Interpretable Attention-Based Multi-Agent PPO for Latency Spike Resolution in 6G RAN Slicing

TL;DR

This paper introduces AE-MAPPO, an interpretable multi-agent reinforcement learning framework with attention mechanisms that effectively resolves latency spikes in 6G RAN slicing, ensuring SLA compliance and real-time decision-making.

Contribution

The paper presents AE-MAPPO, a novel attention-enhanced multi-agent RL approach that provides faithful explanations and improves latency spike resolution in 6G RAN slicing.

Findings

Resolves latency spikes in 18ms

Restores latency to 0.98ms with 99.9999% reliability

Reduces troubleshooting time by 93%

Abstract

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.