Using neural networks and extreme value distributions to model electricity pool prices: Evidence from the Australian National Electricity Market 1998-2013

Abstract Competitors in the electricity supply industry desire accurate predictions of electricity spot prices to hedge against financial risks. Neural networks are commonly used for forecasting such prices, but certain features of spot price series, such as extreme price spikes, present critical challenges for such modeling. We investigate the predictive capacity of neural networks for electricity spot prices using Australian National Electricity Market data. Following neural net modeling of the data, we explore extreme price spikes through extreme value modeling, fitting a Generalized Pareto Distribution to price peaks over an estimated threshold. While neural nets capture the smoother aspects of spot price data, they are unable to capture local, volatile features that characterize electricity spot price data. Price spikes can be modeled successfully through extreme value modeling.

[1]  Tomonobu Senjyu,et al.  Next day price forecasting in deregulated market by combination of Artificial Neural Network and ARIMA time series models , 2009, 2010 5th IEEE Conference on Industrial Electronics and Applications.

[2]  J. Pickands.  Statistical Inference Using Extreme Order Statistics , 1975 .

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

[4]  Murray Smith,et al.  Neural Networks for Statistical Modeling , 1993 .

[5]  A. Kazemi,et al.  Day-ahead price forecasting in restructured power systems using artificial neural networks , 2008 .

[6]  Alberto Gómez,et al.  Forecasting next-day price of electricity in the Spanish energy market using artificial neural networks , 2008, Eng. Appl. Artif. Intell..

[7]  Kostas S. Metaxiotis,et al.  Artificial intelligence in short term electric load forecasting: a state-of-the-art survey for the researcher , 2003 .

[8]  J. Partanen,et al.  Price Forecasting in the Day-Ahead Energy Market by an Iterative Method with Separate Normal Price and Price Spike Frameworks , 2013 .

[9]  Zuyi Li,et al.  Adaptive short-term electricity price forecasting using artificial neural networks in the restructured power markets , 2004 .

[10]  Arvid Naess,et al.  Combination of the peaks-over-threshold and bootstrapping methods for extreme value prediction , 2001 .

[11]  J. Lima,et al.  Simulating Electricity Spot Prices in Brazil Using Neural Network and Design of Experiments , 2007, 2007 IEEE Lausanne Power Tech.

[12]  J. Contreras,et al.  Forecasting next-day electricity prices by time series models , 2002 .

[13]  Mahesh D. Pandey,et al.  Bootstrap simulations for evaluating the uncertainty associated with peaks‐over‐threshold estimates of extreme wind velocity , 2003 .

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

[15]  Øystein Wormstrand,et al.  Electricity price prediction: a comparison of machine learning algorithms , 2011 .

[16]  Siem Jan Koopman,et al.  Periodic Seasonal Reg-ARFIMA–GARCH Models for Daily Electricity Spot Prices , 2007 .

[17]  Rosa Espínola,et al.  The effect of wind generation and weekday on Spanish electricity spot price forecasting , 2011 .

[18]  Hsiao-Tien Pao,et al.  Forecasting electricity market pricing using artificial neural networks , 2007 .

[19]  C. S. Chang,et al.  Real-time pricing related short-term load forecasting , 1998, Proceedings of EMPD '98. 1998 International Conference on Energy Management and Power Delivery (Cat. No.98EX137).

[20]  V. Mendes,et al.  Short-term electricity prices forecasting in a competitive market: A neural network approach , 2007 .

[21]  A. Gil,et al.  Forecasting of electricity prices with neural networks , 2006 .

[22]  D. Sansom,et al.  Neural networks for forecasting electricity pool price in a deregulated electricity supply industry , 1999 .