Pay Attention to Network: Reliability-Aware Spatial-Temporal-Frequential Scheduling for TSN-WiFi Networks
Bibliographic record
Abstract
Time-Sensitive Networking (TSN) is a pivotal technology in providing deterministic and reliable communications in the wired domain. Complementarily, Wi-Fi Multi-link Operation (MLO) extends the TSN capabilities over the wireless domain to further increase the throughput and reliability for wired-wireless-integrated scenarios such as smart factories in industrial automation. To incorporate TSN and Wi-Fi MLO seamlessly, cross-domain flow scheduling is of vital importance in reliable control message transmission. Existing approaches leverage Deep Reinforcement Learning (DRL) to adapt to the dynamic wireless channel quality. However, the traditional multilayer perception (MLP)-based DRL model fails to integrate the input features of all the flows, resulting in severe underfitting issues and scheduling ineffectiveness. In this paper, we observe that the mutual dependencies among flows over the network resources are analogical to the contextual dependencies of tokens over the lexical sequence. Leveraging this insight, we exploit the self-attention mechanism in Natural Language Processing (NLP) to learn the network-wise dependencies among different flows. Theoretically, to provide an analytical guide to TSN-WiFi flow scheduling, we present a global scheduling abstraction to describe the key resource constraints of the cross-domain flow scheduling problem. Following that, we propose the load-aware TSN scheduling algorithm and the attention-based DRL scheduling algorithm to allocate spatial-temporal-frequencial resources for flows adhering to the above constraints. Experiments in various settings validate the effectiveness of the proposed method, which enhances the reliability by 12.09% compared with the state-of-the-art method.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 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".