An on-line determination of the ready reserve power

The paper presents usage of an artificial neural network (ANN) for the on-line determination of the ready reserve (RR) required for compensation of power deficit in power systems. The power deficit usually results after generator outage or failure of the other means of ensuring the operational reserve. RR consists of rapid start-up generating units such as gas turbines and hydro plants. Due to the stochastic nature of the power system operation, the amount of ready reserve is essential for balancing the power system operating states in perturbed conditions. For that purpose, an ANN using back-propagation learning rule could yield the amount of ready reserve. Prompt assessment of the appropriate amount of RR minimizes the potential reduction of quality of electrical energy delivered to customers and, consequently, maintains a high reliability of the power system as a whole.