Research On Traffic Scheduling Algorithms In Time-sensitive Networks

With the development of autonomous driving,smart factories,and industrial automation,traditional fieldbuses can no longer meet their requirements for high bandwidth,real-time,and safety.In order to meet the communic ation needs,in the era of Industry 4.0,operation technology and information technology continue to merge,the IEEE working group has developed a unified standardized protocol suite TSN,that is,time-sensitive network.Efficient network scheduling algori thms can transmit data in a timely and reliable manner.At the same time,it combines routing optimization to control the forwarding and transmission of data traffic,and realize the deterministic transmission of data flow in the network.In TSN,a credit shaper-based mechanism is usually used to schedule AVB traffic,but this mechanism usually increases the overall delay.Many scholars at home and abroad have also ignored this problem.Therefore,this article focuses on this problem and focuses on the sche duling of AVB traffic.And propose a solution algorithm.The traffic scheduling problem in TSN can be mapped to the well-known non-waiting job shop scheduling problem.Based on this mathematical model,the main innovations of this paper are as follows:1.A hybrid genetic tabu search algorithm for traffic scheduling in TSN to optimize the maximum transmission completion time is proposed.Due to the wait-free scheduling model,traffic scheduling can ultimately be attributed to the scheduling problem and the sequencing problem.This algorithm solves the scheduling problem,that is,determines the start transmission sequence of the traffic.The algorithm first uses the genetic algorithm to generate the initial population,generates new individuals through a series of operations such as selection,crossover,and mutation,and then uses the tabu search algorithm to optimize these new individuals to obtain the optimization results.This algorithm combines the advantages of genetic algorithm and tabu search algorithm to make it have strong global search ability and local search ability.2.A load balancing routing algorithm based on the K shortest path is proposed,which is used to consider the routing problem of traffic,balance the link load,and optimize the maximum transmission completion time.This algorithm is based on the hybrid genetic tabu search algorithm,which considers link load balancing and makes full use of idle links for traffic scheduling.The algorithm combines the K shortest path algorithm,according to the first K candidate paths of each flow,considers the link load in the topology,and determines the route of each transmission flow,so that the load in the link is balanced without causing The link is congested.Experiments show that the results of traffic scheduling by the hybrid genetic tabu search algorithm are better than the results obtained by the traditional genetic algorithm and the tabu search algorithm,15.79% lower than the result of the genetic algorithm,10.48% lower than the result of the tabu search algorithm,and speed up Iterative convergence speed.The transmission completion time obtained by the load balancing routing algorithm based on the K shortest path is 10.17% lower than that of the traditional shortest path algorithm direct ly,which effectively reduces the delay increase caused by link congestion.Aiming at the problems of high latency,slow iteration convergence,and mutual influence between routes in traffic scheduling in TSN,this paper proposes a new scheduling algorithm that can significantly reduce the final transmission completion time of traffic and ensure deterministic transmission of traffic.,Provide an important technical reference and guarantee for the real-time reliability design of the system.