Implementation of automatic system of forecasting in INTER RAO UES

The Energy-Forecast system allows to build forecasts of prices of electricity on the basis of historical data with use of optimal mathematical algorithms.

The Energy-Forecast system allows to build forecasts with different detailing (hourly - day weeks) on different cuts of the electricity market. On the basis of historical data the analysis and visualization of dynamics of time series is carried out. The received results remain in the report.

"One of strategic tasks of JSC INTER RAO UES is increase in profitability of trading transactions. System implementation of Energy-Forecast allowed us to optimize labor-intensive process of creation of forecasts", - the specialist of INTER RAO UES Grigory Pogorelov said.

Commenting on this project, the chief executive of StatSoft Russia Onishchenko Marina noted: "The electricity market demands from all participants of drawing up forecasts both on short-term, and for a long-term outlook today. So, the consumer of the electric power should have the forecast of hourly consumption for the week ahead. The seller is faced, on the other hand, by a problem of forecasting of the prices of the near-term outlook. It is also necessary to note that the price is not homogeneous across the territory of the Russian Federation and the countries of importers. Therefore we created the convenient automatic system allowing to build forecasts and to make corrections."

According to system developers, in Energy-Forecast automatic search of predictive models is performed: the ARPSS model and model of exponential smoothing and also average profiles of behavior of the price are used. A basis of Energy-Forecast is the STATISTICA system – a multifunction analysis system, visualization and forecasting.