A Neural Network Based Method For Fast ATC Estimation in Electricity Markets

In a competitive electricity market, available transfer capability (ATC) information is required by market participants as well as the system operator (SO) for secure operation of the power system. The on-line updating of ATC information requires a fast and accurate method for its determination. This paper proposes a multi-layer perceptron (MLP) based neural network model for ATC estimation in a competitive electricity market having bilateral as well as multilateral transactions. Relevant input features have been obtained by using a random forest (RF) technique. Levenberg-Marquardt algorithm has been used for training of neural network. The effectiveness of the proposed method has been tested on 39-bus New England System and a practical 246-bus Indian system.