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

2026-03-28

AI Summary

This work addresses the challenge of dynamic resource allocation in 6G network slicing for tactile internet applications where enhanced mobile broadband (eMBB) and high-reliability low-latency communication (HRLLC) coexist, requiring simultaneous satisfaction of heterogeneous QoS and stringent latency constraints. The proposed DRASTIC framework introduces a dexterity index dependent on task execution to establish a closed-loop coupling between network and task dynamics. By incorporating probabilistic latency constraints into the objective function via Lagrangian relaxation, it formulates a min-max optimization structure that jointly maximizes throughput and guarantees latency. An advantage actor-critic reinforcement learning algorithm guided by Lyapunov optimization enables efficient scheduling under a Markov-modulated Poisson traffic model. Simulations demonstrate that DRASTIC stabilizes queues and meets multidimensional QoS requirements under dynamic wireless conditions and varying task loads, significantly outperforming existing 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.

Problem

• Network Slicing
• Tactile Internet
• Resource Allocation
• Quality of Service
• Latency Constraint

Innovation

• Dynamic Resource Allocation
• Network Slicing
• Tactile Internet
• Reinforcement Learning
• Lyapunov Optimization