When building stochastic models for electricity spot prices the problem of uttermost importance is the estimation and consequent forecasting of a component to deal with trends and seasonality in the data. While the short-term seasonal components (daily, weekly) are more regular and less important for valuation of typical power derivatives, the long-term seasonal components (LTSC; seasonal, annual) are much more difficult to tackle. Surprisingly, in many academic papers dealing with electricity spot price modeling the importance of the seasonal decomposition is neglected and the problem of forecasting it is not considered. With this paper we want to fill the gap and present a thorough study on estimation and forecasting of the LTSC of electricity spot prices. We consider a battery of models based on Fourier or wavelet decomposition combined with linear or exponential decay. We find that all considered wavelet-based models are significantly better in terms of forecasting spot prices up to a year ahead than all considered sine-based models. This result questions the validity and usefulness of stochastic models of spot electricity prices built on sinusoidal long-term seasonal components.
We present the results of a study on modeling and forecasting of the long-term seasonal component (LTSC) of electricity spot prices. We consider a vast array of models including linear regressions, monthly dummies, sinusoidal decompositions and wavelet smoothers. We find that in terms of forecasting EEX and Nord Pool spot prices up to a year ahead, wavelet-based models significantly outperform all considered piecewise constant and sine-based models. This result challenges the traditional approach to deseasonalize spot electricity prices by fitting monthly dummies or sinusoidal functions. We also find that extending the calibration window up to four years does not improve the results; two-and especially three-year windows lead to better spot price forecasts.
in this paper the authors present an original methodology that may be useful for dedicated online compressed air consumption analyses for end-point devices. Unlike the classical forward engineering approaches, which are based on a detailed compressed air system description, the presented solution is based on reverse engineering and needs very little initial data. The proposed analytical approach is based on observations of machine behaviour. The presented results can be easily applicable for the assessment of energy efficiency, monitoring the degradation parameters of machines and quickly detecting anomalies in existing compressed air end point devices.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.