Radial Basis ANN-Based Static Load Flow Analysis in Iraqi National Super Grid (400 KV)

This paper presents the application of Artificial Neural Networks for Load-flow analysis of Iraqi National super grid (400 KV network) using radial basis neural network (RBNN) to handle the slow computational process of Error Backpropagation Neural Network (EBPNN). The proposed method is fast and has acceptable accuracy. Active and reactive powers of system buses excluding slack bus, as well as the magnitudes and phase angle of slack bus are chosen as inputs to the ANN. Phase angle and voltage magnitude of all buses excluding slack bus are chosen as the outputs. Training data are obtained by performed a load flow program using an iterative numerical method namely Decoupled load flow method (DLF), same input and output parameters of RBNN are feed to the EBPNN. Load flow analyses results achieve from two neural methods are compared with the result of DLF method to illustrate the accuracy of result and the results are compiled to form the training set. The proposed algorithm is applied and the numerical results are presented in this paper in order to demonstrate the effectiveness of this proposed algorithm in terms of accuracy and speed. It is concluded that the trained ANN can be utilized for both off-line and on-line simulation studies. The simulation programs implemented using 7.5-Matlab programming language to obtain the satisfactory results.