Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.11076 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911441198514176 |
|---|---|
| author | Fatehi, Kavan Ghourtani, Mostafa Rahmani Sonee, Amir Yadav, Poonam Russo, Alessandra M Ahmadi, Hamed Calinescu, Radu |
| author_facet | Fatehi, Kavan Ghourtani, Mostafa Rahmani Sonee, Amir Yadav, Poonam Russo, Alessandra M Ahmadi, Hamed Calinescu, Radu |
| contents | Sixth-generation (6G) radio access networks (RANs) must enforce strict service-level agreements (SLAs) for heterogeneous slices, yet sudden latency spikes remain difficult to diagnose and resolve with conventional deep reinforcement learning (DRL) or explainable RL (XRL). We propose \emph{Attention-Enhanced Multi-Agent Proximal Policy Optimization (AE-MAPPO)}, which integrates six specialized attention mechanisms into multi-agent slice control and surfaces them as zero-cost, faithful explanations. The framework operates across O-RAN timescales with a three-phase strategy: predictive, reactive, and inter-slice optimization.
A URLLC case study shows AE-MAPPO resolves a latency spike in $18$ms, restores latency to $0.98$ms with $99.9999\%$ reliability, and reduces troubleshooting time by $93\%$ while maintaining eMBB and mMTC continuity. These results confirm AE-MAPPO's ability to combine SLA compliance with inherent interpretability, enabling trustworthy and real-time automation for 6G RAN slicing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11076 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Interpretable Attention-Based Multi-Agent PPO for Latency Spike Resolution in 6G RAN Slicing Fatehi, Kavan Ghourtani, Mostafa Rahmani Sonee, Amir Yadav, Poonam Russo, Alessandra M Ahmadi, Hamed Calinescu, Radu Systems and Control Artificial Intelligence Signal Processing Sixth-generation (6G) radio access networks (RANs) must enforce strict service-level agreements (SLAs) for heterogeneous slices, yet sudden latency spikes remain difficult to diagnose and resolve with conventional deep reinforcement learning (DRL) or explainable RL (XRL). We propose \emph{Attention-Enhanced Multi-Agent Proximal Policy Optimization (AE-MAPPO)}, which integrates six specialized attention mechanisms into multi-agent slice control and surfaces them as zero-cost, faithful explanations. The framework operates across O-RAN timescales with a three-phase strategy: predictive, reactive, and inter-slice optimization. A URLLC case study shows AE-MAPPO resolves a latency spike in $18$ms, restores latency to $0.98$ms with $99.9999\%$ reliability, and reduces troubleshooting time by $93\%$ while maintaining eMBB and mMTC continuity. These results confirm AE-MAPPO's ability to combine SLA compliance with inherent interpretability, enabling trustworthy and real-time automation for 6G RAN slicing. |
| title | Interpretable Attention-Based Multi-Agent PPO for Latency Spike Resolution in 6G RAN Slicing |
| topic | Systems and Control Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2602.11076 |