Scholarlink

<p>Conventional methods like Automatic Voltage Regulators (AVRs) and Power System Stabilizers (PSSs) fall short of effectively damping Low-Frequency Oscillations (LFOs), necessitating the exploration of advanced solutions. This paper addresses the challenge of power system stability by utilizing advanced soft computing techniques in Supplementary Damping Control (SDC) for Static Synchronous Compensator (STATCOM) to mitigate low frequency oscillations in multi-machine power system. The proposed Type-II NeuroFuzzy Wavelet Controls (NFWC) employ Gaussian Type-II membership functions, with uncertainties in mean and standard deviation parameters, in the antecedent part and Wavelet Neural Networks (WNNs) in the consequent part. A multi-machine power system with STATCOM is considered for the performance evaluation of the proposed controllers. The proposed Type-II NFWC-1 and Type-II NFWC-2 outperform Adaptive NeuroFuzzy TSK Control (ANFTSKC) in terms of convergence speed and damping performance. Type-II NFWC-2 exhibits and maintains its superior performance over Type-II NFWC-1 and ANFTSK, highlighting the effectiveness of incorporating additional uncertainty in both mean and standard deviation parameters.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Stability Enhancement of Grid Connected Power System Using Type-II Neurofuzzy Wavelet Control

  • 期刊论文

  • 发表日期：

    2025年5月13日

查看全文
  • Saad Dilshad,
  • Rabiah Badar,
  • Aun Haider,
  • Naeem Abas

摘要

Conventional methods like Automatic Voltage Regulators (AVRs) and Power System Stabilizers (PSSs) fall short of effectively damping Low-Frequency Oscillations (LFOs), necessitating the exploration of advanced solutions. This paper addresses the challenge of power system stability by utilizing advanced soft computing techniques in Supplementary Damping Control (SDC) for Static Synchronous Compensator (STATCOM) to mitigate low frequency oscillations in multi-machine power system. The proposed Type-II NeuroFuzzy Wavelet Controls (NFWC) employ Gaussian Type-II membership functions, with uncertainties in mean and standard deviation parameters, in the antecedent part and Wavelet Neural Networks (WNNs) in the consequent part. A multi-machine power system with STATCOM is considered for the performance evaluation of the proposed controllers. The proposed Type-II NFWC-1 and Type-II NFWC-2 outperform Adaptive NeuroFuzzy TSK Control (ANFTSKC) in terms of convergence speed and damping performance. Type-II NFWC-2 exhibits and maintains its superior performance over Type-II NFWC-1 and ANFTSK, highlighting the effectiveness of incorporating additional uncertainty in both mean and standard deviation parameters.