A Decentralized Multi-Agent Reinforcement Learning for Fault Detection and Isolation in Distribution Networks
Bibliographic record
Abstract
The increasing integration of renewable energy sources (RES) in modern smart grids introduces challenges in fault detection, isolation, and voltage regulation. Conventional centralized control strategies often face limitations such as communication delays, scalability concerns, and vulnerability to system-wide failures. This paper proposes a fully decentralized multi-agent reinforcement learning (MARL) framework based on the proximal policy optimization (PPO) algorithm to enhance distribution system resilience. The proposed framework develops autonomous MARL agents that independently learn localized control policies for real-time fault detection, isolation, and voltage stabilization. To improve performance, adaptive reward shaping is employed to enhance fault detection accuracy, reduce false positives, and accelerate system recovery. Each PPO agent is trained with customized observation spaces, action strategies, and power flow constraints to ensure robust decision-making under dynamic grid conditions. Simulations on the IEEE 33-bus system demonstrate the proposed framework’s superior fault detection accuracy, faster isolation response, and improved voltage stability compared to conventional reinforcement learning and deep learning models, effectively enhancing grid resilience.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".