Research On Hybrid Traffic Scheduling Algorithms In Time Sensitive Networking

The rapid growth of the Internet and the emergence of new applications have dramatically changed the way people live and work.Many industry applications,including in-vehicle and avionics networks,require bounded latency at the millisecond level or even lower.As a result,Time Sensitive Networking(TSN)task group was established and has proposed a series of traffic shaping mechanisms,such as Time Aware Shaper(TAS),Credit Based Shaper(CBS)and Strict Priority Queuing(SPQ).There are many flows with different real-time requirements from different end sytems in the time-sensitive network.In order to meet the transmission requirements of each flow as much as possible with limited bandwidth resources,hybrid traffic scheduling algorithms need to be researched in depth.Currently,most of the existing literature focuses on how to guarantee bounded low-latency transmission of Scheduled Traffic(ST)and Stream Reservation(SR)traffic.However,if high-priority traffic blocks Best Effort(BE)traffic,represented by data logging and periodic software updates,for a long time,the end-to-end delay of BE messages will be excessive and the network state maintenance and system management will be affected.This thesis focuses on how to minimise the end-to-end delay of BE messages while meeting the delay requirements of ST and SR traffic in networks with mixed transmission of multiple types of traffic,and proposes hybrid traffic scheduling algorithms for two scenarios:single-hop networks and multi-hop networks respectively.The main work of this thesis is as follows.Firstly,in order to reduce the maximum end-to-end delay of BE messages by reducing the reserved bandwidth of SR traffic,this thesis proposes a traffic scheduling algorithm that combines TAS,CBS and Weighted Round-Robin(CTCW).The CTCW scheduling algorithm first adds ingress buffers before the SR_A and SR_B queues,then adjusts the reserved bandwidth ratio among the same priority traffic by setting the number of frames in each ingress buffer that enter the egress queue during ingress shaping,and finally,joints egress shaping and ingress shaping to reserve bandwidth resources that match its delay requirement for each SR flow.Simulation results show that the maximum end-to-end delay of BE messages in a single-hop network can be reduced by 9.66%～75.76%by applying the traffic scheduling algorithm that combines ingress shaping.Then,the CTCW scheduling algorithm is improved to address the problem that it is not suitable for multi-hop networks because it does not give an explicit arrival curve of the traffic as it enters the next TSN switch.As a result,a scheduling algorithm which combines TAS,SPQ and Token Bucket Emulation(CTST)is proposed.The CTST scheduling algorithm first schedules SR traffic on a per-flow basis in the TSN switch by adjusting the internal priority of each SR flow in the TSN switch and limiting the rate at which frames in each ingress buffer enter the SR_A queue and SR_B queue;then,uses a combination of egress shaping and ingress shaping to provide fine-grained services of different quality for flows with the same priority but different delay requirements.This reduces the amount of reserved bandwidth required by SR traffic when the network is schedulable and reduces the blocking of the transmission of SR frames on the transmission of BE frames.Simulation results show that in a multi-hop network,applying the CTST scheduling algorithm can reduce the maximum end-to-end delay of BE messages by 2.50%～59.41%compared to applying the CTCW scheduling algorithm,and can reduce the maximum end-to-end delay of BE messages by 0.6 1%～14.62%compared to applying the TAS+CBS scheduling algorithm.