With the rapid development of mobile industrial applications and due to the limited coverage of static edge servers, traditional edge computing technology has great limitations in dynamic environmental applications. This paper proposes a deep reinforcement learning-based cloud-edge collaborative mobile computation offloading mechanism for satisfying the dynamic service requirements in industrial networks. Specifically, a three-layer network model of digital twins and a decentralized network of task resources are first constructed to handle the mobility of user terminals and the relevance of tasks. Then, based on the comprehensive consideration of mobility, associated tasks, computing resources and offloading decisions, an optimization problem is formulated to minimize the weighted sum of the execution delay and energy consumption of all tasks for all users. Additionally, a deep reinforcement learning-based cloud-edge collaborative mobile computation offloading (DRL-CCMCO) algorithm is proposed to solve this optimization problem. Based on the differences in each edge cloud, this algorithm sets the priority of the shared experience pool and selects the most effective experience samples to complete better learning and training. It also utilizes a distributed learning method to learn the probability of an approximate reward distribution and optimizes network parameters through cloud-edge collaboration to achieve faster optimal offloading decision. Finally, a large number of simulation results show that the proposed algorithm has the characteristics of fast convergence and high stability, and it can obtain the optimal offloading decision with the lowest total cost.

中文翻译：

---

工业网络中基于深度强化学习的云边缘协作移动计算卸载

随着移动工业应用的快速发展，由于静态边缘服务器的覆盖范围有限，传统的边缘计算技术在动态环境应用中存在很大的局限性。本文提出了一种基于深度强化学习的云边协同移动计算卸载机制，以满足工业网络中的动态服务需求。具体而言，首先构建了数字孪生的三层网络模型和任务资源的分散网络，以处理用户终端的移动性和任务的相关性。然后，基于对移动性、关联任务、计算资源和卸载决策的综合考虑，制定了一个优化问题，以最小化所有用户的所有任务的执行延迟和能耗的加权和。此外，提出了一种基于深度强化学习的云边协同移动计算卸载（DRL-CCMCO）算法来解决该优化问题。该算法根据每个边缘云的差异，设置共享经验池的优先级，选择最有效的经验样本，以完成更好的学习和训练。它还利用分布式学习方法来学习近似奖励分布的概率，并通过云边协作优化网络参数，以实现更快的最优卸载决策。最后，