Forecasting Tariffs for the Day-Ahead Market Based on the Additive Model

The problem of constructing an additive model for forecasting of the market tariff for the day ahead is solved. The trend component is constructed on the basis of the autoregressive model of already known values of the day-ahead market tariff and the external factor of electricity consumption according to the United Energy System (UES) of the Urals Wholesale Electricity and Power Market (OREM) of Russia for 2009-2018. Based on the construction of the autocorrelation function, three seasonal components are identified in the time series of hourly values of the market tariff for the day ahead: annual (8760 values), weekly (168 values), daily (24 values). A harmonic model of each component is constructed. The final additive model is constructed taking into account the specifics of the electricity market and the process of setting the market tariff for the day ahead and a balancing market. The practical significance of the developed additive model is adequate accuracy with the well-known models for forecasting of the market tariff for the day ahead of the UES of the Urals. The proposed model allows the subjects of the electric power industry to avoid penalties from the balancing market by ensuring high accuracy of forecasting.

Keywords

modelling; forecasting; autoregression; additive model; electric power industry; energy market.

References

1. Garcia R.C. Forecasting Model to Predict Day-Ahead Electricity Prices. IEEE Transactions on Power Systems, 2005, vol. 20, no. 2, pp. 867-874. DOI: 10.1109/TPWRS.2005.846044
2. Mokhov V.G., Demyanenko T.S. The Construction of the Trend Component of the Additive Model of Long-Term Forecasting of the Wholesale Market of Electric Energy and Power of Russia Using the Example of the Ural Energy System. Bulletin of the South Ural State University. Series: Economics and Management, 2018, vol. 12, no. 2, pp. 80-87. DOI: 10.14529/em180209
3. Taylor J.W., McSharry P.E. Short-Term Load Forecasting Methods: an Evaluation Based on European Data. IEEE Transactions on Power Systems, 2008, vol. 22, pp. 2213-2219. DOI: 10.1109/TPWRS.2007.907583
4. Taylor J.W., Short-Term Electricity Demand Forecasting Using Double Seasonal Exponential Smoothing. Journal of Operational Research Society, 2003, vol. 54, pp. 799-805. DOI: 10.1057/palgrave.jors.2601589
5. Perez, M. tTime Series Analysis with Matlab. ARIMA and ARIMAX Models. Scotts Valley, CreateSpace Independent Publishing Platform, 2016.