Deep Neural Network Based Demand Side Short Term Load Forecasting
Tóm tắt
In the smart grid, one of the most important research areas is load forecasting; it spans from traditional time series analyses to recent machine learning approaches and mostly focuses on forecasting aggregated electricity consumption. However, the importance of demand side energy management, including individual load forecasting, is becoming critical. In this paper, we propose deep neural network (DNN)-based load forecasting models and apply them to a demand side empirical load database. DNNs are trained in two different ways: a pre-training restricted Boltzmann machine and using the rectified linear unit without pre-training. DNN forecasting models are trained by individual customer’s electricity consumption data and regional meteorological elements. To verify the performance of DNNs, forecasting results are compared with a shallow neural network (SNN), a double seasonal Holt–Winters (DSHW) model and the autoregressive integrated moving average (ARIMA). The mean absolute percentage error (MAPE) and relative root mean square error (RRMSE) are used for verification. Our results show that DNNs exhibit accurate and robust predictions compared to other forecasting models, e.g., MAPE and RRMSE are reduced by up to 17% and 22% compared to SNN and 9% and 29% compared to DSHW.
Từ khóa
Tài liệu tham khảo
Feinberg, E.A., and Genethliou, D. (2005). Applied Mathematics for Restructured Electric Power Systems, Springer.
Albadi, 2008, A summary of demand response in electricity markets, Electr. Power Syst. Res., 78, 1989, 10.1016/j.epsr.2008.04.002
Park, 2015, Data-driven baseline estimation of residential buildings for demand response, Energies, 8, 10239, 10.3390/en80910239
Hagan, 1987, The time series approach to short term load forecasting, IEEE Trans. Power Syst., 2, 785, 10.1109/TPWRS.1987.4335210
Taylor, 2003, Short-term electricity demand forecasting using double seasonal exponential smoothing, J. Oper. Res. Soc., 54, 799, 10.1057/palgrave.jors.2601589
Taylor, 2006, A comparison of univariate methods for forecasting electricity demand up to a day ahead, Int. J. Forecast., 22, 1, 10.1016/j.ijforecast.2005.06.006
Park, 1991, Electric load forecasting using an artificial neural network, IEEE Trans. Power Syst., 6, 442, 10.1109/59.76685
Hernandez, 2013, Short-term load forecasting for microgrids based on artificial neural networks, Energies, 6, 1385, 10.3390/en6031385
Hippert, 2001, Neural networks for short-term load forecasting: A review and evaluation, IEEE Trans. Power Syst., 16, 44, 10.1109/59.910780
Bakirtzis, 1996, A neural network short term load forecasting model for the Greek power system, IEEE Trans. Power Syst., 11, 858, 10.1109/59.496166
Lu, 1993, Neural network based short term load forecasting, IEEE Trans. Power Syst., 8, 336, 10.1109/59.221223
Rodrigues, 2014, The daily and hourly energy consumption and load forecasting using artificial neural network method: A case study using a set of 93 households in Portugal, Energy Procedia, 62, 220, 10.1016/j.egypro.2014.12.383
Chen, H., Cañizares, C., and Singh, A. (February, January 28). ANN-based short-term load forecasting in electricity markets. Proceedings of the 2001 IEEE Power Engineering Society Winter Meeting, Columbus, OH, USA.
Papadakis, 1998, A novel approach to short-term load forecasting using fuzzy neural networks, IEEE Trans. Power Syst., 13, 480, 10.1109/59.667372
Bashir, 2009, Applying wavelets to short-term load forecasting using PSO-based neural networks, IEEE Trans. Power Syst., 24, 20, 10.1109/TPWRS.2008.2008606
Kodogiannis, V.S., Amina, M., and Petrounias, I. (2013). A clustering-based fuzzy wavelet neural network model for short-term load forecasting. Int. J. Neural Syst., 23.
Shayeghi, 2009, Intelligent neural network based STLF, Int. J. Comput. Syst. Sci. Eng., 4, 17
Fan, 2006, Short-term load forecasting based on an adaptive hybrid method, IEEE Trans. Power Syst., 21, 392, 10.1109/TPWRS.2005.860944
Park, S., Ryu, S., Choi, Y., and Kim, H. (2014, January 3–6). A framework for baseline load estimation in demand response: Data mining approach. Proceedings of the 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), Venice, Italy.
Dalto, M., Matusko, J., and Vasak, M. (2015, January 17–19). Deep neural networks for ultra-short-term wind forecasting. Proceedings of the 2015 IEEE International Conference on Industrial Technology (ICIT), Seville, Spain.
He, 2014, Deep neural network based load forecast, Comput. Model. New Technol., 18, 258
Qiu, X., Zhang, L., Ren, Y., Suganthan, P.N., and Amaratunga, G. (2014, January 9–12). Ensemble deep learning for regression and time series forecasting. Proceedings of the 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL), Orlando, FL, USA.
Hinton, 2006, Reducing the dimensionality of data with neural networks, Science, 313, 504, 10.1126/science.1127647
Leshno, 1993, Multilayer feedforward networks with a nonpolynomial activation function can approximate any function, Neural Netw., 6, 861, 10.1016/S0893-6080(05)80131-5
Abu-Mostafa, Y.S., Magdon-Ismail, M., and Lin, H.T. (2012). Learning from Data, AMLBook.
Erhan, 2010, Why does unsupervised pre-training help deep learning?, J. Mach. Learn. Res., 11, 625
Maas, A.L., Hannun, A.Y., and Ng, A.Y. (2013, January 16–21). Rectifier nonlinearities improve neural network acoustic models. Proceedings of the International Machine Learning Society, Atlanta, GA, USA.
Drees, M. (2013). Implementierung und Analyse von Tiefen Architekturen in R. [Master’s Thesis, Fachhochschule Dortmund].
Simard, P.Y., Steinkraus, D., and Platt, J.C. (2003, January 3–6). Best practices for convolutional neural networks applied to visual document analysis. Proceedings of the 2003 7th International Conference on Document Analysis and Recognition (ICDAR), Edinburgh, UK.
Riedmiller, M., and Braun, H. (April, January 28). A direct adaptive method for faster backpropagation learning: The RPROP algorithm. Proceedings of the 1993 IEEE International Conference On Neural Networks, San Francisco, CA, USA.
Srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15, 1929
Sevlian, R., and Rajagopal, R. (2014). Short term electricity load forecasting on varying levels of aggregation. Statistics.