Artificial Neural Network Based Transient Stability Assessment of the Benin Sub Regional 330kv Network

DOI

No Doi

Published In

Year 2026 · Volume 3 · Issue 2

Published Online

May-August 2026

Pages

33-37

Article Type

Original Article

Check for updates

This study investigates the application of Artificial Neural Networks (ANNs) for rapid and accurate prediction of Critical Clearing Time (CCT) in the Nigerian 330 kV Benin sub-regional transmission network. System data were obtained from the Transmission Company of Nigeria (TCN) and modeled using MATLAB/PSAT. The Extended Equal Area Criterion (EEAC) method was employed to compute target CCTs, while generation and load parameters were varied by ±10 % to produce diverse training scenarios. A feed-forward ANN was trained and validated using the Levenberg–Marquardt algorithm. The results demonstrated high predictive accuracy with R2 =0.999, mean squared error (MSE) = 0.0021, and mean absolute error (MAE) = 0.037 s. The ANN reduced computational time by over 90 % compared to traditional time-domain simulations. Graphical analyses confirmed that the ANN accurately predicts CCT values under different disturbance conditions, indicating its suitability for real-time transient stability assessment in large-scale grids