A Cost-Effective and Eco-Friendly Micro-Grid by Employing a Model-Free Multi-Agent Reinforcement Learning Strategy for Power Management
Bibliographic record
Abstract
This paper proposes the employment of reinforcement learning based strategies to tackle the complexities of micro-grid (MG) power management. The envisioned MG comprises combined cooling, heating, and power (CCHP) units, a wind turbine (WT), photovoltaic (PV), and a battery energy storage system (BESS). To accurately set the output of renewable resources and micro-turbine power generation for the upcoming day, a model-free reinforcement learning (MARL) approach is employed. This approach aims to minimize a multi-objective function that considers fuel consumption and$\text{CO}_{2}$emissions, ensuring the MG operates efficiently and environmentally friendly. The primary goal of the proposed method is to address the complex challenge of determining the optimal operational points within a sophisticated environment, a task that would be challenging for a single agent. The proposed strategy also suggests employing a meta-learning approach to fine-tune the discount factor (DF) in the Q-table function. It enhances the efficiency and robustness of the overall system compared to the fixed or grid-searched DF. Results indicate that the proposed MARL framework effectively manages the distribution of power generation among renewable resources and micro turbines in CCHP system aiming to optimize fuel cost and$\text{CO}_{2}$emission. Additionally, findings validate the BESS's reliable performance during both light and heavy load periods within the MG.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| 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".