计算机科学
可扩展性
不确定性算法
算法
网络拓扑
调度(生产过程)
分布式计算
计算机网络
数学优化
数学
数据库
作者
Yuting Li,Junhui Jiang,Seung Ho Hong
标识
DOI:10.1109/jiot.2022.3163411
摘要
Recently, time-sensitive networking (TSN) has been developed to incorporate real-time capabilities to the standard Ethernet for the incompatible issue in existing industrial communication solutions and is considered a promising solution to satisfy the requirements of the Industrial Internet of Things (IIoT). However, the routing and scheduling methods are left out of the TSN standard. This study developed a novel joint traffic routing and scheduling algorithm to compute routes for time-critical flows and construct the schedules. The validity of the proposed algorithm was verified using a random synthetic test scenario. The simulation results demonstrated that the real-time requirements of time-critical traffic could be satisfied with the proposed algorithm. Subsequently, we evaluated the scalability of the proposed algorithm from the perspective of the number of flows that can be scheduled and the network size. The results showed that the computational times for 4000 flows in the realistic industrial network topology and random network topologies (with up to 21 switches and 105 end stations) are at the subsecond level, which indicated the perfect scalability of the proposed algorithm. In addition, compared with the well-known integer linear programming (ILP)-based approach, Degree of Conflict (DoC)-aware iterative routing and scheduling (DA/IRS) approach, and hybrid genetic algorithm (HGA)-based approach, the proposed algorithm is faster than the three approaches by at least an order of magnitude.
科研通智能强力驱动
Strongly Powered by AbleSci AI