Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Digital Twin-Assisted In-Network and Edge Collaboration for Joint User Association, Task Offloading, and Resource Allocation in the Metaverse

Ibrahim Aliyu, Seungmin Oh, Sangwon Oh, Jinsul Kim

Abstract

Advancements in extended reality (XR) are driving the development of the metaverse, which demands efficient real-time transformation of 2D scenes into 3D objects, a computation-intensive process that necessitates task offloading because of complex perception, visual, and audio processing. This challenge is further compounded by asymmetric uplink (UL) and downlink (DL) data characteristics, where 2D data are transmitted in the UL and 3D content is rendered in the DL. To address this issue, we propose a digital twin (DT)-based in-network computing (INC)-assisted multi-access edge computing (MEC) framework that enables real-time synchronization and collaborative computing via URLLC. In this framework, a network operator manages wireless and computational resources for XR user devices (XUDs), while XUDs autonomously offload tasks to maximize their utilities. We model the interactions between XUDs and the operator as a Stackelberg Markov game, where the optimal offloading strategy constitutes an exact potential game with a Nash Equilibrium (NE), and the operator's problem is formulated as an asynchronous Markov decision process (MDP). We further propose a decentralized solution in which XUDs determine offloading decisions based on the operator's joint UL-DL optimization of offloading mode (INC-E or MEC only) and DL power allocation. A Nash-asynchronous hybrid multi-agent reinforcement learning (AMRL) algorithm is developed to predict the UL user-associated and DL transmission power, thereby achieving NE. Simulation results demonstrate that the proposed approach considerably improves system utility, uplink rate, and energy efficiency by reducing latency and optimizing resource utilization in metaverse environments.

Digital Twin-Assisted In-Network and Edge Collaboration for Joint User Association, Task Offloading, and Resource Allocation in the Metaverse

Abstract

Advancements in extended reality (XR) are driving the development of the metaverse, which demands efficient real-time transformation of 2D scenes into 3D objects, a computation-intensive process that necessitates task offloading because of complex perception, visual, and audio processing. This challenge is further compounded by asymmetric uplink (UL) and downlink (DL) data characteristics, where 2D data are transmitted in the UL and 3D content is rendered in the DL. To address this issue, we propose a digital twin (DT)-based in-network computing (INC)-assisted multi-access edge computing (MEC) framework that enables real-time synchronization and collaborative computing via URLLC. In this framework, a network operator manages wireless and computational resources for XR user devices (XUDs), while XUDs autonomously offload tasks to maximize their utilities. We model the interactions between XUDs and the operator as a Stackelberg Markov game, where the optimal offloading strategy constitutes an exact potential game with a Nash Equilibrium (NE), and the operator's problem is formulated as an asynchronous Markov decision process (MDP). We further propose a decentralized solution in which XUDs determine offloading decisions based on the operator's joint UL-DL optimization of offloading mode (INC-E or MEC only) and DL power allocation. A Nash-asynchronous hybrid multi-agent reinforcement learning (AMRL) algorithm is developed to predict the UL user-associated and DL transmission power, thereby achieving NE. Simulation results demonstrate that the proposed approach considerably improves system utility, uplink rate, and energy efficiency by reducing latency and optimizing resource utilization in metaverse environments.

Paper Structure

This paper contains 40 sections, 1 theorem, 39 equations, 8 figures, 2 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Our Approach and Rationale
  3. Motivation and Our Contribution
  4. System model and problem formulation
  5. Offloading Model in INC-E Network
  6. INC-E DT Model
  7. Communication Model
  8. Uplink
  9. Downlink
  10. Computation Model
  11. Non-collaborative task offloading
  12. Collaborative task offloading
  13. Latency Model
  14. Problem Formulation
  15. Proposed solution
  16. ...and 25 more sections

Key Result

Theorem 1

Given the global state $X^t=(X_m^t)_{m\in\mathcal{M}}$ with $X_m^t=(X_{u,m}^t,X_{d,m}^t)\in\mathcal{X}$, the operator policy $\pi^t=\{\pi_u^t,\pi_d^t\}$ determines $(\mathbf{o}^t,\mathbf{p'}^t)$, and the instantaneous cost $C_\pi^t$ in operator_cost_updated_final. Then, $\mathcal{P}_O$ is an AMDP. $

Figures (8)

  • Figure 1: DT-assisted INC-E architecture
  • Figure 2: Nash-AMRL scheme for DT-assisted INC-E system
  • Figure 3: AMRL architectures: (a) Asynchronous Hybrid Multiagent Reinforcement Learning (AHMRL), (b) Actor--critic (AC), and (c) Multi-actor shared-critic (MASC).
  • Figure 4: Training for different models and metrics (a) GL reward (b) UL reward (c) DL reward (d) Utility (e) UL rate (f) Energy (g) End-to-end Latency (h) Game utility convergence.
  • Figure 5: Influence of task type vs number of UE
  • ...and 3 more figures

Theorems & Definitions (2)

  • Definition 1: SPE
  • Theorem 1