Model-Driven Time-Sensitive Network Planning: Topology Construction, Routing, and Scheduling

To meet the urgent demand for deterministic communication in time-critical applications such as industrial control, autonomous driving, and aerospace systems, this paper systematically analyzes the key technologies and proposes a model-driven time-sensitive network planning solution. The solution considers the three key technologies: topology construction, route selection, and traffic scheduling, to ensure that the end-to-end delay of timecritical flows meets the stringent delay requirements. In addition to the models, the network planning algorithm is designed. Experimental results show that the network planning solution proposed in this paper can effectively guarantee the bounded delay of time-critical flows and increase the schedulability by about $\mathbf{5 \% - 1 5 \%}$ in multiple scheduling scenarios, including from $70.8 \%$ to $88.8 \%$ under high load conditions. At the same time, it significantly reduces the standard deviation of link load from 10.74 to about 4.126, which is beneficial to load balancing.