Internal Backpressure for Onboard Crosspoint-Buffered Switches with Port Multiplexing
Source abstract
Abstract
Onboard switching, as a core technology in satellite networks, offers robust support for the advancement of the Space–Air–Ground Integrated Network (SAGIN). The onboard switching fabric is tasked with achieving high-speed and large-capacity data exchange and ensuring service quality within the constraints of limited resources. However, the current onboard crossbar switching fabric is confronted with internal traffic congestion issues. To address this, this paper introduces an internal backpressure scheme for the crosspoint buffered switching. This scheme entails the incorporation of a buffer queue at the output port. Once an output queue reaches the maximum queue capacity due to traffic congestion, a backpressure (BP) signal is transmitted to the input end, thereby preventing the input port from sending data to the output port, alleviating crosspoint buffer overload. A validation and performance evaluation of various backpressure algorithms are conducted. The results demonstrate that the implementation of a backpressure mechanism in switching fabric can significantly reduce packet loss rate under network congestion conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Interconnection Networks and Systems · Advanced Optical Network Technologies · Satellite Communication Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Communication and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, China
State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, China
Funding
National Natural Science Foundation of China · Natural Science Basic Research Program of Shaanxi Province
References (47)
Show source-provided references
1. Space-air-ground integrated network: A survey10.1109/COMST.2018.2841996 ↗
2. SFC-based service provisioning for reconfigurable space-air-ground integrated networks10.1109/JSAC.2020.2986851 ↗
3. A traffic distribution technique to minimize packet delivery delay in multilayered satellite networks10.1109/TVT.2013.2256812 ↗
4. 5G embraces satellites for 6G ubiquitous IoT: Basic models for integrated satellite terrestrial networks10.1109/JIOT.2021.3068596 ↗
5. Zheng, L., Yi, C., Pan, W., and Liu, H. (2021, January 24–25). Combined Shared-Memory and Buffered-Crossbar Architecture for High-Bandwidth Onboard Switching Fabric. Proceedings of the 5th Asia-Pacific Workshop on Networking, Shenzhen, China.10.1145/3469393.3469672 ↗
6. A parallel route assignment algorithm for fault-tolerant clos networks in otn switches10.1109/TPDS.2018.2880782 ↗
7. Kleban, J., and Suszyńska, U. (2013, January 7–10). Static dispatching with internal backpressure scheme for SMM Clos-network switches. Proceedings of the 2013 IEEE Symposium on Computers and Communications (ISCC), Split, Croatia.10.1109/ISCC.2013.6755022 ↗
8. Design of a 640-Gbps two-stage switch fabric for satellite on-board switches10.1109/ACCESS.2020.2986300 ↗
9. Gong, L., Liu, L., Yang, S., Xu, J.J., Xie, Y., and Wang, X. (2020, January 11–14). SERENADE: A parallel iterative algorithm for crossbar scheduling in input-queued switches. Proceedings of the 2020 IEEE 21st International Conference on High Performance Switching and Routing (HPSR), Newark, NJ, USA.10.1109/HPSR48589.2020.9098995 ↗
10. Cao, D., and Mhamdi, L. (2012, January 21–23). A high-throughput scheduling algorithm for partially buffered crossbar switches. Proceedings of the 2012 Third International Conference on The Network of the Future (NOF), Tunis, Tunisia.10.1109/NOF.2012.6463989 ↗
11. Zheng, L., Wei, G., Zhang, K., and Chu, H. (2024). Traffic Classification and Packet Scheduling Strategy with Deadline Constraints for Input-Queued Switches in Time-Sensitive Networking. Electronics, 13.10.3390/electronics13030629 ↗
12. On heavy-traffic optimal scaling of c-weighted MaxWeight scheduling in input-queued switches10.1109/TAC.2021.3121367 ↗
13. High Throughput Scheduling Algorithms for Input Queued Packet Switches
14. The simulation and realization of input-buffer scheduling algorithm in satellite switching system
15. LSTM network optimization and task network construction based on heuristic algorithm
16. Performance analysis and prediction of asymmetric two-level priority polling system based on BP neural network10.1016/j.asoc.2020.106880 ↗
17. Zyla, K., Liess, M., Wild, T., and Herkersdorf, A. (2024). FlexCross: High-Speed and Flexible Packet Processing via a Crosspoint-Queued Crossbar. arXiv.10.1109/DSD64264.2024.00022 ↗
18. Predictive unicast and multicast scheduling in onboard buffered crossbar switches10.1109/LCOMM.2016.2514493 ↗
19. Architecture design and performance analysis of a novel memory system for high-bandwidth onboard switching fabric10.1016/j.comnet.2021.108367 ↗
20. Li, J., Li, H., Lai, Z., Wu, Q., Liu, Y., Zhang, Q., Li, Y., and Liu, J. (2024, January 13–17). SatGuard: Concealing Endless and Bursty Packet Losses in LEO Satellite Networks for Delay-Sensitive Web Applications. Proceedings of the ACM on Web Conference, Virtual.10.1145/3589334.3645639 ↗
21. QoS provision in hierarchical and non-hierarchical switch architectures10.1016/j.jpdc.2020.10.009 ↗
22. Inoue, T., Mano, T., and Uno, T. (2023, January 17–20). Cost-effective live expansion of three-stage switching networks without blocking or connection rearrangement. Proceedings of the IEEE INFOCOM 2023-IEEE Conference on Computer Communications, Tokyo, Japan.10.1109/INFOCOM53939.2023.10229107 ↗
23. Cascaded versus parallel architectures of two-stage optical crossbar switches with an extra set of inputs and outputs10.1049/iet-opt.2017.0096 ↗
24. Handley, M., Raiciu, C., Agache, A., Voinescu, A., Moore, A.W., Antichi, G., and Wójcik, M. (2017, January 21–25). Re-architecting datacenter networks and stacks for low latency and high performance. Proceedings of the Conference of the ACM Special Interest Group on Data Communication, Los Angeles, CA, USA.10.1145/3098822.3098825 ↗
25. Analyzing the impact of buffer capacity on crosspoint-queued switch performance10.1109/JCN.2016.000067 ↗
26. Analyzing and enhancing dynamic threshold policy of data center switches10.1109/TPDS.2017.2671429 ↗
27. Sharma, N.K., Zhao, C., Liu, M., Kannan, P.G., Kim, C., Krishnamurthy, A., and Sivaraman, A. (2020, January 25–27). Programmable calendar queues for high-speed packet scheduling. Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20), Santa Clara, CA, USA.
28. Yu, Z., Hu, C., Wu, J., Sun, X., Braverman, V., Chowdhury, M., Liu, Z., and Jin, X. (2021, January 23–27). Programmable packet scheduling with a single queue. Proceedings of the 2021 ACM SIGCOMM 2021 Conference, Virtual Event.10.1145/3452296.3472887 ↗
29. About Optimal Management of FIFO-Queues in Two-Level Memory10.1134/S1995080222070034 ↗
30. Han, K.E., Song, J., Youn, J., Kim, D.U., and Kim, K. (2020, January 4–8). Two-stage Pipelined Parallel Matching Scheduler for VOQ-based Input-buffered Switches. Proceedings of the 2020 Opto-Electronics and Communications Conference (OECC), Taipei, Taiwan.10.1109/OECC48412.2020.9273647 ↗
31. Shi, D., Han, X., Chen, W., and Li, H. (April, January 31). Overview of router architecture in high performance computing. Proceedings of the 3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023), Wuhan, China.10.1117/12.2686172 ↗
32. A load-balanced crosspoint-queued switch fabric10.1109/CC.2013.6472865 ↗
33. Flow Based Performance Guarantee Scheduling in Buffered Crossbar Switches10.1109/TCOMM.2012.082812.100625 ↗
34. Improved analytical model for performance evaluation of crosspoint-queued switch under uniform traffic10.1049/iet-net.2017.0016 ↗
35. Iterative Throughput Calculation for Crosspoint Queued Switch10.1587/transcom.E93.B.3635 ↗
36. On the combined input-crosspoint buffered switch with round-robin arbitration10.1109/TCOMM.2005.858667 ↗
37. PBC: A partially buffered crossbar packet switch10.1109/TC.2009.65 ↗
38. SQUID: A practical 100% throughput scheduler for crosspoint buffered switches10.1109/TNET.2010.2042460 ↗
39. Predictive Queue-Based Rate Control for Low Latency in Lossless Data Center Networks10.1109/TNSM.2024.3363463 ↗
40. Backpressure control with estimated queue lengths for urban network traffic10.1049/itr2.12027 ↗
41. Huang, Y., Hu, B., Wang, Y., and Su, Q. (2019, January 9–13). A Deterministic Switch with Perfect Resource Utilization and Guaranteed QoS. Proceedings of the 2019 IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA.10.1109/GLOBECOM38437.2019.9013369 ↗
42. Yazhinian, S., Navaz, K., Soruban, S., and Purushotham, N. (2023, January 17–18). RL Based Queue Selection Algorithm for Input Queued Switches: A Theoretical Approach. Proceedings of the 2023 International Conference on System, Computation, Automation and Networking (ICSCAN), Puducherry, India.10.1109/ICSCAN58655.2023.10395220 ↗
43. Performance analysis and hardware implementation of a nearly optimal buffer management scheme for high-performance shared-memory switches10.1002/dac.4365 ↗
44. Baklizi, M. (2020). Weight queue dynamic active queue management algorithm. Symmetry, 12.10.3390/sym12122077 ↗
45. Shan, D., Jiang, W., and Ren, F. (May, January 26). Absorbing micro-burst traffic by enhancing dynamic threshold policy of data center switches. Proceedings of the 2015 IEEE Conference on Computer Communications (INFOCOM), Hong Kong, China.10.1109/INFOCOM.2015.7218374 ↗
46. Traffic-aware buffer management in shared memory switches10.1109/TNET.2022.3173930 ↗
47. Dynamic queue length thresholds for shared-memory packet switches10.1109/90.664262 ↗