Multi-agent systems in networked microgrids: Reinforcement learning and strategic pricing mechanisms
Bibliographic record
Abstract
This study presents a novel, multi-layered approach for optimizing power transactions in networked microgrids using a multi-agent system framework. It incorporates peer-to-peer trading within microgrid clusters and a market based mechanism for inter-microgrid cluster transactions. To facilitate trading efficiency and market coordination, microgrids are first grouped into clusters based on similar load profiles and generation characteristics, enabling efficient intra-microgrid cluster energy balancing before engaging in inter-microgrid cluster trading. Within each microgrid cluster, microgrids operate autonomously, using local optimization to assess power surpluses and shortages, followed by multi-agent reinforcement learning to dynamically determine bid/ask prices. The proposed framework integrates a two-tiered trading mechanism. First, intra-microgrid cluster trading is facilitated through a proportional bargaining pricing model, ensuring fair power distribution among microgrids within the same microgrid cluster. Then, inter-microgrid cluster trading is optimized using a system marginal pricing mechanism, allowing microgrid clusters to efficiently sell surplus and buy shortage while minimizing grid dependency. Simulations using real-world data demonstrate substantial cost reductions and improved market efficiency. The proposed approach achieves a reduction of 43.9% in the annual surplus energy sold to the grid which reduces reliance on the utility grid by 7.1%. Additionally, annual electricity purchase costs from the grid and the cost of selling electricity to the grid are decreased by 7.5% and 44.6%, respectively. These improvements contribute to greater energy self-sufficiency, lower transaction costs, and enhanced economic fairness among microgrids. This framework provides a scalable, effective, and market-driven solution for power trading in networked microgrids by integrating microgrid clustering, local optimization, dynamic bid/ask price learning, and decentralized trading mechanisms. This improves operational resilience and economic viability of future distributed power markets.
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 | 0.000 |
| 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".