DRL-COO: DRL-Based Collaborative Offloading Optimization for Multiaccess Edge Computing Using Improved Experience Replay

doi:10.1109/JSEN.2025.3623885

DRL-COO: DRL-Based Collaborative Offloading Optimization for Multiaccess Edge Computing Using Improved Experience Replay

2025-12-01

0

PRE

AI

DOI：10.1109/JSEN.2025.3623885

Original

Original request for help

Save

Abstract

En 中文

The demands from the Internet of Everything (IoE) ecosystem led to the emergence of the sixth-generation (6G) networks. Multiaccess edge computing (MEC) provides an efficient solution for enhancing the performance of integrated sensing and communications within the 6G IoE through offloading optimization. Nevertheless, existing offloading decision methods encounter difficulties in balancing the computational load within the system and obtaining a globally optimal strategy. In this article, a deep reinforcement learning-based collaborative offloading optimization (DRL-COO) method is proposed to solve the offloading optimization problem in the 6G-enabled multiuser collaborative task offloading MEC (MU-CTOMEC) system, which aims to minimize delay, energy consumption, and task failure rate. Specifically, this method establishes a Markov decision process (MDP) model for collaborative task offloading and trains it through interaction with the environment using a deep reinforcement learning (DRL) algorithm based on an asynchronous priority experience replay mechanism. The experimental results demonstrate the superiority of our proposed optimization algorithm over state-of-the-art methods in terms of average computation time, energy consumption, and task failure rate.

Keywords:

Collaborative offloading

deep reinforcement learning (DRL)

edge computing

DRL-COO: DRL-Based Collaborative Offloading Optimization for Multiaccess Edge Computing Using Improved Experience Replay

Abstract

Journal

Organization