Multiagent Deep Reinforcement Learning for Task Offloading and Resource Allocation in Cybertwin-Based Networks

In this article, a hierarchical task offloading strategy is presented for delay-tolerant and delay-sensitive missions by integrating edge computing and artificial intelligence into Cybertwin-based network to guarantee user Quality of Experience (QoE), low latency, and ultrareliable services, which are huge challenges to the Internet of Things (IoT) due to diverse application requirements, heterogeneous multidimensional resources, and time-varying network environments. The novel scheme achieves faster task processing, dynamic real-time allocation, and lower overhead by taking advantages of a multiagent deep deterministic policy gradient (MADDPG). Moreover, federated learning is used to train the MADDPG model. Numerical results demonstrate that the proposed algorithm improves system processing efficiency and task completion ratio compared to the benchmark schemes.

Automated summary

This article proposes a hierarchical task offloading strategy that integrates edge computing and artificial intelligence to ensure user QoE, low latency, and ultrareliable services in IoT. By utilizing multiagent deep deterministic policy gradient, the novel scheme achieves faster task processing and dynamic real-time allocation with lower overhead. Federated learning is used to train the model, leading to improved system processing efficiency and task completion ratio compared to benchmark schemes.