Available transfer capability calculations using neural networks in deregulated power

This paper presents a backpropagation feed forward algorithm methodology for the problem of available power transfer capability calculations. The computation of ATC is very important to the transmission system security and market forecasting in a deregulated power systems. Based on the AC power distribution factor formulation of the problem, the inputs for the neural network are generator status, line status and load status and the output is the available transfer capability. The backpropagation algorithm is used to train the neural network and tested for the transaction between area-2 and area-1. A case study of IEEE 30-bus system is presented demonstrating the feasibility of this approach and the results are compared.