A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914368752451584 |
|---|---|
| author | Aygün, Ozan Vitale, Vincenzo Norman Tulino, Antonia M. Feng, Hao Erkip, Elza Llorca, Jaime |
| author_facet | Aygün, Ozan Vitale, Vincenzo Norman Tulino, Antonia M. Feng, Hao Erkip, Elza Llorca, Jaime |
| contents | Next-generation networks aim to provide performance guarantees to real-time interactive services that require timely and cost-efficient packet delivery. In this context, the goal is to reliably deliver packets with strict deadlines imposed by the application while minimizing overall resource allocation cost. A large body of work has leveraged stochastic optimization techniques to design efficient dynamic routing and scheduling solutions under average delay constraints; however, these methods fall short when faced with strict per-packet delay requirements. We formulate the minimum-cost delay-constrained network control problem as a constrained Markov decision process and utilize constrained deep reinforcement learning (CDRL) techniques to effectively minimize total resource allocation cost while maintaining timely throughput above a target reliability level. Results indicate that the proposed CDRL-based solution can ensure timely packet delivery even when existing baselines fall short, and it achieves lower cost compared to other throughput-maximizing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04353 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications Aygün, Ozan Vitale, Vincenzo Norman Tulino, Antonia M. Feng, Hao Erkip, Elza Llorca, Jaime Networking and Internet Architecture Machine Learning Next-generation networks aim to provide performance guarantees to real-time interactive services that require timely and cost-efficient packet delivery. In this context, the goal is to reliably deliver packets with strict deadlines imposed by the application while minimizing overall resource allocation cost. A large body of work has leveraged stochastic optimization techniques to design efficient dynamic routing and scheduling solutions under average delay constraints; however, these methods fall short when faced with strict per-packet delay requirements. We formulate the minimum-cost delay-constrained network control problem as a constrained Markov decision process and utilize constrained deep reinforcement learning (CDRL) techniques to effectively minimize total resource allocation cost while maintaining timely throughput above a target reliability level. Results indicate that the proposed CDRL-based solution can ensure timely packet delivery even when existing baselines fall short, and it achieves lower cost compared to other throughput-maximizing methods. |
| title | A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications |
| topic | Networking and Internet Architecture Machine Learning |
| url | https://arxiv.org/abs/2603.04353 |