YAPAY SİNİR AĞLARI YÖNTEMLERİ İLE ELEKTRİK TÜKETİMİ ANALİZİ

Yıl 2024, Cilt: 4 Sayı: 2, 98 - 111, 31.12.2024

Şeyma Nur Ünal

Öz

Enerji konusu ile ilgili yapılmış akademik çalışmalar içerisinde elektrik, ekonominin önemli bir bölümünü oluşturmaktadır. Elektrik tüketimi etkileyen birçok faktör bulunmakta olup çalışmada bu faktörler arasında ülkenin toplam elektrik enerjisi üretimi, ihracat, ithalat, sanayi üretim endeksi ve döviz kuru (Dolar/TL) ile ülkenin toplam elektrik tüketim miktarının 2005-2023 yılları verileri alınarak aralarındaki ilişki incelenmiş ve Yapay Sinir Ağları (YSA) yöntemiyle analiz edilmiştir. Veriler Türkiye İstatistik Kurumu (TÜİK), Türkiye Elektrik İletim Anonim Şirketi (TEİAŞ), Türkiye Cumhuriyet Merkez Bankası (TCMB)’dan alınarak Matlab ortamında ölçeklenmiş ve Matlab ortamında YSA modeline uygulanmıştır. Çalışmada YSA yöntemlerinden ileri beslemeli geri yayılımlı sinir ağı, elman sinir ağı NARX (Nonlinear Autoregressive Exogenous) sinir ağları kullanılmıştır. Yapılan analizler sonucunda 2 katmanlı ileri beslemeli geri yayılımlı sinir ağının performans ölçütü olarak alınan RMSE değeri 0.0157 R değeri ise 0.9976 elde edilerek kullanılan elman ve NARX sinir ağlarından daha iyi bir sonuç elde edildiği tespit edilmiştir.

Anahtar Kelimeler

Yapay Sinir Ağları, Elman Sinir Ağı, NARX Sinir Ağı, Elektrik Tüketimi

ANALYSIS OF ELECTRICITY CONSUMPTION BY ARTIFICIAL NEURAL NETWORKS METHODS

Öz

Among the academic studies on energy, electricity constitutes an important part of the economy. There are many factors affecting electricity consumption, and in this study, the relationship between the country's total electricity production, exports, imports, industrial production index and exchange rate (USD/TL) and the country's total electricity consumption for the years 2005-2023 was analyzed and analyzed with the Artificial Neural Network method (ANN). The data are obtained from Turkish Statistical Institute, Turkish Electricity Transmission Corporation, Central Bank of the Republic of Turkey, scaled in MATLAB environment and applied to the model. Feed-forward back-propagation neural network, Elman neural network and NARX neural network were used in the study. In the light of the analysis, it was determined that the RMSE value of the 2-layer feed-forward back-propagation neural network, which is taken as a performance criterion, was 0.0157 and the R value was 0.9976 and a better result was obtained than the Elman and NARX neural networks used.

Anahtar Kelimeler

Artificial Neural Network, Elman Neural Network, NARX Neural Network, Electricity Consumption

Kaynakça

• Alam, S. M., Deb, J. B., Al Amin, A., & Chowdhury, S. (2024). An Artificial Neural Network for Predicting Air Traffic Demand Based on Socio-Economic Parameters. Decision Analytics Journal, (10), 100382.
• Azadeh, A., Ghaderi, S. F., & Sohrabkhani, S. (2007). Forecasting Electrical Consumption by Integration of Neural Network, Time Series and ANOVA. Applied Mathematics and Computation (186), 1753-1761.
• Barcos, S. M., Perez, D. R., Garcia, J. R., & Ortega, M. A. (2024). Forecasting Electricity Demand of Municipalities Through Artificial Neural Networks and Metered Supply Point Classification. Energy Reports(11), 3533-3549.
• Behm, C., Nolting, L., & Praktiknjo, A. (2020). Forecasting Long-Term Electricity Demand Time Series Using Artificial Neural Networks. USAEE Working Paper No. 20-432. https://doi.org/10.3390/electricity2010002
• Boussaada, Z., Curea, O., Remaci, A., Camblong, H., & Bellaaj, N. M. (2018). A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation. Energies, 11(3), 1-21.
• Bouteska, A., Hajek , P., Fisher, B., & Abedin, M. Z. (2023). Nonlinearity in Forecasting Energy Commodity Prices: Evidence from a Focused Time-Delayed Neural Network. Research in International Business and Finance, (64), 101863.
• Guanghua, R., Cao, Y., Wen, S., Huang, T., & Zeng, Z. (2018). A Modified Elman Neural Network with a New Learning Rate Scheme. Neurocomputing, (286). 11-18.
• Hodson, T. O. (2022). Root-mean-square error (RMSE) or Mean bsolute error (MAE): When to use them or not. Geoscientific Model Development, 15(14). 5481-5487.
• Hsu, C.-C., ve Chen, C.-Y. (2003). Regional Load Forecasting in Taiwan-Applications of Artificial Neural Networks. Energy Conversion and Management(44), 1941–1949.
• Joshi, A. (2024). Artificial Intelligence and Human Evolution: Contextualizing AI in Human History. Apress.
• Kanwisher, N., Khosla, M., & Dobs, K. (2023). Using Artificial Neural Networks to Ask ‘Why’ Questions of Minds and Brains. Trends in Neurosciences, 3(46). 240-254.
• Karabulut, Y. (2004). Türkiye'de Elektrik Enerjisi. Ankara Üniversitesi Türkiye Coğrafyası Araştırma ve Uygulama Merkezi Dergisi (3), 53-77.
• Kiessling, S., Darabkhani, H. G., & Soliman, A.-H. A. (2024). Greater Energy Independence with Sustainable Steel Production. MDPI, 16 (3), 2-17.
• Koç, S., ve Onocak, D. (2018). Yapay Sinir Ağları ile Emeklilik Yatırım Fonu Hisse Senedi Fiyatlarının Tahmini. Finans Ekonomi ve Sosyal Araştırmalar Dergisi, 3(3), 590-600.
• Krauss, P. (2024). Artificial Intelligence and Brain Research: Neural Networks, Deep Learning and the Future of Cognition. Germany: Springer.
• Kumar Chandar, S. (2020). Grey Wolf Optimization-Elman Neural Network Model for Stock Price Prediction. Soft Computing, 25 (1), 649–658.
• Mandal, P., Senjyu, T., Urasaki, N., & Funabashi, T. (2006). A Neural Network Based Several-Hour-Ahead Electric Load Forecasting Using Similar Days Approach. Electrical Power and Energy Systems(28), 367–373.
• Muruganandam, S., Joshi, R., Suresh, P., Balakrishna, N., Kishore, K. H., & Manikanthan, S. V. (2023). A Deep Learning Based Feed Forward Artificial Neural Network to Predict the K-barriers For Intrusion Detection Using a Wireless Sensor Network. Measurement: Sensors, 25, 100613.
• Nizami, J. S., ve AI-Garni, Z. A. (1995). Forecasting Electric Energy Consumption Using Neural Networks. Energy Policy, 23(12), 1097- 1104.
• Nunno, F. D., ve Granata, F. (2020). Groundwater Level Prediction in Apulia Region (Southern Italy) Using NARX Neural Network, Environmental Research, (190), 1-17.
• Panklib, T., Prakasvudhisarnb, C., & Khummongkol, D. (2015). Electricity Consumption Forecasting in Thailand Using an Artificial Neural Network and Multiple Linear Regression. Energy Sources, Part B, 10(4), 427-434.
• Rafindadi, A. A., Aliyu , I. B., & Usman, O. (2022). Revisiting the Electricity Consumption-Led Growth Hypothesis: Is the Rule Defied in France?, Journal of Economic Structures, 11(1), 1-23.
• Sazlı, M. H. (2006). A Brief Review of Feed-Forward Neural Networks. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 50(1), 11-17.
• Shengfeng, X., Ming Sheng, X., Tianxing, Z., & Xuelli, Z. (2012). The Relationship between Electricity Consumption and. Economic Growth in China (24), 56-62.
• Thakur, K., Barker, H. G., & Pathan, A.-S. K. (2024). Artificial Intelligence and Large Language Models An Introduction to the Technological Future. CRC Press Taylor Francis Group.
• TMMOB. (2010). Türkiye’nin Enerji Görünümü. Ankara: TMMOB Makina Mühendisleri Odası.
• Torabi, M., Hashemi, S., Saybani, M. R., Shamshirband, S., & Mosavi, A. (2018). A Hybrid Clustering and Classification Technique for Forecasting Short-Term Energy Consumption. Environmental Progress & Sustainable Energy, (38), 66–76.
• TSKB. (2021). Enerji Görünümü. https://www.tskb.com.tr/i/assets/document/pdf/enerji-sektor-gorunumu-2021.pdf
• Wang , F., & Tax, D. M. (2016). Survey on the Attention Based RNN Model and its Applications in Computer Vision. Computer Science. https://arxiv.org/pdf/1601.06823.
• Xu, X., & Zhang, Y. (2022). Thermal Coal Price Forecasting Via The Neural Network. Intelligent Systems with Applications, 14, 200084.