ANN-based block frequency prediction in ABT regime and optimal availability declaration

In the post availability based tariff (ABT) scenario in India, the introduction of frequency linked pricing mechanism has made the prediction of system mean block frequency a key component of the daily operation and planning activities of an electric utility. It helps the utilities and system operators to take decisions for better scheduling and operation of the power system. An artificial neural network (ANN) based model to predict short term system mean block frequency (hour ahead and day ahead) in the ABT regime is developed in this paper. The data obtained from NRLDC (Northern Regional Load Dispatch Center), BTPS (Badarpur Thermal Power Station) and IMD (India Meteorological Department) for the period from March 2005 to April 2006 have been used for training, validating and testing the ANN models. The results have been analyzed using error indices. The application of predicted day ahead system mean block frequency for optimal declaration of available capacity of gas turbine stations by a genco has been presented. Expected net savings in money terms has also been computed.