DRASTIC: A Dynamic Resource Allocation Framework over 6G Network Slicing in Task-aware Closed-Loop Tactile Internet Applications

TL;DR

This paper introduces DRASTIC, a reinforcement learning-based framework for dynamic resource allocation in 6G network slicing tailored for task-aware tactile Internet applications, ensuring QoS and stability.

Contribution

It presents a novel, learning-driven bandwidth optimization method that dynamically manages resources for eMBB and HRLLC slices with feedback-aware task interaction.

Findings

Framework effectively meets diverse QoS requirements.

Maintains queue stability under dynamic conditions.

Outperforms existing resource allocation approaches.

Abstract

This work proposes a novel learning driven bandwidth optimization framework called DRASTIC (Dynamic Resource Allocation for Slicing in Task aware Closed loop tactile Internet applications). The proposed framework dynamically allocates resources among network slices supporting both enhanced Mobile Broadband (eMBB) and high reliable low latency communication (HRLLC) users. The algorithm ensures queue stability and meets delay targets with high probability under a Markov-modulated Poisson traffic, exploiting a Lyapunov guided advantage actor critic reinforcement learning technique. The proposed network model includes an open-loop eMBB queue whose arrival and departure are mainly driven by throughput demand, as well as a closed loop HRLLC queue that captures feedback and task execution effects. A task execution dependent dexterity index adjusts the effective arrival rate, creating a feedback aware interaction between the network and the task. A probabilistic delay constraint is incorporated into the objective via Lagrangian relaxation, yielding a min_max optimization framework that enforces latency guarantees while maximizing throughput for both types of users. Simulation results demonstrate that the proposed framework meets diverse Quality of Service (QoS) requirements, maintains queue stability under dynamic wireless and robotic task variation conditions, and outperforms other approaches.