论文信息 - Deep Neural Network Regression for Short-Term Load Forecasting of Natural Gas

Deep Neural Network Regression for Short-Term Load Forecasting of Natural Gas

This paper proposes a short-term load forecasting method for natural gas using deep learning. Deep learning has proven to be a powerful tool for many classification problems seeing significant use in machine learning fields like image recognition and speech processing. This paper explores many aspects of using deep neural networks for time series forecasting. It is determined that the proposed network outperforms traditional artificial neural networks and linear regression based forecasters.

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

[2] S. Muto,et al. Regression based peak load forecasting using a transformation technique , 1994 .

[3] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[4] Yee Whye Teh,et al. A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[5] Gregory Merkel,et al. Deep Neural Networks As Time Series Forecasters of Energy Demand , 2017 .

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

[7] Richard J. Povinelli,et al. Deep Neural Network Regression as a Component of a Forecast Ensemble , 2017 .

[8] Amy Loutfi,et al. A review of unsupervised feature learning and deep learning for time-series modeling , 2014, Pattern Recognit. Lett..

[9] George F. Corliss,et al. Mathematical Models for Natural Gas Forecasting , 2009 .