Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.09637 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918139435941888 |
|---|---|
| author | Rashwan, Ahmed Briggs, Keith Budd, Chris |
| author_facet | Rashwan, Ahmed Briggs, Keith Budd, Chris |
| contents | The drift-plus-penalty method is a Lyapunov optimisation technique commonly applied to network routing problems. It reduces the original stochastic planning task to a sequence of greedy optimizations, enabling the design of distributed routing algorithms which stabilize data queues while simultaneously optimizing a specified penalty function. While drift-plus-penalty methods have desirable asymptotic properties, they tend to incur higher network delay than alternative control methods, especially under light network load. In this work, we propose a learned variant of the drift-plus-penalty method that can preserve its theoretical guarantees, while being flexible enough to learn routing strategies directly from a model of the problem. Our approach introduces a novel mechanism for learning routing decisions and employs an optimal transport-based method for link scheduling. Applied to the joint task of transmit-power allocation and data routing, the method achieves consistent improvements over common baselines under a broad set of scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09637 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A neural drift-plus-penalty algorithm for network power allocation and routing Rashwan, Ahmed Briggs, Keith Budd, Chris Systems and Control The drift-plus-penalty method is a Lyapunov optimisation technique commonly applied to network routing problems. It reduces the original stochastic planning task to a sequence of greedy optimizations, enabling the design of distributed routing algorithms which stabilize data queues while simultaneously optimizing a specified penalty function. While drift-plus-penalty methods have desirable asymptotic properties, they tend to incur higher network delay than alternative control methods, especially under light network load. In this work, we propose a learned variant of the drift-plus-penalty method that can preserve its theoretical guarantees, while being flexible enough to learn routing strategies directly from a model of the problem. Our approach introduces a novel mechanism for learning routing decisions and employs an optimal transport-based method for link scheduling. Applied to the joint task of transmit-power allocation and data routing, the method achieves consistent improvements over common baselines under a broad set of scenarios. |
| title | A neural drift-plus-penalty algorithm for network power allocation and routing |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2509.09637 |