Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards a Partial Computation offloading in In-networking Computing-Assisted MEC: A Digital Twin Approach

Ibrahim Aliyu, Awwal Arigi, Seungmin Oh, Tai-Won Um, Jinsul Kim

TL;DR

This work tackles latency minimization for partial computation offloading in a COIN-assisted MEC setting using URLLC by introducing a digital twin that models computing resources and processing rates. It casts the offloading decision as a distributed exact potential game (EPG) and employs a DDQN to predict optimal offloading ratios and resource allocation, enabling scalable, low-complexity coordination. The DT emulation provides accurate insights for efficient resource allocation, improving end-to-end latency and robustness while mitigating UE contention. The results show significant gains over MEC baselines and random strategies, highlighting the practical impact of combining DT, game theory, and deep reinforcement learning for industrial edge computing.

Abstract

This paper addresses the problem of minimizing latency with partial computation offloading within Industrial Internet-of-Things (IoT) systems in in-network computing (COIN)-assisted Multiaccess Edge Computing (C-MEC) via ultra-reliable and low latency communications (URLLC) links. We propose a digital twin (DT) scheme for a multiuser scenario, allowing collaborative partial task offloading from user equipment (UE) to COIN-aided nodes or MEC. Specifically, we formulate the problem as joint task offloading decision, ratio and resource allocation. We employ game theory to create a low-complexity distributed offloading scheme in which the task offloading decision problem is modelled as an exact potential game. Double Deep Q-Network (DDQN) is utilized within the game to proactively predict optimal offloading ratio and resource allocation. This approach optimizes resource allocation across the whole system and enhances the robustness of the computing framework, ensuring efficient execution of computation-intensive services. Additionally, it addresses centralized approaches and UE resource contention issues, thus ensuring faster and more reliable communication.

Towards a Partial Computation offloading in In-networking Computing-Assisted MEC: A Digital Twin Approach

TL;DR

This work tackles latency minimization for partial computation offloading in a COIN-assisted MEC setting using URLLC by introducing a digital twin that models computing resources and processing rates. It casts the offloading decision as a distributed exact potential game (EPG) and employs a DDQN to predict optimal offloading ratios and resource allocation, enabling scalable, low-complexity coordination. The DT emulation provides accurate insights for efficient resource allocation, improving end-to-end latency and robustness while mitigating UE contention. The results show significant gains over MEC baselines and random strategies, highlighting the practical impact of combining DT, game theory, and deep reinforcement learning for industrial edge computing.

Abstract

This paper addresses the problem of minimizing latency with partial computation offloading within Industrial Internet-of-Things (IoT) systems in in-network computing (COIN)-assisted Multiaccess Edge Computing (C-MEC) via ultra-reliable and low latency communications (URLLC) links. We propose a digital twin (DT) scheme for a multiuser scenario, allowing collaborative partial task offloading from user equipment (UE) to COIN-aided nodes or MEC. Specifically, we formulate the problem as joint task offloading decision, ratio and resource allocation. We employ game theory to create a low-complexity distributed offloading scheme in which the task offloading decision problem is modelled as an exact potential game. Double Deep Q-Network (DDQN) is utilized within the game to proactively predict optimal offloading ratio and resource allocation. This approach optimizes resource allocation across the whole system and enhances the robustness of the computing framework, ensuring efficient execution of computation-intensive services. Additionally, it addresses centralized approaches and UE resource contention issues, thus ensuring faster and more reliable communication.
Paper Structure (16 sections, 14 equations, 3 figures, 1 table, 1 algorithm)

This paper contains 16 sections, 14 equations, 3 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System model and problem formulation
  3. Offloading Model in C-MEC Network
  4. C-MEC DT Model
  5. Communication Model
  6. Computation Model
  7. COIN Node Processing
  8. MEC Processing
  9. Latency model
  10. Problem formulation
  11. Proposed solution
  12. Multi-user Computation Offloading Game
  13. DDQN for optimal offloading ratio and resource allocation
  14. Game-Theoretic Offloading Framework (GTOF)
  15. Numerical Results
  16. ...and 1 more sections

Figures (3)

  • Figure 1: C-MEC architecture
  • Figure 2: Performance evaluation based on Experimental Parameters on the System Model (a) Episode (b) Task input type
  • Figure 3: Performance evaluation based on different numbers of users/COIN node (a) UE number (b) COIN nodes