Rolling Forecast Nature Gas Spot Price with Back Propagation Neural Network

Investment of integrated energy system (IES) is usually faced with a high degree of risk due to uncertainty associated with nature gas price. Therefore, accurate prediction of nature gas price is critical in the planning of IES, which can make better strategies with minimized risk. This paper presents a rolling back propagation (BP) neural network method to forecast the long-term monthly nature gas spot prices (GSP). The rolling forecast of monthly nature GSP is realized by using the previous output of network as part of the next input of network for rolling training and forecasting. Then, a rolling forecast for the monthly nature GSP is being done based on the historical spot price data from Henry Hub. The error of forecast result is analyzed and obtained the probability distribution function (PDF) of the forecast error. Numerical testing shows that this method can provide accurate predictions.

[1]  Markus Weinmann,et al.  Forecasting day ahead spot price movements of natural gas – An analysis of potential influence factors on basis of a NARX neural network , 2012, MKWI 2012.

[2]  Jun Chen,et al.  Application of BP Neural Networks based on genetic simulated annealing algorithm for shortterm electricity price forecasting , 2014, 2014 International Conference on Advances in Electrical Engineering (ICAEE).

[3]  Ian T. Nabney,et al.  Short-term electricity demand and gas price forecasts using wavelet transforms and adaptive models , 2010 .

[4]  C. Wooa,et al.  Market efficiency , cross hedging and price forecasts : California ’ s natural-gas markets , 2006 .

[5]  Kit Po Wong,et al.  Electricity Price Forecasting With Extreme Learning Machine and Bootstrapping , 2012, IEEE Transactions on Power Systems.

[6]  Vinod Mishra,et al.  Are natural gas spot and futures prices predictable , 2016 .

[7]  Apostolos Serletis,et al.  Returns and volatility in the NYMEX Henry Hub natural gas futures market , 2006 .

[8]  Narges Salehnia,et al.  Forecasting natural gas spot prices with nonlinear modeling using Gamma test analysis , 2013 .

[9]  Jing Gao,et al.  Research on electricity price forecasting method based on genetic algorithm and neural network in power market , 2018, 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2).

[10]  Vladimir Ceperic,et al.  Short-term forecasting of natural gas prices using machine learning and feature selection algorithms , 2017 .

[11]  S. B. Patil,et al.  Day ahead price forecasting in deregulated electricity market using Artificial Neural Network , 2016, 2016 International Conference on Energy Efficient Technologies for Sustainability (ICEETS).

[12]  N. Sadati,et al.  Electricity Price Forecasting Using Artificial Neural Network , 2006, 2006 International Conference on Power Electronic, Drives and Energy Systems.

[13]  A. Azadeh,et al.  A Hybrid Neuro-Fuzzy Approach for Improvement of Natural Gas Price Forecasting in Vague and Noisy Environments : Domestic and Industrial Sectors , 2022 .