<![CDATA[The growing reliance on renewable energy sources (RES), alongside the surge in electricity consumption, has intensified the challenges associated with congestion management in power transmission lines. This article investigates the use of an advanced interline power flow controller (AIPFC) combined with artificial intelligence (AI) and machine learning (ML) methods to tackle congestion management challenges. The aim is to establish a dependable and effective power system, all while reducing the costs associated with congestion management. Algorithms in AI and ML are utilized to create models aimed at predicting and managing congestion, whereas optimization techniques are applied to identify the most effective operation of AIPFC and strategies for alleviating congestion. The IEEE 30-bus system is utilized as a test case to assess the proposed methodology. A comparative analysis is performed, evaluating the effectiveness of the AI/ML-based approach in relation to traditional congestion management techniques. The findings demonstrate that the incorporation of AIPFC alongside AI/ML methodologies markedly alleviates congestion within the power transmission lines of the IEEE 30-bus system. The proposed combination of model predictive control (MPC) and AIPFC (MPC-AIPFC), integrated with chaotic fuzzy particle swarm optimization (CFPSO), achieves the lowest fuel cost of $798.81/h, the minimum total power loss of 0.0855 pu, and demonstrates congestion mitigation under overload conditions. These results underscore the approach’s significant advancements in reducing cost, optimizing power flow, and relieving congestion compared to traditional methods.]]>
Copyrights © 2025
