Pay Attention to Network: Reliability-Aware Spatial-Temporal-Frequential Scheduling for TSN-WiFi Networks

Time-Sensitive Networking (TSN) is a pivotal technology in providing deterministic and reliable communications in the wired domain. Complementarily, Wi-Fi Multi-link Operation (MLO) extends the TSN capabilities over the wireless domain to further increase the throughput and reliability for wired-wireless-integrated scenarios such as smart factories in industrial automation. To incorporate TSN and Wi-Fi MLO seamlessly, cross-domain flow scheduling is of vital importance in reliable control message transmission. Existing approaches leverage Deep Reinforcement Learning (DRL) to adapt to the dynamic wireless channel quality. However, the traditional multilayer perception (MLP)-based DRL model fails to integrate the input features of all the flows, resulting in severe underfitting issues and scheduling ineffectiveness. In this paper, we observe that the mutual dependencies among flows over the network resources are analogical to the contextual dependencies of tokens over the lexical sequence. Leveraging this insight, we exploit the self-attention mechanism in Natural Language Processing (NLP) to learn the network-wise dependencies among different flows. Theoretically, to provide an analytical guide to TSN-WiFi flow scheduling, we present a global scheduling abstraction to describe the key resource constraints of the cross-domain flow scheduling problem. Following that, we propose the load-aware TSN scheduling algorithm and the attention-based DRL scheduling algorithm to allocate spatial-temporal-frequencial resources for flows adhering to the above constraints. Experiments in various settings validate the effectiveness of the proposed method, which enhances the reliability by 12.09% compared with the state-of-the-art method.