Short-Term Forecasting of District Heating Demand

Focus of the paper is statistical data pre-processing before it applies for prediction the thermal load in district heating networks, focusing on day-ahead hourly planning. Such a planning is highly important for cogeneration plants participating in electricity wholesale markets. Article considers the possibility of correcting detected inconsistencies into district heating statistical data using forecasted values of the heat demand. The case study is based on the examples of heat supply of a large city, gas fired cogeneration power plants and real world data. The cost of errors in the prediction of heat consumption is estimated.