The increase in power demand and limited power sources has caused the system to operate at its maximum capacity. Therefore, the ability to determine voltage stability before voltage collapse has received a great attention due to the complexity of power system. In this paper there is a prediction of Power Transfer Stability Index (PTSI) based on Radial Basis Function Neural Network (RBFNN) for the Iraqi Super Grid network, 400 kV. Learning data has been obtained for various settings of load variables using load flow and conventional PTSI method. The input data was performed by using a 400 samples test with different bus voltage (Vb), Bus active and reactive power (Pb, Qb), bus load angle (δb) and PTSIb. The three RBFNN models have 2, 3 and 4 inputs representing the (Vb, Pb, Qband δb) respectively, the best hidden layer have thirty six nodes and the output layer has node representing PTSIb have been used to assess bus security. The proposed method has been tested on a practical system and compared with Back-propagation neural network. In Simulation results show that the proposed method is more suitable for on-line bus voltage stability assessment in term of automatically detection of critical bus when additional real or reactive loads are added or loss of transmission line.
Key words: Voltage stability, radial basis function neural network, voltage collapse.
Copyright © 2023 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0