Digital Twin-Assisted Adaptive Federated Multi-Agent DRL with GenAI for Optimized Resource Allocation in IoV Networks
Bibliographic record
Abstract
In this study, we introduce a digital twin (DT)-assisted IoV framework that combines a semi-synchronous adaptive federated learning (AdFL) method with multi-agent deep reinforcement learning, enhanced by generative artificial intelligence (GenAI) techniques, specifically conditional variational autoencoders (CVAE). This framework optimizes partial task offloading across distributed mobile edge computing (MEC) servers, ensuring scalable and efficient decision-making in diverse vehicular networks. By continuously reflecting the real-time conditions of vehicles and roadside units (RSUs), the DT framework ensures precise resource distribution and adaptive task handling. To handle the complexity of dynamic environments, we develop a global model that includes transformer layers in the federated learning (FL) process, which captures long-range dependencies. A semi-synchronous aggregation mechanism is introduced to maintain a balance between timely updates and model quality. The adaptive federated multi-agent reinforcement learning (AF-MARL) algorithm enables decentralized, collaborative learning among vehicles and RSUs, optimizing overall cost and energy use, reducing delays, and improving task completion rates. Comprehensive simulations show the framework's effectiveness compared to existing methods, emphasizing its potential to revolutionize real-time decision-making in IoV networks.
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 | 0.002 | 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".