Türk Elektrik Piyasalarında YSA Yaklaşımıyla Elektrik Yükü Tahmini

Yıl 2020, Cilt: 3 Sayı: 2, 170 - 184, 31.12.2020

Fazıl Gökgöz , Fahrettin Filiz

https://doi.org/10.33721/by.834285

Cited By: 1

Öz

Elektrik yük tahmini yapabilmek, elektrik hizmetleri, enerji santralleri ve düzenleyiciler için gereklidir. Enerji politikalarını için büyük öneme sahip olan elektrik yükü tahminlerinin sağlıklı ve güvenilir sonuçlar üretmesi esastır. Yapay sinir ağları (YSA) karmaşık ve doğrusal olmayan ilişkileri öğrenebilir. Bu makale, elektrik yükü tahmini için 400 farklı YSA modelini tanımlamaktadır. Model performansları Ortalama Mutlak Yüzde Hata (MAPE) ve Diebold-Mariano (DM) testi ile karşılaştırılmıştır. Bu çalışma için kullanılan elektrik yükü verileri 2014 ile 2016 yılları arasında değişmektedir. Farklı modeller için YSA'nın tahmin kabiliyetleri tartışılmıştır. Log-sigmoid aktarım işlevine sahip Levenberg-Marquardt (LM), en iyi performanslı YSA modelini eğitir.

Anahtar Kelimeler

Elektrik Yük Tahmini, Yapay Sinir Ağları, Türkiye

Electricity Load Forecasting via ANN Approach in Turkish Electricity Markets

Öz

Forecasting electricity load has become the essential task for electric utilities, power plants and regulators. It is essential that electricity load forecasts, which are a vital necessity of energy policies, produce healthy and reliable results. Artificial neural networks (ANN) can learn complex and nonlinear relationships. This article introduces 400 different ANN models for electricity load forecasting. Model performances have compared with Mean Absolute Percentage Error (MAPE) and Diebold-Mariano (DM) test. The electricity load data used for this study range from 2014 to 2016. The variation in forecasting ability of ANN for different models has also discussed. Levenberg-Marquardt (LM) with log-sigmoid transfer function trains the best performance ANN model.

Anahtar Kelimeler

Electricity Load Forecast, Artificial Neural Network, Turkey

Kaynakça

• Alfares, H. K. & Nazeeruddin, M. (2002). Electric Load Forecasting: Literature Survey and Classification of Methods. International Journal of Systems Science. 33(1), 23-34.
• Ali, S. S., Moinuddin, M., Raza, K. & Adil, S. H. (2014). An Adaptive Learning Rate for Rbfnn Using Time-Domain Feedback Analysis. Scientific World Journal. Doi: 10.1155/2014/850189.
• Azar, A. T. (2013). Fast Neural Network Learning Algorithms for Medical Applications. Neural Computing and Applications Applications, 23(3-4), 1019-1034.
• Basterrech, S., Rubino, G., Mohammed, S. & Soliman, M. (2011). Levenberg - Marquardt Training Algorithms for Random Neural Networks. Computer Journal. 54(1), 125-135.
• Buhari, M., & Adamu, S. S. (2012). Short-term Load Forecasting Using Artificial Neural Network . Proceedings of the International Multi-Conference of Engineers and Computer Scientist, 14-16.
• Diebold, F. (2007). Elements of Forecasting. Thomson South-western.
• Fine, T. L. (1999). Feedforward Neural Network Methodology. Springer.
• Güney, E. S. (2005). Restructuring, Competition and Requlation in the Turkish Electricity Industry, Tech. Tepav.
• Günay, M. (2016). Forecasting Annual Gross Electricity Demand by Artificial Neural Networks Using Predicted Values of Socio-Economic Indicators and Climatic Conditions: Case of Turkey. Energy Policy, 90, 92-101.
• Hahn, H., Meyer-Nieberg, S. & Pickl, S. (2009). Electric Load Forecasting Methods: Tools for Decision Making. European Journal of Operational Research, 199(3), 902-907.
• Haykin, S. S. (1999). Neural Networks: A Comprehensive Foundation. Pearson Prentice Hall.
• Hippert, H. S., Pedreira, C. E., & Souza, R. C. (2001). Neural Networks for Short-Term Load Forecasting: A Review and Evaluation. IEEE Transactions on Power Systems, 16(1), 44-55.
• Hobbs, B. F., Jitprapaikulsarn, S., Konda, S., Chankong, V., Loparo, K. A., & Maratukulam, D. J. (1999). Analysis of the Value for Unit Commitment of İmproved Load Forecasts. IEEE Transactions on Power Systems, 14(4), 1342– 1348.
• Kankal, M., Akpinar, A., Komurcu, M. I. & Ozsahin, T. S. (2011). Modeling and Forecasting of Turkeys Energy Consumption Using Socio-Economic and Demographic Variables. Applied Energy, 88(5), 1927-1939.
• Khadse, C. B., Chaudhari, M. A. & Borghate, V. B. (2016). Conjugate Gradient Back- Propagation Based Artificial Neural Network for Real Time Power Quality Assessment. International Journal of Electrical Power & Energy Systems, 82, 197- 206.
• Kodogiannis, V. S. Amina, M., & I. Petrounias. (2013). A Clustering- Based Fuzzy Wavelet Neural Network Modek for Short-Term Load Forecasting. International Journal of Neural Systems.
• Kourentzes, N., Barrow, D. K., & Crone, S. F. (2014). Neural Network Ensemble Operators for Time Series Forecasting . Expert Systems With Applications, 23(05), 1350024.
• Küçükali, S., & Barış, K. (2010). Turkeys Short-Term Gross Annual Electricity Demand Forecast by Fuzzy Logic Approach . Energy Policy, 38(5), 2438-2445.
• Lahmiri, S. (2011). A Comparative Study Of Backpropagation Algorithms In Financial Prediction. International Journal of Computer Science, Engineering and Applications (IJCSEA), 1(4).
• Likas, A., & Stafylopatis, A. (2000). Training the Random Neural Network Using Quasi Newton Methods. European Journal of Operational Research, 126(2), 331-339.
• Lou, C. W. & Dong, M. C. (2015). A Novel Random Fuzzy Neural Networks for Tackling Uncertainties of Electric Load Forecasting. International Journal of Electrical Power & Energy Systems, 73, 34- 44.
• Mandal, P., Senjyu, T., & Funabashi, T. (2006). Neural Networks Approach to Forecast Several Hour Ahead Electricity Prices and Loads in Deregulated Market. Energy Conversion and Management, 47(15-16), 2128-2142.
• Srinivasan, D., Liew, A., & J. S. Chen. (1991). A Novel Approach to Electrical Load Forecasting Based on a Neural Network, in: Neural Networks. IEEE International Joint Conference on, IEEE.
• Osman, Z. H., Awad, M. L., & Mahmoud, T. K. (2009). Neural Network Based Approach for Short-Term Load Forecasting. Power Systems Conference and Exposition.
• Talaee, P. (2014). Multilayer Perceptron with Different Training Algorithms for Streamflow Forecasting. Neural Computing and Applications, 24(3-4), 695-703.
• Wang, L., Yang, Y., Min, M. R. & Chakradhar, S. (2016). Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent. Neural Networks, 93, 219-229.
• Zhang, G., Patuwo, B. E., & Hu, M. Y. (1998). Forecasting with Artificial Neural Networks: The State of the Art. International Journal of Forecasting. 14(1), 35-62.