Microgrid Formation-based Service Restoration Using Deep Reinforcement Learning and Optimal Switch Placement in Distribution Networks
Bibliographic record
Abstract
A power distribution network that demonstrates resilience has the ability to minimize the duration and severity of power outages, ensure uninterrupted service delivery, and enhance overall reliability. Resilience in this context refers to the network's capacity to withstand and quickly recover from disruptive events, such as equipment failures, natural disasters, or cyber attacks. By effectively mitigating the effects of such incidents, a resilient power distribution network can contribute to enhanced operational performance, customer satisfaction, and economic productivity. The implementation of microgrids as a response to power outages constitutes a viable approach for enhancing the resilience of the system. \nIn this work, a novel method for service restoration based on dynamic microgrid formation and deep reinforcement learning is proposed. To this end, microgrid formation-based service restoration is formulated as a Markov decision process. Then, by utilizing the node cell and route model concept, every distributed generation unit equipped with the black-start capability traverses the power system, thereby restoring power to the lines and nodes it visits. The deep Q-network is employed as a means to achieve optimal policy control, which guides agents in the selection of node cells that result in maximum load pick-up while adhering to operational constraints. \nIn the next step, a solution has been proposed for the switch placement problem in distribution networks, which results in a substantial improvement in service restoration. Accordingly, an effective algorithm, utilizing binary particle swarm optimization, is employed to optimize the placement of switches in distribution networks. The input data necessary for the proposed algorithm comprises information related to the power system topology and load point data. The fitness of the solution is assessed by minimizing the unsupplied loads and the number of switches placed in distribution networks. \nThe proposed methods are validated using a large-scale unbalanced distribution system consisting of 404 nodes, which is operated by Saskatoon Light and Power, a local utility in Saskatoon, Canada. Additionally, a balanced IEEE 33-node test system is also utilized for validation purposes.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.007 | 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 teacher head, 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".