Multi-Agent Reinforcement Learning for SLA-Aware Network Slicing in UAV-Enabled MEC

2026-07-10

AI Summary

This work addresses the challenge of guaranteeing service-level agreement (SLA) compliance for heterogeneous network slices in unmanned aerial vehicle (UAV)-enabled mobile edge computing, where dynamic user mobility, stochastic task arrivals, and limited onboard resources complicate resource management. To this end, the authors propose a predictive multi-agent reinforcement learning framework that integrates a lightweight user mobility prediction module with Multi-Agent Proximal Policy Optimization (MAPPO) to jointly optimize UAV trajectories and computational resource allocation. A novel SLA-aware reward function is designed to account for violation probability, duration, and energy consumption, while a centralized training with decentralized execution architecture enhances scalability. Experimental results demonstrate that the proposed approach significantly improves SLA stability, closely approaching the ideal performance bound under accurate mobility prediction, while effectively balancing energy efficiency and latency.

Abstract

Unmanned Aerial Vehicle (UAV)-enabled Mobile Edge Computing (MEC) offers flexible capacity provisioning for heterogeneous network slices, including Hyper-Reliable and Low-Latency Communication (HRLLC), Enhanced Mobile Broadband (eMBB), and Massive Machine-Type Communications (mMTC). However, guaranteeing slice-level Service-Level Agreements (SLAs) under dynamic user mobility, stochastic task arrivals, and constrained onboard energy and computing resources remains a fundamental challenge. This paper proposes a predictive multi-agent Reinforcement Learning (RL) framework that proactively maintains SLA stability in UAV-enabled MEC through coordinated trajectory control and computation resource allocation. A lightweight prediction module forecasts near-future user mobility, enabling UAVs to anticipate congestion and reposition before SLA violations occur. We design an SLA-aware reward function that explicitly penalizes both violation probability and duration across slices, alongside total energy consumption. UAV agents are trained using Multi-Agent Proximal Policy Optimization (MAPPO) with centralized training and decentralized execution, enabling scalable online decision-making. Event-driven simulations with realistic mobility traces demonstrate that the proposed framework significantly improves SLA stability compared with baselines while maintaining competitive energy efficiency and delay performance, approaching oracle-level performance with sufficiently accurate predictive information.

Problem

• Service-Level Agreement (SLA)
• Network Slicing
• UAV-enabled MEC
• Resource Allocation
• User Mobility

Innovation

• Multi-Agent Reinforcement Learning
• SLA-Aware Network Slicing
• UAV-Enabled MEC
• Predictive Trajectory Control
• MAPPO