Predictive Control and Production Process Forecasting Under Deterministic Chaos

Electricity consumption forecasting is an integral part of the workflow in most industries. At the same time, daily load schedules of the mining industry are characterized by deterministic chaotic fluctuations in the electricity consumption curve caused by the technology of the production process. The paper proposes two mathematical forecasting models, one of which is based on the recurrent method, and the second one is based on the vector method. At the same time, the structure of the models allows taking into account the individual features of the operating cycle of the production process, as well as identifying and smoothing the “noise” components of the rank parametric surface of this production process. The Singular Spectrum Analysis method was chosen as the algorithm for preprocessing and smoothing time series of electricity consumption. The method was applied for the first time for a multidimensional array of electricity consumption data. As a result, rank parametric surfaces were plotted, one of which is the initial surface, and the second one is the final surface.