ZTE Communications ›› 2022, Vol. 20 ›› Issue (4): 7888.DOI: 10.12142/ZTECOM.202204010
• Research Paper • Previous Articles Next Articles
LI Zonghui^{1}, YANG Siqi^{1}, YU Jinghai^{2}(), HE Fei^{3}, SHI Qingjiang^{4,}^{5}
Received:
20220104
Online:
20221231
Published:
20221230
About author:
LI Zonghui received his BS degree in computer science from Beijing Information Science and Technology University, China in 2010, and MS and PhD degrees from the Institute of Microelectronics and the School of Software, Tsinghua University, China in 2014 and 2019, respectively. He is currently an associate professor in the School of Computer and Information Technology, Beijing Jiaotong University, China. His research interests include embedded and high performance computing, realtime embedded systems, especially for industrial control networks and timesensitive networking.YANG Siqi received her BS degree in network engineering from Hebei University, China. She is currently working toward her master’s degree at Beijing Jiaotong University, China. Her research interest is realtime networks.YU Jinghai (LI Zonghui, YANG Siqi, YU Jinghai, HE Fei, SHI Qingjiang. Predictive Scheme for Mixed Transmission in TimeSensitive Networking[J]. ZTE Communications, 2022, 20(4): 7888.
X Distribution Within the Range of Length [64, 1 518]  RemainedTimeLoss/byte  Guardloss/byte 

Uniform distribution  395.5  1 122.5 
Binomial distribution  363.75  1 154.2 
Poisson distribution  395.5  1 122.5 
Normal distribution  395.75  1 122.3 
Table 1 Expected bandwidth loss: the remaining time transmission strategy (RemainedTimeLoss) vs the guard band strategy (Guardloss) of 802.1QBV
X Distribution Within the Range of Length [64, 1 518]  RemainedTimeLoss/byte  Guardloss/byte 

Uniform distribution  395.5  1 122.5 
Binomial distribution  363.75  1 154.2 
Poisson distribution  395.5  1 122.5 
Normal distribution  395.75  1 122.3 
X Distribution Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte  Reduced Rate/byte 

Uniform distribution  29.08  131.43  77.87% 
Binomial distribution  27.31  135.96  79.91% 
Poisson distribution  27.05  136.52  80.19% 
Normal distribution  27.28  136.01  79.94% 
Table 2 Expected bandwidth loss: the optimal preemption strategy (OPLoss) vs the mixed strategy (MixedLoss) of the guard band and the frame preemption
X Distribution Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte  Reduced Rate/byte 

Uniform distribution  29.08  131.43  77.87% 
Binomial distribution  27.31  135.96  79.91% 
Poisson distribution  27.05  136.52  80.19% 
Normal distribution  27.28  136.01  79.94% 
Figure 7 Comparison of the expected bandwidth loss between the optimal preemption strategy (OPLoss) and the mixed strategy (MixedLoss) of the guard band and the frame preemption
Uniform Distribution Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  1.93  3.14 
X ≥ 124, Y < 60  3.04  11.61 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  17.89  106.61 
X ≥ 124, Y ≥ 60, X  Y < 64  6.22  10.07 
Table 3 Expected bandwidth loss of each part: the optimal preemption strategy (OPLoss) vs the mixed strategy (MixedLoss) in Uniform distribution
Uniform Distribution Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  1.93  3.14 
X ≥ 124, Y < 60  3.04  11.61 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  17.89  106.61 
X ≥ 124, Y ≥ 60, X  Y < 64  6.22  10.07 
Binomial Distribution (p=0.5) Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  0  0 
X ≥ 124, Y < 60  2.43  9.27 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  19.91  118.64 
X ≥ 124, Y ≥ 60, X  Y < 64  4.97  8.04 
Table 4 Expected bandwidth loss of each part: the optimal preemption strategy (OPLoss) vs the mixed strategy (MixedLoss ) in Binomial distribution
Binomial Distribution (p=0.5) Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  0  0 
X ≥ 124, Y < 60  2.43  9.27 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  19.91  118.64 
X ≥ 124, Y ≥ 60, X  Y < 64  4.97  8.04 
Poisson Distribution Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  0  0 
X ≥ 124, Y < 60  2.24  8.53 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  20.24  120.58 
X ≥ 124, Y ≥ 60, X  Y < 64  4.57  7.4 
Table 5 Expected bandwidth loss of each part: the optimal preemption strategy (OPLoss) vs the mixed strategy (MixedLoss) in poisson distribution
Poisson Distribution Within the Range of Length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  0  0 
X ≥ 124, Y < 60  2.24  8.53 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  20.24  120.58 
X ≥ 124, Y ≥ 60, X  Y < 64  4.57  7.4 
Normal distribution within the range of length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  0.016  0.028 9 
X ≥ 124, Y < 60  2.41  9.18 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  19.94  118.83 
X ≥ 124, Y ≥ 60, X  Y < 64  4.92  7.96 
Table 6 Expected bandwidth loss of each part: the optimal preemption strategy (OPLoss) vs the mixed strategy (MixedLoss) in normal distribution
Normal distribution within the range of length [64, 1 518]  OPLoss/byte  MixedLoss/byte 

X < 124  0.016  0.028 9 
X ≥ 124, Y < 60  2.41  9.18 
X ≥ 124, Y ≥ 60, X  Y ≥ 64  19.94  118.83 
X ≥ 124, Y ≥ 60, X  Y < 64  4.92  7.96 
1  HERMANN M, PENTEK T, OTTO B. Design principles for industrie 4.0 scenarios [C]//The 49th Hawaii International Conference on System Sciences. IEEE, 2016: 3928–3937 
2  ISO. Road vehicles: controller area network (CAN) (part 2): highspeed medium access unit. [S]. 2016 
3  International Electrotechnical Commission. Electric railway equipment: Train bus (Part 2): train communication network conformance testing. [S]. 2007 
4 
DECOTIGNIE J D. Ethernetbased realtime and industrial communications [J]. Proceedings of the IEEE, 2005, 93(6): 1102–1117. DOI: 10.1109/JPROC.2005.849721
DOI 
5 
BELLO L LO, STEINER W. A perspective on IEEE timesensitive networking for industrial communication and automation systems [J]. Proceedings of the IEEE, 2019, 107(6): 1094–1120. DOI: 10.1109/JPROC.2019.2905334
DOI 
6  International Group SAE. Timetriggered Ethernet. Aerospace standard: AS6802 [S]. 2011 
7  International Group SAE. TTP Communication Protocol. Aerospace standard: AS6003 [S]. 2011 
8 
STEINER W. An evaluation of SMTbased schedule synthesis for timetriggered multihop networks [C]//The 31st IEEE RealTime Systems Symposium. IEEE, 2010: 375–384. DOI: 10.1109/RTSS.2010.25
DOI 
9  IEEE. Standard for a precision clock synchronization protocol for networked measurement and control systems. IEEE std 15882002 [S]. 2002. DOI: 10.1109/IEEES 
10  IEEE. IEEE standard for local and metropolitan area networkstiming and synchronization for timesensitive applications in bridged local area networks. IEEE std 802 1AS2011 [S]. 2011 
11 
LI Z H, WAN H, DENG Y D, et al. A flattenedpriority framework for mixedcriticality systems [J]. IEEE transactions on industrial electronics, 2020, 67(11): 9862–9872. DOI: 10.1109/TIE.2019.2956406
DOI 
12 
LI Z H, WAN H, DENG Y D, et al. A resourceefficient priority scheduler for timesensitive networking switches [J]. CCF transactions on networking, 2020, 3(1): 21–34. DOI: 10.1007/s4204502000034x
DOI 
13  IEEE. IEEE standard for local and metropolitan area networksaudio video bridging (AVB) systems [S]. 2011 
14  IEEE. IEEE standard for local and metropolitan area networksvirtual bridged local area networks amendment 12: Forwarding and queuing enhancements for timesensitive streams. IEEE std 802 1Qav2009 [S]. 2010 
15  IEEE. IEEE standard for local and metropolitan area networksbridges and bridged networksamendment 25: Enhancements for scheduled traffic. IEEE Std 802.1 [S]. 2011 
16  IEEE. IEEE standard for local and metropolitan area networks: bridges and bridged networks: amendment 26: frame preemption. IEEE std 802 1Qbu2016 [S]. 2016 
No related articles found! 
Viewed  
Full text 


Abstract 

