Enhancing Fault Detection and Classification in MMC-HVDC Systems: Integrating Harris Hawks Optimization Algorithm with Machine Learning Methods

Accurate fault detection in high-voltage direct current (HVDC) transmission lines plays a pivotal role in enhancing operational efciency, reducing costs, and ensuring grid reliability. Tis research aims to develop a cost-efective and high-performance fault detection solution for HVDC systems. Te primary objective is to accurately identify and localize faults within the power system. In pursuit of this goal, the paper presents a comparative analysis of current and voltage characteristics between the rectifer and inverter sides of the HVDC transmission system and their associated alternating current (AC) counterparts under various fault conditions. Voltage and current features are extracted and optimized using a metaheuristic approach, specifcally Harris Hawk’s optimization method. Leveraging machine learning (ML) and artifcial neural networks (ANN), this technique demonstrates its efectiveness in generating a fault locator with exceptional accuracy. With a substantial volume of data employed for learning and training, the Harris Hawks optimization method exhibits faster convergence compared to other metaheuristic methods examined in this study. Te research fndings are applied to simulate diverse fault types and unknown fault locations at multiple system points. Evaluating the fault detection system’s efectiveness, quantifed through metrics such as specifcity, accuracy, F1 score, and sensitivity, yields remarkable results, with percentages of 99.01%, 98.69%, 98.64%, and 98.67%, respectively. Tis research underscores the critical role of accurate fault detection in HVDC systems, ofering valuable insights into optimizing grid performance and reliability.