Flow Preprocessing for Online Routing and Scheduling in Time-Sensitive Networks

Abstract

More and more attention has been attracted to online flow scheduling mechanisms in Time-Sensitive Networks (TSN) because of the significantly increasing demand for low delay and low jitter communication in fields such as smart factories or automatic vehicles. However, because of the lack of flow information known in advance, such as when and what kind of flows will arrive and will be scheduled, it’s easy for most online routing and scheduling methods to reach the bottleneck of flow scheduling in the scenario where there are time-triggered flows with large period differences to be scheduled, resulting in a low scheduling success rate.In this paper, a flow preprocessing method is proposed to filter flows with certain characteristics that have potential negative influence on the overall scheduling success rate or bandwidth utilization according to their periods and arrival probability. The proposed method can be easily superimposed on any kind of online routing and scheduling methods in TSN to improve performance. The flow preprocessing method is evaluated in scenarios with different numbers and types of flows, and the result shows that the flow scheduling with our preprocessing method outperform the flow scheduling without preprocessing in terms of scheduling success rate, bandwidth utilization and computation time.