Predictive management of enterprise power consumption based on the SINGULAR SPECTRUM ANALYSIS method using recurrent forecasting

Modern energy strategies aimed at the development of energy industry presuppose a significant change in the structure of process of formation, transmission, consumption of electrical energy and increasing energy efficiency by introducing modern technologies at all stages. The growth of capacities of industrial enterprises in the conditions of wholesale market of electrical energy and capacity in the modern energy system determines the need for development technologies of predictive control of power consumption process of these enterprises. The introduction of such technologies at the control rooms of the operational management of enterprises will allow to reduce the number of human errors, the number of emergency stops of technological process, increase the reliability of power system mode, rationally manage the process of power consumption of enterprises. In this regard, forecasting the load demand and consumption is an important stage in the functioning and planning of modern power systems. An accurate, correctly compiled forecast is the key to effective management of energy consumption process and reliable operation of the enterprise. Forecasting errors lead to imbalanced supply-demand, which negatively affects operating costs, reliability and efficiency.