L., Han, X., and Zhao, T., (2023). Improving building energy consumption prediction using occupant-building interaction inputs and improved swarm intelligent algorithms. Journal of Building Engineering, 70:1-12.

20. Kang, X., An, J., and Yan, D., (2023). A systematic review of building electricity use profile models. Energy and Buildings, 279:1-15.