İdil IŞIKLI ESENER, Tolga YÜKSEL, Mehmet KURBAN

Short-term load forecasting without meteorological data using AI-based structures

STLF is used in making decisions about economical power generation capacity, fuel purchasing, safety assessment, and power system planning in order to have economical power conditions. In this study, Turkey's 24-hour-ahead load forecasting without meteorological data is studied. ANN, wavelet transform and ANN, wavelet transform and RBF NN, and EMD and RBF NN structures are used in STLF procedures. Local holidays' historical load data are changed into data with normal day characteristics, and the estimation results of these days are not included in error computation. To obtain more accurate results, a regulation on forecasted loads is proposed. Regulated and unregulated forecasting error percentages are computed as daily average MAPE and maximum daily MAPE, and compared between the proposed structures. A simulation is performed for the years 2009--2010 via the user interface created using MATLAB GUI.

Anahtar Kelimeler:

Short-term load forecasting, artificial neural networks, radial basis function neural networks, wavelet transform, empirical mode decomposition

Short-term load forecasting without meteorological data using AI-based structures

Keywords:

Short-term load forecasting, artificial neural networks, radial basis function neural networks, wavelet transform, empirical mode decomposition,

PDF

___

Conclusion
The structures ANN and RBF NN are good function approximators. WT and EMD help these approx- imators by decomposing signals into higher and more useful dimensions. It must be noted that ANN gives different forecast results for each training stage because of random initial weight values for neurons.
All the structures and forecasting procedures are based on artificial intelligence.
In future studies, analytical methods will be used and analytical and artificial intelligence methods will be compared. Furthermore, a load forecasting procedure for local holidays will be proposed.
A.S. Pandey, D. Singh, S.K. Sinha, “Intelligent hybrid wavelet models for short-term load forecasting”, IEEE Transactions on Power Systems, Vol. 25, pp. 1266–1273, 2010.
A. Khotanzad, R. Afkhami-Rohani, T.L. Lu, A. Abaye, M. Davis, D.J. Maratukulam, “ANNSTLF: a neural- network-based electric load forecasting system”, IEEE Transactions on Neural Networks, Vol. 8, pp. 835–846, 1997.
M.S. Kıran, E. Ozceylan, M. Gunduz, T. Paksoy, “A novel hybrid approach based on particle swarm optimization and ant colony algortihm to forecast energy demand of Turkey”, Energy Conversion and Management, Vol. 53, pp. 75–83, 2012.
A. Azadeh, S.F. Ghadrei, B. Pourvalikhan Nokhandan, “Short term load forecasting by ANN”, Hybrid Intelligent Models and Applications, pp. 39–43, 2009.
G. Ceylan, A. Demiroren, “Yapay sinir a˘gları ile G¨olba¸sı b¨olgesinin kısa d¨onem y¨uk tahmini”, ELECO 2004, pp. 103–107, 2004.
Q.S. Chen, X. Zhang, S.H. Xiong, X.W. Chen, “Short-term load forecasting with least squares support vector machines and wavelet transform”, Proceedings of the Seventh International Conference on Machine Learning and Cybernetics Kunming, pp. 1425–1429, 2008.
N. Dongxiao, T. Jie, “Improved RBF network applied to short-term load forecasting”, ICSESS 2011, pp. 864–867, 2011.
Z. Gontar, N. Hatziargyriou, “Short term load forecasting with radial basis function network”, IEEE Porto Power Tech. Conference, 2001.
Y.J. He, Y.C. Zhu, D.X. Duan, W. Sun, “Application of neural network model based on combination of fuzzy classification and input selection in short term load forecasting”, Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, pp. 3152–3156, 2006.
A. Jain, B. Satish, “Integrated architecture for short-term load forecasting using support vector machines”, NAPS ‘08, pp. 1–8, 2008.
N. Lu, J. Zhou, “Particle swarm optimization-based RBF neural network load forecasting model”, APPEEC 2009, pp. 27–31, 2009.
Q. Mu, Y. Wu, X. Pan, L. Huang, X. Li, “Short-term load forecasting using improved similar days method”, APPEEC 2010, pp. 1–4, 2010.
H. Xu, J.H. Wang, S.Q. Zheng, “Online daily load forecasting based on support vector machines”, Proceedings of the Fourth International Conference on Machine Learning and Cybernetics Guangzhou, pp. 3985–3990, 2005.
Z. Zhu, Y. Sun, H. Li, “Hybrid of EMD and SVMs for short-term load forecasting”, ICCA 2007, pp. 1044–1047, 2007.
Y. Chen, P.B. Luh, C. Guan, Y. Zhao, L.D. Michel, M.A. Coolbeth, P.B. Friedland, S.J. Rourke, “Short-term load forecasting: similar day-based wavelet neural networks”, IEEE Transactions on Power Systems, Vol. 25, pp. 322–330, 2010.
R. Gao, L.H. Tsoukalas, “Neural-wavelet methodology for load forecasting”, Journal of Intelligent and Robotic Systems, Vol. 31, pp. 149–157, 2001.
A. Nalbant, Y. Aslan, C. Yasar, “K¨utahya ili i¸cin elektrik puant y¨uk tahmini”, Elektrik Elektronik Bilgisayar M¨uhendisli˘gi 11. Ulusal Kongresi, Vol. 1, pp. 211–214, 2005.
K.K. Sumer, O. G¨oktas, A. Hepsag, “The application of seasonal latent variable in forecasting electricity demand as an alternative method”, Energy Policy, Vol. 37, pp. 1317–1322, 2007.
J.W. Taylor, P.E. McSharry, “Short-term load forecasting methods: an evaluation based on European data”, IEEE Transactions on Power Systems, Vol. 22, 2213–2219.
T. Yalcinoz, S. Herdem, U. Eminoglu, “Yapay sinir a˘gları ile Ni˘gde b¨olgesinin elektrik y¨uk tahmini”, ELECO 2002, pp. 25–29, 2002.
K.H. Kim, H.S. Youn, Y.C. Kang, “Short-term load forecasting for special days in anomalous load conditions using neural networks and fuzzy inference method”, IEEE Transactions on Power Systems, Vol. 15, pp. 559–565, 2000.
K.B. Song, Y.S. Back, D.H. Hong, G. Jang, “Short-term load forecasting for the holidays using linear regression method”, IEEE Transactions on Power Systems, Vol. 20, pp. 96–101, 2005.
K. Ari, S. Ozen, O.H. Colak, Dalgacık Teorisi (Wavelet) Matlab Uygulamaları ˙Ile, Palme Publishing, 2008.
S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice Hall, 1998.
G. Rilling, P. Flandrin, P. Gon¸calv`es, “On empirical mode decomposition and its algorithms”, NSIP-03, 2003.