Home / Current Issue / Paper 1706007
PSO-Symbolic Regression Based Voltage Stability Analysis for the Nigerian 330kv Transmission Network
Subject area: Science,Engineering and Technology · Area of research: Electrical and Electronic Engineering
Abstract
This review explores the analysis of the Nigerian 330kV transmission network profile using Particle Swarm Optimization (PSO). The primary purpose of this study is to evaluate the effectiveness of PSO in optimizing the performance and stability of the Nigerian power transmission network, addressing prevalent issues such as voltage instability and inefficient power distribution. The Nigerian 330kV transmission network faces significant challenges, including frequent voltage collapses and suboptimal power flow, leading to reliability and efficiency concerns. These problems are exacerbated by the network's non-linear dynamics and the increasing demand for electricity. Addressing these challenges requires advanced optimization techniques capable of providing robust solutions. The study employs an improved PSO approach to determine the optimal sizing and placement of shunt injection capacitor banks within the transmission network. By using PSO, the research aims to enhance the network's voltage stability and overall performance. The methodology involves detailed simulations of the Nigerian 330kV network, considering various load scenarios and generator configurations. Additionally, a Symbolic Regression (SR) model fitting technique is used to represent solution states and account for deviations from optimal capacitor bank MVARS across load buses. The results demonstrate that PSO optimization significantly improves the voltage profile of the transmission network, achieving an 8.4% enhancement. Furthermore, the SR model effectively represents the solution states with minimal error deviations, ensuring accurate and reliable performance assessments. The study highlights the potential of PSO and SR in addressing complex power system problems, and promoting the adoption of AI-based solutions in the energy sector. In conclusion, this review underscores the importance of advanced optimization techniques like PSO in improving the performance and stability of power transmission networks. The findings advocate for policies that support the integration of AI and machine learning approaches in power system analysis and optimization, paving the way for a more resilient and efficient energy infrastructure in Nigeria.
Keywords
Optimization, PSO, Symbolic Regression, Transmission Network, Voltage Stability
References
[1] Salomon, C. P., Lambert-Torres, G., Da Silva, L. E. B., Coutinho, M. P., & De Moraes, C. H. V. (2013). A Hybrid Particle Swarm Optimization Approach for Load-Flow Computation. International Journal of Innovative Computing, Information, and Control, 9(11), 4359-4372.
[2] Rilwan, U., Marvin, B. S., & Steve M. (2016). Analysis of the effect of Flexible Alternating Current Transmission System (FACTS) on the Nigerian 330kV Transmission Network Using ERACS and Matlab Simulink. European Journal of Engineering and Technology, 4(3), 2056-5860.
[3] Taylor, C. W. (1994). Voltage stability. Power system voltage stability, 27-32.
[4] Jaramillo, M., Carrion, D., & Munoz, J. (2022). A Deep Neural Network as a Strategy for Optimal Sizing and Location of Reactive Compensation Considering Power Consumption Uncertainties. Energies, 15 (24), 9367. DOI: 10.3390/en15249367
[5] Osegi, E. N., Wokoma, B. A., Ojuka, O., Bruce-Allison, S.A., & Chujor, C. C., (2022). A Swarm-Intelligent Optimization Technique for Voltage Collapse Mitigation. Journal of Engineering Studies and Research. 28(2022), No. 2 https://doi.org/10.29081/jesr.v28i2.004.
[6] Jagun, Z. O., Osegi, Okandeji. A. A., Olajide, M. B., Osegi, N. E., & Wokoma, B. A. (2020). Adaptive Hybrid PSO-RAO-Type for Predictive Economic Load Dispatch. Equity Journal of Science and Technology, 7 (1), 131-131.
[7] Bakare, G. A., Lawal, L. A., & Okereke, O. U. (2020). Reactive Power Voltage Control of Nigerian Grid System Based on Artificial Bee Colony Algorithm. ABUAD Journal of Engineering Research and Development (AJERD), 3 (2), 142-151.
[8] Sani, S. A., Bakare, G. A., Ya’u, S. H., Isa, A. I., & Musa, U. (2019). Optimal Capacitor Placement in Distribution Systems Using Improved Bacterial Foraging Algorithm. IEEE PES/IAS PowerAfrica (pp. 233-237). IEEE.
[9] Remha, S., Chettih, S., & Arif, S. (2018). A Novel Multi-Objective Bat Algorithm for Optimal Placement and Sizing of Distributed Generation in Radial Distributed Systems. Advances in Electrical and Electronic Engineering, 15(5), 736-746.
How to cite this paper
@article{1706007,
author = {Blue-Jack, K. Q., Ojuka, O. E., Bala, T. K., Wokoma, B. A.},
title = {PSO-Symbolic Regression Based Voltage Stability Analysis for the Nigerian 330kv Transmission Network},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {8},
number = {1},
pages = {124-131},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/17060071.pdf},
abstract = {This review explores the analysis of the Nigerian 330kV transmission network profile using Particle Swarm Optimization (PSO). The primary purpose of this study is to evaluate the effectiveness of PSO in optimizing the performance and stability of the Nigerian power transmission network, addressing prevalent issues such as voltage instability and inefficient power distribution. The Nigerian 330kV transmission network faces significant challenges, including frequent voltage collapses and suboptimal power flow, leading to reliability and efficiency concerns. These problems are exacerbated by the network's non-linear dynamics and the increasing demand for electricity. Addressing these challenges requires advanced optimization techniques capable of providing robust solutions. The study employs an improved PSO approach to determine the optimal sizing and placement of shunt injection capacitor banks within the transmission network. By using PSO, the research aims to enhance the network's voltage stability and overall performance. The methodology involves detailed simulations of the Nigerian 330kV network, considering various load scenarios and generator configurations. Additionally, a Symbolic Regression (SR) model fitting technique is used to represent solution states and account for deviations from optimal capacitor bank MVARS across load buses. The results demonstrate that PSO optimization significantly improves the voltage profile of the transmission network, achieving an 8.4% enhancement. Furthermore, the SR model effectively represents the solution states with minimal error deviations, ensuring accurate and reliable performance assessments. The study highlights the potential of PSO and SR in addressing complex power system problems, and promoting the adoption of AI-based solutions in the energy sector. In conclusion, this review underscores the importance of advanced optimization techniques like PSO in improving the performance and stability of power transmission networks. The findings advocate for policies that support the integration of AI and machine learning approaches in power system analysis and optimization, paving the way for a more resilient and efficient energy infrastructure in Nigeria.},
keywords = {Optimization, PSO, Symbolic Regression, Transmission Network, Voltage Stability},
month = {July},
}