Multi-Agent Distributed V2G Scheduling Optimization via Double Deep Q-Networks
Bibliographic record
Abstract
Under the “Dual Carbon” strategy, the largescale adoption of electric vehicles (EVs) presents both opportunities for green transportation and challenges for power grid load management. This paper proposes a distributed multiagent reinforcement learning scheduling method based on a double deep Q-network architecture (DQ-MARLS) to address multi-objective charging coordination in vehicle-grid interaction scenarios. Each charging pile is modeled as an independent agent with local state perception and deep policy learning. The state space integrates queuing status, electricity price, and grid load, while the action space is dynamically generated based on user availability. An$\varepsilon$-greedy strategy and double Q-learning mechanism are adopted to improve decision robustness and mitigate$Q$-value overestimation. A multi-objective reward function that considers user satisfaction, operator profit, and grid performance guides the agents toward coordinated and optimal scheduling. To support strategy training and performance evaluation, this paper constructs a simulation platform with approximately$\mathbf{1, 0 0 0}$virtual electric vehicle users dynamically interacting in a multi-region, multi-type charging station, and multi-time period environment to generate structured data. The experimental results show that the proposed method exhibits superior control performance and scalability compared to traditional heuristic and disordered scheduling strategies in terms of improving grid operation stability and reducing peak loads.
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) | 0.001 | 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) | 0.002 | 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".