Enhancing Margin and Sensitivity Approaches for 330kV Transmission Network Security using a Wavelet-based Extreme Learning Method
- Post by: airjournals
- July 18, 2024
- Comments off
Fidelis Ikechukwu Onah1, Martin Ogharandukun2, Joe Essien3, Ngang Bassey Ngang4
1 4Department of Electrical and Electronic Engineering, Veritas University, Abuja
2Department of Pure and Applied Physics, Veritas University, FCT, Abuja
3Department of Computer and Information Technology, Veritas University, Abuja
Citations – APA
| Onah, F. I., Ogharandukun, M., Essien, J, & Ngang, N. B. (2024). Enhancing Margin and Sensitivity Approaches for 330kV Transmission Network Security using a Wavelet-based Extreme Learning Method. International Journal of Information Sciences and Engineering, 8(1), 1-14. DOI: https://doi.org/10.5281/zenodo.12770002 |
ABSTRACT
The security of high-voltage transmission networks is crucial for the stability and reliability of power systems. This study presents an innovative approach that combines margin and sensitivity analysis with a wavelet-based extreme learning method (WELM) to enhance the security of 330kV transmission networks. Integrating wavelet transforms with extreme learning algorithms improves fault detection and system response. Extensive simulations and real-world data analysis show that this method significantly improves detection accuracy and computational efficiency compared to traditional methods. Persistent power failures in transmission networks are often due to low sensitivity and insufficient margin, with per-unit voltages not maintaining the required threshold of 0.95 to 1.05. To address these issues, this study introduces an improved margin and sensitivity method for 330kV transmission network security, utilizing a wavelet-based extreme learning technique. The methodology includes characterizing the transmission network, conducting load flow analysis to identify buses with low margins and sensitivities, developing a wavelet rule base, training an artificial neural network (ANN), creating an algorithm for implementation, and designing a SIMULINK model for validation. Results indicate that the conventional per-unit voltage of weak bus 1 was 0.930, below the stability threshold, leading to inconsistent power supply. Incorporating the wavelet-based technique increased the voltage to 1.023 per unit, achieving stability and ensuring a consistent power supply. The conventional power margin at weak bus 1 was 58.85MW, contributing to intermittent power supply, but increased to 64.73MW with the wavelet technique, representing a 9.99% improvement. Additionally, the conventional sensitivity of 0.000983, which caused network failures, improved to 0.001081, enhancing the stability and performance of the transmission network.
Keywords: Improving Margin; Sensitivity Approach; 330kV Transmission Network; Wavelet-Based Extreme Learning Method; Artificial Neural Network (ANN)