In a competitive and deregulated power scenario, the utilities try to maintain their real electric power generation in balance with the load demand, which creates a need for the precise real time generation scheduling (GS). In this paper, the GS problem is solved to perform the unit commitment (UC) based on frequency prediction by using artificial neural network (ANN) with the objective to minimize the overall system cost of the state utility. The introduction of availability-based tariff (ABT) signifies the importance of frequency in GS. Under-prediction or over-prediction will result in an unnecessary commitment of generating units or buying power from central generating units at a higher cost. Therefore, an accurate frequency prediction is the first step toward optimal GS. The dependency of frequency on various parameters such as actual generation, load demand, wind power and power deficit has been considered in this paper. The proposed technique provides a reliable solution for the input parameter different from the one presented in the training data. The performance of the frequency predictor model has been evaluated based on the absolute percentage error (APE) and the mean absolute percentage error (MAPE). The proposed predicted frequency sensitive GS model is applied to the system of Indian state of Tamilnadu, which reduces the overall system cost of the state utility by keeping off the dearer units selected based on the predicted frequency.