The purpose of the publication is to use the methods of the similarity theory to control power consumption in industrial enterprises. On the basis of the fifth additional provision of the theory of similarity, it is proposed to apply the stochastic characteristics of the daily graphs of the electrical load of transformer substations. An approximate method for calculating the coefficient of similarity of both daily schedules of electrical load with each other and the selected daily schedule with the declared schedule on the "Daily market in advance and intraday market" has been developed. This method can be used when choosing the consumption of various energy resources.

No abstract

The purpose of the study in this paper is based on a detailed analysis of various mathematical and statistical methods for determining the similarity and uniformity of daily schedules of electrical load to form an approach to solving several important tasks. Namely, method of forming a static sample of complex load measurement data for the same included composition of single electrical receivers, selection of the optimum declared schedule of electric loading at purchase of the electric power on "Energorinka", as well as solving other similar tasks, all this in general requires effective clustering of graphs. Due to the fact that daily schedules of electrical load are divided into working days, pre-weekend, pre-holiday and weekend in this paper it is proposed to express the data of electric load graphs in Cartesian or polar coordinates. This allowed us to record the difference between the daily schedule of electrical load on normal working days from the day before. The efficiency of application of these methods of search of identical and similar daily schedules of electric loading was analyzed by allocation of several basic types of similarity of time series, similar: in time, on the form, on structure. It is shown that the calculation of the Euclidean distance allows to determine the uniformity of daily load graphs. And phase analysis is their similarity. The most acceptable method is to determine the correlation coefficient, which reveals the similarity and similarity of daily schedules of electrical load.

The problem of early and accurate forecasting of electricity consumption is acute for the unified energy system of Ukraine. With successful forecasting of consumption, which is based on many aspects, it is possible to buy electricity/losses in different market segments much more profitably, saving large amounts of money, which can then be directed to the development and modernization of electricity networks. This has always been an urgent issue, but today, when a large part of Ukraine's energy equipment has been destroyed by Russian missiles, it has become even more painful. The use of the method of artificial neural networks (ANN) for short-term forecasting of electricity consumption is considered. It was established that ANN can be used to make a forecast of electricity consumption a day ahead with an error of 4.86% compared to the actual amount of electricity consumption. Performing a comparison of forecast values with actual values allows us to talk about the adequacy of the selected forecasting model and its application in practice for the successful operation of energy supply companies in the electricity market.