A new approach to modeling cycles with summer and winter demand peaks as input variables for deep neural networks

Abstract

Electricity demand is highly cyclical. In many markets, two demand peaks are observed – winter and summer. The paper presents a new, complex approach to modeling this type of cycles using trigonometric functions and long-term changes using the sliding window technique. The proposed method allows the modeling of annual cycles with asymmetrically located upper maxima of the demand. The new formulas take into account the moments of each peak occurrence, their values, as well as the demand course between them. All parameters can be selected in an algorithmic manner. Due to the modeling of each of the 24 h separately, it is possible to take into consideration the differences in the course of the cycles for each of them. The approach was tested in three electricity markets that differ in the demand pattern, with a different relation between values of winter and summer peaks. The precision of the proposed approach was verified by deep neural networks. They were used to forecast electricity demand for each of the 24 h of the day, one day ahead. As comparative models, deep neural networks based on lagged values of demand were used. A large test dataset out of sample forecasts covering a period of two calendar years was used. This showed that the proposed novel approach significantly reduces the mean absolute percentage error compared to the models directly forecasting total electricity demand. The described approach can also be used in forecasting techniques other than artificial neural networks.