Deep neural network based demand side short term load forecasting

In smart grid, one of the most important research areas is load forecasting; it spans from traditional time series analysis to recent machine learning approach 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 demand side empirical load database. DNNs are trained by two different ways: pre-training restricted Boltzmann machine and using 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 shallow neural network (SNN), and double seasonal Holt-Winters (DSHW) model. The mean absolute percentage error (MAPE) and relative root mean square error (RRMSE) are used for verification. The results show that DNNs exhibit accurate and robust forecasts 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.

[1]  Hongseok Kim,et al.  Data-Driven Baseline Estimation of Residential Buildings for Demand Response , 2015 .

[2]  P. McSharry,et al.  A comparison of univariate methods for forecasting electricity demand up to a day ahead , 2006 .

[3]  Ram Rajagopal,et al.  Short Term Electricity Load Forecasting on Varying Levels of Aggregation , 2014, ArXiv.

[4]  C. Cañizares,et al.  ANN-based short-term load forecasting in electricity markets , 2001, 2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194).

[5]  VASSILIS S. KODOGIANNIS,et al.  A Clustering-Based Fuzzy Wavelet Neural Network Model for Short-Term Load Forecasting , 2013, Int. J. Neural Syst..

[6]  Le Zhang,et al.  Ensemble deep learning for regression and time series forecasting , 2014, 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL).

[7]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[8]  Hossein Shayeghi,et al.  A Neural Network Based Short Term Load Forecasting , 2007, IC-AI.

[9]  Carlos Cardeira,et al.  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☆ , 2014 .

[10]  Mario Vasak,et al.  Deep neural networks for ultra-short-term wind forecasting , 2015, 2015 IEEE International Conference on Industrial Technology (ICIT).

[11]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[12]  J. Theocharis,et al.  A novel approach to short-term load forecasting using fuzzy neural networks , 1998 .

[13]  Hongseok Kim,et al.  A framework for baseline load estimation in demand response: Data mining approach , 2014, 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[14]  Jaime Lloret,et al.  Short-Term Load Forecasting for Microgrids Based on Artificial Neural Networks , 2013 .

[15]  Z.A. Bashir,et al.  Applying Wavelets to Short-Term Load Forecasting Using PSO-Based Neural Networks , 2009, IEEE Transactions on Power Systems.

[16]  Yoshua Bengio,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2010, AISTATS.

[17]  J. W. Taylor,et al.  Short-term electricity demand forecasting using double seasonal exponential smoothing , 2003, J. Oper. Res. Soc..

[18]  Mohammed H. Albadi,et al.  A summary of demand response in electricity markets , 2008 .

[19]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[20]  Madeleine Gibescu,et al.  Deep learning for estimating building energy consumption , 2016 .

[21]  H. Farhangi,et al.  The path of the smart grid , 2010, IEEE Power and Energy Magazine.

[22]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[23]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[24]  Madeleine Gibescu,et al.  Unsupervised energy prediction in a Smart Grid context using reinforcement cross-building transfer learning , 2016 .

[25]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[26]  S. J. Kiartzis,et al.  A neural network short term load forecasting model for the Greek power system , 1996 .

[27]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[28]  S. Fan,et al.  Short-term load forecasting based on an adaptive hybrid method , 2006, IEEE Transactions on Power Systems.

[29]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[30]  Wan He,et al.  Deep neural network based load forecast , 2014 .

[31]  Mehmed Kantardzic,et al.  Learning from Data , 2011 .

[32]  Hossein Shayeghi,et al.  Intelligent Neural Network Based STLF , 2009 .

[33]  Farrokh Albuyeh,et al.  Grid of the future , 2009, IEEE Power and Energy Magazine.

[34]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.