This article presents a different approach to power consumption forecasting problem. This forecasting can help power supply companies to program their production or purchases. Based on this forecasting the companies take part in auctions that determine the price of the MWh in the electricity market and at the end of the day, the price for the end consumer. So far, the problem of forecasting power supply time series has mainly been dealt with the use of classical time series algorithms or VAR models. In this paper, we use a method from the insurance sector to forecast Greek power consumption hourly values. The innovation in this method is that it allows converting the forecasting of a system of time series (high dimensional time series) into forecasting a single time series and propagating the results back to each time series. It leaves the forecasting algorithm choice to the researcher, making it very flexible and removing the necessity of choosing complex algorithms. We demonstrate the forecasting of the results of this method by applying the ARIMA algorithm.