• Home
  • Search
  • Joint Optimization of DNN Partition and Continuous Task Scheduling for Digital Twin-Aided MEC Network With Deep Reinforcement Learning
  • Cite Icon21
  • https://doi.org/10.1109/access.2023.3257342Copy DOI Icon

Joint Optimization of DNN Partition and Continuous Task Scheduling for Digital Twin-Aided MEC Network With Deep Reinforcement Learning

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Nowadays, mobile application services face the challenges of high speed, low latency and high reliability. The combination of digital twin (DT) technology and mobile edge computing (MEC) network can effectively solve these challenges. DT technology can help MEC network monitor and predict the network states. In this paper, we propose a DT-aided MEC network scenario with deep neural network (DNN) inference as the computing task of end devices (EDs). ED can offload part of DNN layers to MEC server. To allocate communication resources, we propose an algorithm based on asynchronous advantage actor-critic (A3C), which manages the transmission power and channel selection of EDs. Since DNN inference is continuous in real scenes, we consider the continuous DNN inference tasks. We convert the DNN optimal partition point solving problem to a min st-cut problem, and propose a graph theory based DNN optimal partition point solving algorithm to minimize the inference latency. Simulation results show that the proposed algorithm can effectively reduce the inference latency. Compared with actor-critic (AC) and deep Q network (DQN), the proposed algorithm has faster convergence speed and better convergence value. Compared with the traditional one-time DNN model partition algorithm, the proposed algorithm is more suitable for DNN continuous task arrival scenario.

Similar Papers
  • Conference Article
  • Citations10

Delay-Aware DNN Inference Throughput Maximization in Edge Computing via Jointly Exploring Partitioning and Parallelism

  • Oct 04, 2021
  • Jing Li +4
  • Research Article
  • Citations113

Throughput Maximization of Delay-Aware DNN Inference in Edge Computing by Exploring DNN Model Partitioning and Inference Parallelism

  • May 01, 2023
  • IEEE Transactions on Mobile Computing
  • Jing Li +5
  • Research Article
  • Citations1

Efficient Resource Allocation in Digital Twin‐Assisted Mobile Edge Computing Network

  • Apr 01, 2025
  • Transactions on Emerging Telecommunications Technologies
  • Ilsa Rameen +3
  • Research Article
  • Citations14

A Robust Distributed Hierarchical Online Learning Approach for Dynamic MEC Networks

  • Feb 01, 2022
  • IEEE Journal on Selected Areas in Communications
  • Yi-Chen Wu +2
  • Conference Article
  • Citations1

A Robust Hierarchical Learning Approach for dynamic MEC Networks

  • Dec 01, 2020
  • Yi-Chen Wu +2
  • Research Article

Theoretical Analysis of Mixture-of-Experts in Mobile Edge Computing

  • Jan 01, 2025
  • IEEE Transactions on Networking
  • Hongbo Li +1
  • Research Article
  • Citations129

Deep reinforcement learning based mobile edge computing for intelligent Internet of Things

  • Aug 20, 2020
  • Physical Communication
  • Rui Zhao +3
  • Research Article
  • Citations55

Meta-Learning Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks

  • Jan 05, 2021
  • IEEE Communications Letters
  • Liang Huang +4
  • Research Article
  • Citations77

An adaptive DNN inference acceleration framework with end–edge–cloud collaborative computing

  • Nov 04, 2022
  • Future Generation Computer Systems
  • Guozhi Liu +6
  • Research Article
  • Citations34

Energy or Accuracy? Near-Optimal User Selection and Aggregator Placement for Federated Learning in MEC

  • Mar 01, 2024
  • IEEE Transactions on Mobile Computing
  • Zichuan Xu +7
  • Conference Article
  • Citations4

Soft Actor-Critic Learning-Based Joint Computing, Pushing, and Caching Framework in MEC Networks

  • Dec 04, 2023
  • Xiangyu Gao +4
  • Research Article
  • Citations2

Improving Multi-Model Anomaly Traffic Detection in MEC Networks With Large-Model- Powered Continuous Learning

  • May 01, 2025
  • IEEE Network
  • Junjie Zhang +4
  • PDF
  • Research Article
  • Citations4

Joint Radio Map Construction and Dissemination in MEC Networks: A Deep Reinforcement Learning Approach

  • Jul 19, 2022
  • Wireless Communications and Mobile Computing
  • Xingguang Liu +4
  • Research Article
  • Citations61

Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks

  • May 27, 2022
  • Sensors (Basel, Switzerland)
  • Shicheng Yang +2
  • Research Article
  • Citations72

DRL-Based Computation Offloading With Queue Stability for Vehicular-Cloud-Assisted Mobile Edge Computing Systems

  • Apr 01, 2023
  • IEEE Transactions on Intelligent Vehicles
  • Guifu Ma +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.