On the importance of the long-term seasonal component in day-ahead electricity price forecasting

A recent electricity price forecasting study has shown that the Seasonal Component AutoRegressive (SCAR) modeling framework, which consists of decomposing a series of spot prices into a trend-seasonal and a stochastic component, modeling them independently and then combining their forecasts, can yield more accurate point predictions than an approach in which the same autoregressive model is calibrated to the prices themselves. Here, we show that further accuracy gains can be achieved when the explanatory variables (load forecasts) are deseasonalized as well. More importantly, considering a novel extension of the SCAR concept to probabilistic forecasting and applying two methods of combining predictive distributions we find that (i) SCAR-type models nearly always significantly outperform the autoregressive benchmark but are in turn outperformed by combined SCAR forecasts, (ii) predictive distributions computed using Quantile Regression Averaging (QRA) outperform those obtained from historical simulation and bootstrap methods, and (iii) averaging over predictive distributions generally yields better probabilistic forecasts of electricity spot prices than averaging over quantiles.

[1]  Derek W. Bunn,et al.  Analysis and Forecasting of Electricty Price Risks with Quantile Factor Models , 2016 .

[2]  T. Gneiting.  Quantiles as optimal point forecasts , 2011 .

[3]  Jakub Nowotarski,et al.  LTSC_EXAMPLE: MATLAB example script and data for "Robust estimation and forecasting of the long-term seasonal component of electricity spot prices" , 2013 .

[4]  Francesco Lisi,et al.  Combining day-ahead forecasts for British electricity prices , 2013 .

[5]  Rob J Hyndman,et al.  Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond , 2016 .

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

[7]  P. Gaillard,et al.  Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting , 2016 .

[8]  R. Weron,et al.  Recent advances in electricity price forecasting: A review of probabilistic forecasting , 2016 .

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

[10]  Jakub Nowotarski,et al.  Computing electricity spot price prediction intervals using quantile regression and forecast averaging , 2015, Comput. Stat..

[11]  Florian Ziel,et al.  Electricity price forecasting using sale and purchase curves: The X-Model , 2015, 1509.00372.

[12]  N. Amjady,et al.  Energy price forecasting - problems and proposals for such predictions , 2006 .

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

[14]  Yachao Zhang,et al.  Deterministic and probabilistic interval prediction for short-term wind power generation based on variational mode decomposition and machine learning methods , 2016 .

[15]  Jakub Nowotarski,et al.  A hybrid model for GEFCom2014 probabilistic electricity price forecasting , 2016 .

[16]  R. Weron,et al.  Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate models , 2016 .

[17]  Carolina García-Martos,et al.  Seasonal Dynamic Factor Analysis and Bootstrap Inference: Application to Electricity Market Forecasting , 2011, Technometrics.

[18]  Chris Chatfield,et al.  Time‐series forecasting , 2000 .

[19]  Florian Ziel,et al.  Forecasting Electricity Spot Prices Using Lasso: On Capturing the Autoregressive Intraday Structure , 2015, IEEE Transactions on Power Systems.

[20]  Kit Po Wong,et al.  A Hybrid Approach for Probabilistic Forecasting of Electricity Price , 2014, IEEE Transactions on Smart Grid.

[21]  Francesco Lisi,et al.  Component estimation for electricity prices: Procedures and comparisons , 2014 .

[22]  Joanna Janczura,et al.  Identifying Spikes and Seasonal Components in Electricity Spot Price Data: A Guide to Robust Modeling , 2012 .

[23]  Francesco Serinaldi,et al.  Distributional modeling and short-term forecasting of electricity prices by Generalized Additive Models for Location, Scale and Shape , 2011 .

[24]  Rafał Weron,et al.  Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks , 2018, 1805.06649.

[25]  C. Alexander,et al.  Market risk analysis IV: value-at-risk models , 2008 .

[26]  A. Walden,et al.  Wavelet Methods for Time Series Analysis , 2000 .

[27]  Tao Hong,et al.  Improving short term load forecast accuracy via combining sister forecasts , 2016 .

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

[29]  Rafał Weron,et al.  On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks , 2019, International Journal of Forecasting.

[30]  Tao Hong,et al.  Probabilistic electric load forecasting: A tutorial review , 2016 .

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

[32]  R. Weron,et al.  Probabilistic forecasting of electricity spot prices using Factor Quantile Regression Averaging , 2016 .

[33]  Jakub Nowotarski,et al.  Automated Variable Selection and Shrinkage for Day-Ahead Electricity Price Forecasting , 2016 .

[34]  R. Weron.  Electricity price forecasting: A review of the state-of-the-art with a look into the future , 2014 .

[35]  Rafał Weron,et al.  A note on using the Hodrick-Prescott filter in electricity markets , 2014 .

[36]  Tao Hong,et al.  Probabilistic Load Forecasting via Quantile Regression Averaging on Sister Forecasts , 2017, IEEE Transactions on Smart Grid.

[37]  R. Weron.  Modeling and Forecasting Electricity Loads and Prices: A Statistical Approach , 2006 .

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

[39]  Yael Grushka-Cockayne,et al.  Is it Better to Average Probabilities or Quantiles? , 2012, Manag. Sci..

[40]  Jakub Nowotarski,et al.  On the importance of the long-term seasonal component in day-ahead electricity price forecasting , 2016, Energy Economics.

[41]  Michael R. Chernick,et al.  Wavelet Methods for Time Series Analysis , 2001, Technometrics.

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

[43]  Jakub Nowotarski,et al.  An empirical comparison of alternate schemes for combining electricity spot price forecasts , 2013 .

[44]  Saeid Nahavandi,et al.  Quantifying uncertainties of neural network-based electricity price forecasts , 2013 .

[45]  E. Prescott,et al.  Postwar U.S. Business Cycles: An Empirical Investigation , 1997 .