Scholarlink

<p>Load Frequency Management (LFM) is critical for ensuring the stability and dependability of multi-area hybrid power systems. As power demand and generation fluctuate, balancing them across multiple areas to maintain stable frequency levels becomes a significant challenge. This study presents a novel approach to overcome the challenges associated with LFM in multi-area hybrid power systems. The proposed approach utilizes Termite Life Cycle Optimizer (TLCO) to produce a set of control signals for the controller, and Hamiltonian Deep Neural Network (HDNN) to forecast the controller’s optimal gain factor, collectively referred to as the TLCO-HDNN approach. The study focuses on leveraging hybrid intelligent strategies to minimize load frequency deviations and enhance dynamic response in multi-area renewable-integrated power systems. The proposed strategy is simulated using MATLAB and benchmarked against existing approaches including Deep Neural Networks (DNN), Process Parameters Optimization (PPO), and Particle Swarm Optimization (PSO). The proposed strategy demonstrates improved performance in managing frequency deviations across multiple areas, achieving a minimal error of 0.03% and peak overshoot of 0.01% compared to the existing techniques. Also, the findings indicate the efficiency of the proposed technique with a reduced settling time of 3.8&#xa0;s, improved dynamic responses under various load conditions, and lower frequency disturbances. In addition, the study recommends that grid operators and policymakers adopt intelligent frequency control strategies supported by hybrid optimization and deep learning models to improve grid resilience and stability under high renewable energy integration.</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

Integrating TLCO-HDNN approach with FOTPID control for load frequency management in multi-area hybrid power systems featuring renewable energy

  • 期刊论文

  • 发表日期：

    2025年8月31日

查看全文
  • Vijayalaxmi M.,
  • Rathinavel Subramanian N

摘要

Load Frequency Management (LFM) is critical for ensuring the stability and dependability of multi-area hybrid power systems. As power demand and generation fluctuate, balancing them across multiple areas to maintain stable frequency levels becomes a significant challenge. This study presents a novel approach to overcome the challenges associated with LFM in multi-area hybrid power systems. The proposed approach utilizes Termite Life Cycle Optimizer (TLCO) to produce a set of control signals for the controller, and Hamiltonian Deep Neural Network (HDNN) to forecast the controller’s optimal gain factor, collectively referred to as the TLCO-HDNN approach. The study focuses on leveraging hybrid intelligent strategies to minimize load frequency deviations and enhance dynamic response in multi-area renewable-integrated power systems. The proposed strategy is simulated using MATLAB and benchmarked against existing approaches including Deep Neural Networks (DNN), Process Parameters Optimization (PPO), and Particle Swarm Optimization (PSO). The proposed strategy demonstrates improved performance in managing frequency deviations across multiple areas, achieving a minimal error of 0.03% and peak overshoot of 0.01% compared to the existing techniques. Also, the findings indicate the efficiency of the proposed technique with a reduced settling time of 3.8 s, improved dynamic responses under various load conditions, and lower frequency disturbances. In addition, the study recommends that grid operators and policymakers adopt intelligent frequency control strategies supported by hybrid optimization and deep learning models to improve grid resilience and stability under high renewable energy integration.