Forecasting power consumption based on source information

Abstract

The transition to market relations between power consumers and power supply systems leads to stricter requirements to all market participants. Therefore, a power sales company has to face a severe competition in the power retail market and to solve a problem of an efficient distribution of power acquired in the wholesale market. A forecast value of power consumption is a reference indicator for further planning the rated power values required for response to power consumer demand and minimizing the power production and transportation cost. An inaccurate forecast results in a shortage or an excess of purchased power and makes the company buy or sell electricity at a disadvantageous price. The problem of forecasting power consumption can be solved based on data supplied by a power sales company. For this purpose, a forecast of power consumption with a minimum error takes into account meteorological factors, too. Forecasts with different databases are considered. The studies have revealed a clear link between meteorological factors and power consumption, which is expressed in the correlation coefficient. The most effective forecasting model is that with a great number of different input databases.