RL-Loop: Reinforcement Learning-Driven Real-Time 5G Slice Control for Connected and Autonomous Mobility Services

2026-04-02

AI Summary

This study addresses the challenge of efficiently allocating edge CPU resources in 5G network slicing for connected and autonomous driving services under dynamically changing traffic conditions. To this end, the authors propose RL-Loop, a lightweight reinforcement learning-based closed-loop control framework leveraging Proximal Policy Optimization (PPO). RL-Loop enables software-defined, dynamic CPU resource scheduling by observing key slice performance indicators at sub-second intervals. This work represents the first application of reinforcement learning–driven closed-loop control to real-time resource management in 5G slicing. Experimental validation on a real-world platform demonstrates that RL-Loop reduces average CPU allocation by over 55% compared to baseline approaches while maintaining comparable levels of service quality degradation, thereby significantly enhancing both resource efficiency and system responsiveness.

Abstract

Smart and connected mobility systems rely on 5G edge infrastructure to support real-time communication, control, and service differentiation. Achieving this requires adaptive resource management mechanisms that can react to rapidly changing traffic conditions. In this paper, we propose RL-Loop, a closed-loop reinforcement learning framework for real-time CPU resource control in 5G network slicing environments supporting connected mobility services. RL-Loop employs a Proximal Policy Optimization (PPO) agent that continuously observes slice-level key performance indicators and adjusts edge CPU allocations at one-second granularity on a real testbed. The framework leverages real-time observability and feedback to enable adaptive, software-defined edge intelligence. Experimental results suggest that RL-Loop can reduce average CPU allocation by over 55% relative to the reference operating point while reaching a comparable quality-of-service degradation region. These results indicate that lightweight reinforcement learning--based feedback control can provide efficient and responsive resource management for 5G-enabled smart mobility and connected vehicle services.

Problem

• 5G network slicing
• real-time resource control
• connected autonomous mobility
• edge computing
• adaptive resource management

Innovation

• Reinforcement Learning
• 5G Network Slicing
• Edge Computing
• Real-Time Resource Control
• Connected Autonomous Mobility