Scholarlink

<p>This paper proposes a novel adaptive distributed event-triggered consensus mechanism based on artificial neural networks to manage data exchange consistently within microgrid clusters. This new control algorithm reduces data congestion and simplifies the mathematical complexities associated with previous event-triggering strategies. The ANN model was trained on a comprehensive dataset comprising 1,048,000 simulation scenarios, demonstrating robustness across various datasets under diverse conditions. The primary goal of the proposed control strategy is to enhance the performance and reliability of the third level in the hierarchical control scheme by reducing the communication load and improving coordination within the microgrid (MG) cluster. Simulation results show that the proposed control scheme outperforms existing strategies, achieving 100% accuracy in triggering instances and enabling rapid current convergence to its nominal value alongside swift voltage restoration during simultaneous load changes and fault conditions. For this study, a cluster of four interconnected DC MGs was implemented in the MATLAB environment to assess the new control approach’s effectiveness. Additionally, OPAL-RT hardware validated the method's applicability in real-world scenarios.</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

Adaptive distributed ANN-based event-triggered consensus algorithm of a DC microgrid cluster

  • 期刊论文

  • 发表日期：

    2025年12月29日

查看全文
  • Zaid Hamid Abdulabbas Al-Tameemi,
  • Rasool Peykarporsan,
  • Tek Tjing Lie,
  • Ramon Zamora,
  • Frede Blaabjerg

摘要

This paper proposes a novel adaptive distributed event-triggered consensus mechanism based on artificial neural networks to manage data exchange consistently within microgrid clusters. This new control algorithm reduces data congestion and simplifies the mathematical complexities associated with previous event-triggering strategies. The ANN model was trained on a comprehensive dataset comprising 1,048,000 simulation scenarios, demonstrating robustness across various datasets under diverse conditions. The primary goal of the proposed control strategy is to enhance the performance and reliability of the third level in the hierarchical control scheme by reducing the communication load and improving coordination within the microgrid (MG) cluster. Simulation results show that the proposed control scheme outperforms existing strategies, achieving 100% accuracy in triggering instances and enabling rapid current convergence to its nominal value alongside swift voltage restoration during simultaneous load changes and fault conditions. For this study, a cluster of four interconnected DC MGs was implemented in the MATLAB environment to assess the new control approach’s effectiveness. Additionally, OPAL-RT hardware validated the method's applicability in real-world scenarios.