Optimization strategy for TSN scheduling based on an enhanced stream preprocessing method

In the TSN (Time-Sensitive Networking) technology framework, scheduling algorithms are crucial for ensuring conflict-free, low-jitter, and low-latency transmission of high-priority data streams. Nevertheless, with the ever-increasing complexity of network topologies and the continuous expansion of traffic volumes, traditional scheduling algorithms face significant challenges. A significant increase in computational complexity has become a primary concern. Scheduling algorithms are required to handle a vast number of data stream characteristics and their associated constraints, which consequently leads to a significant augmentation in computational overhead and scheduling delay. This research addresses the optimization issue of time-sensitive stream scheduling in TSN. A stream segmentation and shaping method based on feature extraction and optimized clustering is proposed. It conducts analysis, modeling, enhancement, clustering of stream features, and implements segmentation logic. By reducing the scale of scheduling tasks and implementing a strategy of providing redundant gate-opening times, transmission quality is improved, and the solution time for subsequent scheduling problems is reduced. This provides an innovative solution approach for TSN scheduling problems in complex scenarios.