End-to-End Routing for Jointly Ultra-Service and Regular-Service Flows in TSN: An Evolutionary Transformer-Based DRL Approach

Abstract

The development of immersive video service and large-scale cluster computing technology further expand the potential application scope of time-sensitive networks (TSN). In the delivery network for these emerging services, Ultra-Service Flows (USFs), characterized by ultra-high bandwidth and deterministic latency, have become the most representative traffic type. Therefore, the route scheduling for hybrid deployment of Regular-Service Flows (RSFs) and USF has become an unavoidable issue within a deterministic domain. However, existing research has not thoroughly investigated routing issues for the hybrid deployment of USF and RSF since the significant differences between them. To resolve this issue, a multi-objective optimization model is designed in this paper, in which three key factors are comprehensively considered: the path blocking degree of USF, the available bandwidth rate, and the end-to-end latency of RSF. Subsequently, we propose a cooperative framework where a Transformer-DRL agent, enforced by validity-constraint masking, generates high-quality initial populations to “warm start” NSGA-II. This hybrid design replaces random initialization, effectively resolving the evolutionary “cold start” issue in large-scale topologies while ensuring routing feasibility. The simulation results demonstrate that the algorithm proposed here in significantly improves performance and generalization capabilities, improving the RSF’s overall latency, the USF’s path-blocking degree, and the available bandwidth rate by 10.526%, 14.102%, and 14.286%, respectively.