Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Lara Tarkh, Ali Chouman, Hanan Lutfiyya, Abdallah Shami

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.

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

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.

Paper Structure

This paper contains 19 sections, 2 equations, 4 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Reinforcement Learning Framework
  5. RL-Loop Online Control Algorithm
  6. Feedback Loop Design
  7. Implementation Details
  8. Evaluation
  9. Experiment Setup
  10. Performance Metrics
  11. Average CPU Allocation
  12. QoS Degradation
  13. Initial Evaluation
  14. RL Training Behaviour
  15. Discussion
  16. ...and 4 more sections

Figures (4)

  • Figure 1: RL-Loop closed feedback loop in the 5G testbed. The RL agent receives KPIs as state and sends CPU limit update actions directly to the testbed every second.
  • Figure 2: 5G testbed used for RL-Loop experiments
  • Figure 3: Reward versus CPU allocation for RL-Loop. The reward is highest at intermediate CPU levels, where allocation best matches the normalized load estimate.
  • Figure 4: Evolution of the RL-Loop reward during the 900 s online run.