The main directions of the energy strategy of railway transport are to improve the management structure of the railway energy complex, reduce the cost of electric energy and reduce the cost of its acquisition. The initial information for planning optimal operating modes in the management of the energy complex is provided by the forecast of electricity consumption. According to the rules of functioning of retail markets, consumers are required to accurately plan the volume of electricity consumption. If the power consumption deviates by more than 5% of the planned volume, the company incurs additional costs. To make an accurate forecast, it is necessary to analyze the source data – the archive of electricity consumption. At the initial stage of data analysis, the problem of omissions is revealed. If there are gaps in the data, the process of forecasting electricity consumption can be difficult, and sometimes impossible. The most rational solution is to fill in the gaps using modern methods of information processing. This will allow you to clearly present the data structure, calculate the necessary values and interpret the results of the analysis.

Keywords: power consumption, time series, data gaps, recovery of missing values, forecasting of power consumption, train traction, railway transport, neural networks

Market relationships between energy producers and consumers leads to increased obligations for all market players. The problem of efficient distribution of electricity purchased on a wholesale market becomes relevant in the context of development of competition in the retail market. The prognostics of energy consumptions becomes a valuable criterion for planning the further consumers’ demands, reducing generation and transportation costs. In case of inaccurate forecasts, the company will be forced to buy or sell electrical energy at unfavorable price. The usage of multi-factor mathematical models in the prognostics makes it possible to make a highly accurate power consumption forecasting. The author proposes an interpretation of the complex energy consumption system as a multiple linear regression equation that takes the relationship between factors into consideration and allows to single out the influence of any factor on the power output.

Keywords: power consumption, train traction, power consumption forecasting, multiple regression, correlation coefficient, pair correlation, mathematical model, residual analysis, determination coefficient, Fisher's test