Physics-Informed Closed-Loop Python–OpenDSS Co-Simulation for Fault Detection and Localization in Inverter-Dominated Microgrids
Abstract
Protection of inverter-dominated microgrids remains challenging due to limited fault currents, bidirectional power flows, and rapidly changing operating conditions. Although machine learning (ML) techniques have shown considerable promise for fault detection and localization, most existing studies rely on offline datasets that do not fully capture inverter control dynamics and evolving network interactions, often resulting in optimistic performance estimates. This paper proposes a physics-informed closed-loop Python–OpenDSS co-simulation framework that embeds ML-based diagnostic models within a bidirectional simulation environment. The framework enables systematic fault injection, synchronized measurement acquisition, automated feature extraction, and closed-loop diagnostic evaluation under both grid-connected and islanded operating modes. Its performance is evaluated using IEEE 5-, 13-, and 15-bus inverter-dominated microgrid (MG) test systems to investigate scalability and robustness under realistic operating conditions. Results reveal a measurable performance gap between offline evaluation and closed-loop validation, demonstrating that offline accuracy does not necessarily reflect deployable performance. Random Forest and CNN models maintain strong robustness as system complexity increases, whereas K-Means clustering degrades substantially. The proposed framework establishes a reproducible, physics-consistent methodology for benchmarking artificial intelligence (AI)-based…
Read the paper
Related studies
- Preliminary Toxicity Analysis of 3DCRT versus IMRT on the High Dose Arm of the RTOG 0126 Prostate Cancer Trial
- Adaptive Radiotherapy for Head and Neck Cancer: Initial Clinical Outcomes from a Prospective Trial
- American Association of Physicists in Medicine Task Group 263: Standardizing Nomenclatures in Radiation Oncology
- Motion Management Strategies and Technical Issues Associated with Stereotactic Body Radiotherapy of Thoracic and Upper Abdominal Tumors: A Review from NRG Oncology
- High-dose-rate interstitial brachytherapy as a monotherapy for localized prostate cancer: treatment description and preliminary results of a phase I/II clinical trial
- Highly efficient training, refinement, and validation of a knowledge-based plan quality control system for radiotherapy clinical trials
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.