Abstract
This paper presents an adaptive protection strategy for multi-microgrid (MMG) systems with inverter-based resources (IBRs) in medium voltage (MV) networks, using the IEEE 33-bus test system. The approach combines overcurrent (OC) and undervoltage (UV) protections through an offline-optimized, clustering-based scheme and real-time selection of setting groups. A metaheuristic algorithm determines optimal relay settings for representative scenarios, ensuring responsive and coordinated protection. Hardware-in-the-loop validation on OPAL-RT confirms the method's effectiveness across varying loads, DER outputs, and fault conditions. Results demonstrate reliable fault isolation, smooth mode transitions, and uninterrupted supply to healthy segments. Identified limitations in high-impedance fault handling suggest future improvements.

Abstract
The increasing penetration of inverter-based resources (IBR) in medium voltage (MV) networks presents significant challenges for traditional overcurrent (OC) protection systems, particularly in ensuring selectivity, reliability, and fault isolation. This paper presents an adaptive protection system (APS) that dynamically adjusts protection settings based on real-time network conditions, addressing the challenges posed by distributed energy resources (DER). The methodology builds on ongoing research and development efforts, combining an offline phase, where operational scenarios are simulated using historical data, clustered with fuzzy c-means (FCM), and optimized with evolutionary particle swarm optimization (EPSO), and an online phase. To overcome the static nature of conventional schemes, a machine learning (ML)-based classifier is integrated into the APS, enabling real-time adaptation of protection settings. In the online phase, a centralized substation protection controller (CPC) leverages real-time measurements, communicated via IEC 61850 standard protocols, to classify network conditions using a support vector machine (SVM) classifier and activate the appropriate protection settings. The proposed APS has been validated on a Hardware-in-the-Loop (HIL) platform, demonstrating significant improvements in fault detection times, selectivity, and reliability compared to traditional OC protection systems. As part of a continued effort to refine and expand the system's capabilities, this work highlights the potential of integrating artificial intelligence (AI) and realtime/online decision-making to enhance the adaptability and robustness of MV network protection in scenarios with high DER penetration.

Abstract
Modern distribution networks increasingly incorporate intelligent automation schemes to enhance resilience and reduce service interruptions following faults. To support these strategies, this paper investigates the use of machine learning models for fault location, aiming to quickly identify the faulted area and support safe service restoration of non-faulted areas. A comparative study is conducted using three supervised learning methods: Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB), applied to fault location in a distribution test system adapted to include Distributed Energy Resources (DER). Using steady-state current measurements generated from probabilistic fault scenarios based on historical data, each model is evaluated in terms of classification accuracy and computational feasibility. Results indicate that the models demonstrated high classification accuracy and efficient execution time, confirming the viability of machine learning (ML)-based approaches as effective decision-support tools for intelligent fault isolation and service restoration.

Abstract
The integration of Distributed Energy Resources (DER) imposes challenges to the operation of distribution networks. This paper conducts a systematic assessment of the impact of DER on distribution network overcurrent protection, considering the behavior of Inverter Based Resources (IBR) during faults in the coordination of medium voltage (MV) feeders' overcurrent protection. Through a detailed analysis of various scenarios, we propose adaptive protection solutions that enhance the reliability and resilience of distribution networks in the face of growing renewable energy integration. Results highlight the advantages of using adaptive protection over traditional methods and topology changes, and delve into current protection strategies, identifying limitations and proposing mitigation strategies. © The Institution of Engineering & Technology 2024.

Abstract
The integration of inverter-based distributed generation challenges the implementation of an reliable protection This work proposes an adaptive protection method for coordinating protection systems using directional overcurrent relays, where the settings depend on the distribution network operating conditions. The coordination problem is addressed through a specialized genetic algorithm, aiming to minimize the total operating times of relays with time-delayed operation. The pickup current is also optimized. Coordination diagrams from diverse fault scenarios illustrate the method's adaptability to different operational conditions, emphasizing the importance of employing multiple setting groups for optimal protection system performance. The proposed technique provides high-quality solutions, enhancing reliability compared to traditional protection schemes.