Logo image
AI-based Adaptive Overcurrent Protection for Load-side Relays in Offshore DC Microgrids
Conference paper   Peer reviewed

AI-based Adaptive Overcurrent Protection for Load-side Relays in Offshore DC Microgrids

Avy Sheina, Ramon Zamora, Aman Maung Than Oo and Kosala Gunawardane
Proceedings of the 2025 IEEE PES 17th Asia-Pacific Power and Energy Engineering Conference (APPEEC), pp.1-6
Asia-Pacific Power and Energy Engineering Conference (APPEEC), 17th (Auckland, New Zealand, 02-Dec-2025–05-Dec-2025)
Institute of Electrical and Electronics Engineers
2026

Abstract

adaptive protection ANFIS overcurrent protection DC microgrids Offshore power system
The integration of renewable energy sources (RES) such as solar, wind, wave, and tidal power through microgrids is gaining interest globally, particularly for offshore applications. In these circumstances, DC microgrids are preferred over AC counterparts due to their suitability for islanded operation and their ability to simplify the integration of RES and energy storage systems (ESS). DC systems also mitigate common AC challenges such as frequency deviations, harmonic distortion, and voltage imbalance. Despite these advantages, DC microgrids face significant protection challenges, primarily due to the absence of natural zero-crossing, rapid fault current rise, and limited availability of standardized DC protection devices and schemes. To address the need for more responsive protection mechanisms that can accommodate varying RES, ESS, and load conditions, this paper proposes an adaptive overcurrent protection approach based on artificial intelligence (AI). The adaptive scheme employs an Adaptive Neuro-Fuzzy Inference System (ANFIS), trained on data from diverse operating scenarios including normal loading, fault events, and renewable intermittency. The model enables real-time adjustment of relay settings on the load side, ensuring accurate fault detection and improving system reliability. A DC microgrid protection model is developed in MATLAB/Simulink, in which current measurements obtained under different operating conditions are used for training and validation. The ANFIS-based method achieved 99.41% prediction accuracy over 1.35 million samples, and the Opal-RT real-time simulation confirmed its effectiveness with circuit breaker tripping times of 130 milliseconds for overcurrent faults and 20 milliseconds for short-circuit faults.

Details

Metrics

1 Record Views
Logo image