Adaptive and aggressive transport protocol to provide QoS in cloud data exchange over Long Fat Networks

Abstract This paper analyses the different transport protocols used in transfers over high capacity and high delay networks, commonly known as Long Fat Networks (LFNs). After analysing relevant solutions that provide reliable communications, this article presents the design and performance of the Adaptative and Aggressive Transport Protocol (AATP) for the optimisation of data transfers in a LFN Cloud Content Sharing Use Case. Cloud server farms are geographically separated and there is a need to exchange and replicate large amounts of data. By providing calculations of the status of the network and an estimation of the bandwidth of the link, the performance rate of this protocol is high. Moreover, it also includes an adaptative sending rate in the case of packet loss and, as a result of AATP aggressiveness, only the residual bandwidth is left to other protocol flows. To demonstrate AATP performance, different tests have been carried out over a Network Simulator and a Testbed on Field.

[1]  Larry L. Peterson,et al.  TCP Vegas: End to End Congestion Avoidance on a Global Internet , 1995, IEEE J. Sel. Areas Commun..

[2]  Xiaomin Zhu,et al.  cmpSCTP: An Extension of SCTP to Support Concurrent Multi-Path Transfer , 2008, 2008 IEEE International Conference on Communications.

[3]  Takamichi Mizuhara,et al.  A quality measurement tool for high-speed data transfer in long fat networks , 2016, 2016 24th International Conference on Software, Telecommunications and Computer Networks (SoftCOM).

[4]  Robert L. Grossman,et al.  UDT: UDP-based data transfer for high-speed wide area networks , 2007, Comput. Networks.

[5]  D. Nagamalai,et al.  Performance of SCTP over high speed wide area networks , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[6]  Jiannong Cao,et al.  Enabling Software Defined Networking with QoS Guarantee for Cloud Applications , 2017, 2017 IEEE 10th International Conference on Cloud Computing (CLOUD).

[7]  Janardhan R. Iyengar,et al.  Concurrent multipath transfer using SCTP multihoming over independent end-to-end paths , 2006, TNET.

[8]  Pradeeban Kathiravelu,et al.  Software-Defined Networking-Based Enhancements to Data Quality and QoS in Multi-tenanted Data Center Clouds , 2016, 2016 IEEE International Conference on Cloud Engineering Workshop (IC2EW).

[9]  Fei Xie,et al.  Towards Cost Reduction in Cloud-Based Workflow Management through Data Replication , 2017, 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD).

[10]  Biplab Sikdar,et al.  Analytic models for the latency and steady-state throughput of TCP tahoe, Reno, and SACK , 2003, TNET.

[11]  Injong Rhee,et al.  CUBIC: a new TCP-friendly high-speed TCP variant , 2008, OPSR.

[12]  Daniel Raumer,et al.  Towards a Deeper Understanding of TCP BBR Congestion Control , 2018, 2018 IFIP Networking Conference (IFIP Networking) and Workshops.

[13]  Paul D. Amer,et al.  The transport layer: tutorial and survey , 1999, CSUR.

[14]  Samar Shailendra,et al.  MPSCTP: A Simple and Efficient Multipath Algorithm for SCTP , 2011, IEEE Communications Letters.

[15]  Róbert Szabó,et al.  Dynamic adapting of Scalable TCP congestion control parameters , 2006, IEEE International Conference on Computer Systems and Applications, 2006..

[16]  Van Jacobson,et al.  TCP extensions for long-delay paths , 1988, RFC.

[17]  Roland Petrasch,et al.  Cloud storage hub: Data management for IoT and industry 4.0 applications: Towards a consistent enterprise information management system , 2016, 2016 Management and Innovation Technology International Conference (MITicon).

[18]  Chase Qishi Wu,et al.  Performance adaptive UDP for high-speed bulk data transfer over dedicated links , 2008, 2008 IEEE International Symposium on Parallel and Distributed Processing.

[19]  Van Jacobson,et al.  BBR: Congestion-Based Congestion Control , 2016, ACM Queue.

[20]  Attila Kertész.  Interoperating Cloud Services for Enhanced Data Management , 2014, 2014 IEEE Fourth International Conference on Big Data and Cloud Computing.