Optimal Scheduling of Railway Power Supply Systems Integrated With Microgrids: A CCAH-RL Approach
Bibliographic record
Abstract
Globally, the pace of railway system electrification and decarbonization is accelerating to support the worldwide sustainability goals for energy and transportation. Increased electricity demand from transport decarbonization, notably within the railway sector, places additional stress on already constrained power grids. Utilizing local renewable generation and energy storage systems to meet this increased demand has emerged as a crucial strategy to enhance the flexibility and resilience of railway power supply systems. This paper proposes to deploy railway microgrids at weak nodes of the existing co-phase traction power supply lines, maximizing the use of current infrastructure (including traction networks and local power grids) to address energy gaps while mitigating exacerbated three-phase voltage imbalance issues caused by increasing electricity demands. A computational cost-aware heuristic reinforcement learning method is developed first for optimal energy scheduling. Then, two agents operating with the proposed algorithm are employed to coordinate energy management between railway microgrids and co-phased feeder stations. Case studies, including a test scenario based on real operating conditions, show that the proposed solution not only accommodates rising electricity demand but also reduces daily operating costs by 15.1% in representative test scenarios, and 19.8% on average under real-world operation conditions. The proposed reinforcement learning algorithm is shown to save up to 81% computation time compared to other conventional approaches. It further substantially strengthens the ability of co-phase traction power supply systems to manage three-phase voltage imbalance, offering a cost-effective mitigation strategy.
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) | 0.000 | 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".