Forecasting Electricity Prices Using Exogenous Predictors

Since the liberalization of European electricity markets, stakeholders can actively participate in the trading of electricity. Successful participation in such markets requires an accurate forecast of future electricity prices. However, as large volumes of energy from renewable sources are fed into the system, electricity prices become highly volatile. While recent approaches put a strong focus on models from time series analysis using only historic prices, they neglect the influence of exogenous predictors. This paper identifies and includes a set of exogenous predictors, namely, expected solar and expected wind power generation, as well as planned power production according to the demand side. Consequently, we show that these externals decrease Root Mean Squared Errors by up to 23.33%. Second, a Diebold-Mariano test statistically proves that the forecasting accuracy of the proposed models is superior.

[1]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[2]  Michael Y. Hu,et al.  A Cross‐Validation Analysis of Neural Network Out‐of‐Sample Performance in Exchange Rate Forecasting , 1999 .

[3]  J. Contreras,et al.  ARIMA models to predict next-day electricity prices , 2002 .

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

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  T. Niimura,et al.  Short-term electricity price modeling and forecasting using wavelets and multivariate time series , 2004, IEEE PES Power Systems Conference and Exposition, 2004..

[7]  Chen-Ching Liu,et al.  State-of-the-art of electricity price forecasting , 2005, International Symposium CIGRE/IEEE PES, 2005..

[8]  J. Contreras,et al.  Forecasting electricity prices for a day-ahead pool-based electric energy market , 2005 .

[9]  Christopher R. Knittel,et al.  An empirical examination of restructured electricity prices , 2005 .

[10]  Peter Kosater.  On the impact of weather on German hourly power prices , 2006 .

[11]  R. Weron,et al.  Point and Interval Forecasting of Spot Electricity Prices: Linear vs. Non-Linear Time Series Models , 2006 .

[12]  Antonio J. Conejo,et al.  Electricity price forecasting through transfer function models , 2006, J. Oper. Res. Soc..

[13]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[14]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[15]  S. Rachev,et al.  Spot and Derivative Pricing in the EEX Power Market , 2007 .

[16]  N. Pindoriya,et al.  An Adaptive Wavelet Neural Network-Based Energy Price Forecasting in Electricity Markets , 2008, IEEE Transactions on Power Systems.

[17]  R. Weron,et al.  Forecasting spot electricity prices: A comparison of parametric and semiparametric time series models , 2008 .

[18]  Ashwani Kumar,et al.  Electricity price forecasting in deregulated markets: A review and evaluation , 2009 .

[19]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[20]  H. Madsen,et al.  On the market impact of wind energy forecasts , 2010 .

[21]  R. Green,et al.  Market behaviour with large amounts of intermittent generation , 2010 .

[22]  Chi-Keung Woo,et al.  The impact of wind generation on the electricity spot-market price level and variance: The Texas experience , 2011 .

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

[24]  Francesco Ravazzolo,et al.  The Power of Weather , 2009, Comput. Stat. Data Anal..

[25]  T. Kristiansen.  Forecasting Nord Pool day-ahead prices with an autoregressive model , 2012 .

[26]  Der-Chiang Li,et al.  Forecasting short-term electricity consumption using the adaptive grey-based approach—An Asian case , 2012 .

[27]  Amitava Bandyopadhayay,et al.  Forecasting day-ahead price of electricity – a dynamic regression approach , 2013 .

[28]  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 .

[29]  W. Fichtner,et al.  A combined modeling approach for wind power feed-in and electricity spot prices , 2013 .

[30]  Periklis Gogas,et al.  Forecasting energy markets using support vector machines , 2014 .

[31]  D. Bunn,et al.  The Forecasting Performance of a Finite Mixture Regime-Switching Model for Daily Electricity Prices , 2014 .

[32]  Xing Yan,et al.  Mid-term electricity market clearing price forecasting utilizing hybrid support vector machine and auto-regressive moving average with external input , 2014 .

[33]  Xing Yan,et al.  Mid-term electricity market clearing price forecasting: A multiple SVM approach , 2014 .

[34]  Stefan Feuerriegel,et al.  Predictive Analytics for electricity prices using Feed-INS from renewables , 2014, ECIS.

[35]  M. Delimar,et al.  Dynamic Hybrid Model for Short-Term Electricity Price Forecasting , 2014 .