Joint Resource Allocation and Task Offloading for Heterogeneous Cloud-Edge-End Networks Assisted by NOMA
Xiaoxuan Hu, Liang Shan, Jialin Hua, Jin Qi, Zhenjiang Dong, Bin Xu, Yanfei Sun
Abstract
To address the challenges of computational task offloading for resource-constrained, heterogeneous terminals in the 6G Industrial Internet of Things (IIoT), which generate computation-intensive and resource-efficient tasks in real time, we propose a Digital Twin(DT)-driven cloud-edge-end collaborative resource allocation and task offloading (RATO) model that accounts for both latency and energy consumption. First, we establish a cloud-edge-end collaborative communication and computation framework by integrating cloud computing with edge computing, accommodating terminal and edge server heterogeneity, and employing Non-Orthogonal Multiple Access (NOMA) communication along with key authentication mechanisms to ensure secure communications. Next, Digital Twin technology is utilized for real-time monitoring of the physical environment, considering simulation bias to construct accurate DT entities. Finally, we employ a DT-driven multi-agent deep deterministic policy gradient (DT-MADDPG) algorithm to derive the optimal task scheduling strategy. Simulation results demonstrate that the proposed model significantly outperforms existing schemes in terms of delay, energy cost, load balancing of edge servers, and Quality of Service (QoS) for terminals.