Abstract
Forecasting energy load demand data based on high frequency time series has become of primary importance for energy suppliers in nowadays competitive electricity markets. In this work, we model the time series of Italian electricity consumption from 2004 to 2014 using an exponential smoothing approach. Data are observed hourly showing strong seasonal patterns at different frequencies as well as some calendar effects. We combine a parsimonious model representation of the intraday and intraweek cycles with an additional seasonal term that captures the monthly variability of the series. Irregular days, such as public holidays, are modelled separately by adding a specific exponential smoothing seasonal term. An additive ARMA error term is then introduced to lower the volatility of the estimated trend component and the residuals’ autocorrelation. The forecasting exercise demonstrates that the proposed model performs remarkably well, in terms of lower root mean squared error and mean absolute percentage error criteria, in both short term and medium term forecasting horizons.
Similar content being viewed by others
References
Bartolomei SM, Sweet AL (1989) A note on a comparison of exponential smoothing methods for forecasting seasonal series. Int J Forecast 5:111–116
Billah B, King ML, Snyder RD, Koehler AB (2006) Exponential smoothing model selection for forecasting. Int J Forecast 22:239–247
Cancelo JR, Espasa A, Grafe R (2008) Forecasting from one day to one week ahead for the Spanish system operator. Int J Forecast 24:588–602
De Livera AM, Hyndman RJ, Snyder RD (2011) Forecasting time series with complex seasonal patterns using exponential smoothing. J Am Stat Assoc 106:1513–1527
Durbin J, Koopman SJ (2012) Time series analysis by state space methods, 2nd edn. Oxford University Press, Oxford
Gardner ES (2006) Exponential smoothing: the sate of the art-Part II. Int J Forecast 22:637–666
Gould PG, Koehler AB, Ord JK, Snyder RD, Hyndman RJ, Vahid-Araghi F (2008) Forecasting time series with multiple seasonal patterns. Eur J Oper Res 191:207–222
Hagan MT, Behr SM, Ord JK (1987) The time series approach to short-term forecasting. IEEE Trans Power Syst 2:785–791
Harvey AC (1989) Forecasting structural time series models and the Kalman filter. Cambridge University Press, Cambridge
Harvey AC, Koopman SJ, Riani M (1997) Forecasting hourly electricity demand using time-varying splines. J Am Stat Assoc 88:1228–1236
Harvey AC, Koopman SJ, Riani M (1997) The modelling and seasonal adjustment of weekly observations. J Bus Econ Stat 15:354–368
Hippert HS, Pedreira CE, Souza RC (2001) Neural networks for short-term load forecasting: a review and evaluation. IEEE Trans Power Syst 16:44–55
Holt CC (1957) Forecasting trends and seasonals by exponentially weighted averages. Carnegie Institute of Technology, Pittsburgh ONR memorandum no 52
Hyndman RJ, Koehler AB, Snyder RD, Grose S (2002) A state space framework for automatic forecasting using exponential smoothing methods. Int J Forecast 18:439–454
Hyndman RJ, Koehler AB, Ord JK, Snyder RD (2005) Prediction intervals for exponential smoothing using two new classes of state space models. J Forecast 24:17–37
Hyndman RJ, Koehler AB, Ord JK, Snyder RD (2008b) Forecasting with exponential smoothing. The state space approach. Springer, Berlin
Hu Z, Bao Y, Xiong T (2013) Electricity load forecasting using support vector regression with memetic algorithms. Sci World J Article ID 292575, p 10 doi:10.1155/2013/292575
Huang SJ, Shih KR (2003) Short-term load forecasting via ARMA model identification including nongaussian process considerations. IEEE Trans Power Syst 18:673–679
Kuusisto S, Lehtokangas M, Saarinen J, Kaski K (1997) Short term electric load forecasting using a neural network with fuzzy hidden neurons. Neural Comput Appl 6:42–56
Lu CN, Vemuri S (1993) Neural network based short term load forecasting. IEEE Trans Power Syst 8:336–342
Mandal P, Senjyu T, Urasaki N, Funabashi T (2006) A neural network based several-hour-ahead electric load forecasting using similar days approach. Int J Electr Power Energy Syst 28:367–373
Mbmalu GAN, El-Hawary ME (1993) Load forecasting via suboptimal seasonal autoregressive models and iteratively reweighted least squares estimation. IEEE Trans Power Syst 8:343–348
Makridakis S, Hibon M (2000) The M3-competition: results, conclusions and implications. Int J Forecast 16:451–476
Moghram I, Rahman S (1989) Analysis and evaluation of five short-term load forecasting techniques. IEEE Trans Power Syst 4:1484–1491
Monahan JF (1984) A note on enforcing stationarity in autoregressive moving average models. Biometrika 71:403–404
Ord JK, Koehler AB, Snyder RD (1997) Estimation and prediction for a class of dynamic nonlinear statistical models. J Am Stat Assoc 92:1621–1629
Papalexopoulos AD, Hesterberg TC (1990) A regression-based approach to short-term load forecasting. IEEE Trans Power Syst 5:1535–1550
Rahman S, Hazim O (1996) Load forecasting for multiple sites: development of an expert system-based technique. Electr Power Syst Res 39:161–169
Snyder RD (1985) Recursive estimation of dynamic linear models. J R Stat Soc Ser B 47:272–276
Taylor JW (2003) Short-term electricity demand forecasting using double seasonal exponential smoothing. J Oper Res Soc 54:799–805
Taylor JW (2008) A comparison of time series methods for forecasting intraday arrivals at a call center. Manag Sci 54:253–265
Taylor JW (2010a) Triple seasonal methods for short-term electricity demand forecasting. Eur J Oper Res 204:139–152
Taylor JW (2010b) Exponentially weighted methods for forecasting intraday time series with multiple seasonal cycles. Int J Forecast 26:627–646
Taylor JW, Snyder RD (2012) Forecasting intraday time series with multiple seasonal cycles using parsimonious seasonal exponential smoothing. Omega 40:748–757
Acknowledgments
This work has been partially supported by the 2010 Sapienza Research Project “Analisi Statistica per la Previsione dei Consumi di Energia Elettrica e della Produzione da Fonti Energetiche Alternative” and by the Italian Ministry of Research PRIN 2013–2015, “Multivariate Statistical Methods for Risk Assessment” (MISURA), by the 2011 Sapienza University of Rome Research Project and by the “Carlo Giannini Research Fellowship”, the “Centro Interuniversitario di Econometria” (CIdE) and “UniCredit Foundation”.
Author information
Authors and Affiliations
Corresponding author
Appendix: Competing models
Appendix: Competing models
In this “Appendix”, we shortly describe the alternative model formulations we consider as benchmark to test the forecasting ability of the proposed model. The double seasonal exponential smoothing model of Taylor (2003), named \({\mathcal {M}}_{\mathsf {DES}}^{\mathsf {AR}}\), is specified as follows:
where all the parameters \(\left( \alpha ,\gamma _1,\gamma _2,\phi \right) \) are restricted to belong to the unit interval, i.e. \(\left( 0,1\right) \), and, for homogeneity we assume \(\zeta _t\) to be independently and identically distributed drawn from a standardised Gaussian random variable, i.e. \(\zeta _t\sim {\mathcal {N}}\left( 0,1\right) \). Here \(m_1=24\) is the daily seasonal period in hours, while \(m_2=24\times 7\) denotes the weekly seasonal period.
The triple seasonal exponential smoothing model of Taylor (2010a), named \({\mathcal {M}}_{\mathsf {TES}}^{\mathsf {AR}}\), include an additional seasonal term accounting for the annual cycle:
where the additional smoothing parameter \(\gamma _\mathsf {Y}\in \left( 0,1\right) \) account for the annual cycle. The period of the annual cycle is set to \(m_3=24\times 7 \times 52\), about 52 weeks of data. As before, the stochastic term \(\zeta _t\) are independently and identically distributed drawn from a standardised Gaussian distribution, i.e. \(\zeta _t\sim {\mathcal {N}}\left( 0,1\right) \). Finally, the parsimonious multiple seasonal patterns exponential smoothing model of Taylor and Snyder (2012), denoted \({\mathcal {M}}_{\mathsf {MSPT}}^{\mathsf {AR}}\), consists of the following set of equations
where \(x_{it}\), for \(i=1,2,\dots ,k\) have been previously defined and \(\zeta _t\sim {\mathcal {N}}\left( 0,1\right) \), independently and identically distributed. Of course, \(s_{k+1,t}\) denotes the yearly seasonal cycle of period \(m_3=24\times 7 \times 52\) h, while \(m_1\) and \(m_2\) are the daly and weekly seasonal period, respectively. All the alternative model are estimated by minimising the Gaussian log-likelihood function over the same in sample period used for the proposed model. In particular we employed the same two step procedure consisting of running the simulated annealing procedure whose optimal values are subsequently introduced as starting values for a standard quasi Newton–Raphson algorithm. Concerning the specification of the seasonal patterns for the different days of the week in the multiple seasonal pattern model of Taylor and Snyder (2012), we used the same parsimonious representation of the daily seasonal cycles identified for our model. This means that we only consider 5 different daily patterns and we do not consider a specific cycle for the irregular days
Rights and permissions
About this article
Cite this article
Bernardi, M., Petrella, L. Multiple seasonal cycles forecasting model: the Italian electricity demand. Stat Methods Appl 24, 671–695 (2015). https://doi.org/10.1007/s10260-015-0313-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-015-0313-z
Keywords
- Electricity demand forecasting
- Exponential smoothing
- Multiple seasonality
- Single source of error models