Towards an FPGA-Accelerated programmable data path for edge-to-core communications in 5G networks

Abstract The Fifth-Generation (5G) networks, as the emerging next generation mobile networks, are adopting softwarization and virtualization technologies as the cornerstones for the network operators to gain significant competitive advantages by reducing both capital and operational expenditure, enabling agile and flexible service creation and deployment, among others. Meanwhile, a virtualized and softwarized 5G network would suffer from downgraded system performance due to this unprecedented paradigm shift towards software-based networking. Addressing one of the top challenges in this context, this paper focuses on improving the performance of the data plane from the edge to the core network segment (backhaul) in a 5G multi-tenant network by leveraging and exploring the programmability introduced by software-based networking. A fully functional prototype has been designed and implemented utilizing a Field Programmable Gate Arrays (FPGAs) acceleration-based platform, and the prototyped system has been empirically tested and evaluated to demonstrate the superior performance enhancements. The proposed solution can effectively support 5G networks in delivering mission-critical or time-sensitive applications such as ultra-high definition video use cases as experimentally validated and shown in this paper, by fulfilling the strict Quality of Service (QoS) requirements imposed to the data plane.

[1]  George Varghese,et al.  Forwarding metamorphosis: fast programmable match-action processing in hardware for SDN , 2013, SIGCOMM.

[2]  Jose M. Alcaraz Calero,et al.  5G-UHD: Design, prototyping and empirical evaluation of adaptive Ultra-High-Definition video streaming based on scalable H.265 in virtualised 5G networks , 2017, Comput. Commun..

[3]  Hongbo Wang,et al.  Open vSwitch Vxlan performance acceleration in cloud computing data center , 2016, 2016 5th International Conference on Computer Science and Network Technology (ICCSNT).

[4]  Tasos Dagiuklas,et al.  Media-aware proxy: Application layer filtering and L3 mobility for media streaming optimization , 2015, 2015 IEEE International Conference on Communications (ICC).

[5]  Andrew W. Moore,et al.  NetFPGA SUME: Toward 100 Gbps as Research Commodity , 2014, IEEE Micro.

[6]  Douglas Comer,et al.  OSDF: A framework for software defined network programming , 2017, 2018 15th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[7]  Chun-Ying Huang,et al.  High performance traffic classification based on message size sequence and distribution , 2016, J. Netw. Comput. Appl..

[8]  Albert Y. Zomaya,et al.  Resilient virtual communication networks using multi-commodity flow based local optimal mapping , 2018, J. Netw. Comput. Appl..

[9]  Manish Jain,et al.  Effects of Interrupt Coalescence on Network Measurements , 2004, PAM.

[10]  J. M. Pierre Langlois,et al.  P4-Compatible High-Level Synthesis of Low Latency 100 Gb/s Streaming Packet Parsers in FPGAs , 2018, FPGA.

[11]  Gordon J. Brebner,et al.  400 Gb/s Programmable Packet Parsing on a Single FPGA , 2011, 2011 ACM/IEEE Seventh Symposium on Architectures for Networking and Communications Systems.

[12]  Nick McKeown,et al.  OpenFlow: enabling innovation in campus networks , 2008, CCRV.

[13]  Toktam Mahmoodi,et al.  On the Feasibility of MAC and PHY Split in Cloud RAN , 2017, 2017 IEEE Wireless Communications and Networking Conference (WCNC).

[14]  Robert Soulé,et al.  Emu: Rapid Prototyping of Networking Services , 2017, USENIX Annual Technical Conference.

[15]  Yongqiang Xiong,et al.  ClickNP: Highly Flexible and High Performance Network Processing with Reconfigurable Hardware , 2016, SIGCOMM.

[16]  Jianle Chen,et al.  Overview of SHVC: Scalable Extensions of the High Efficiency Video Coding Standard , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[17]  Jae-Hyoung Yoo,et al.  A VoLTE traffic classification method in LTE network , 2014, The 16th Asia-Pacific Network Operations and Management Symposium.

[18]  Ying Chen,et al.  Standardized Extensions of High Efficiency Video Coding (HEVC) , 2013, IEEE Journal of Selected Topics in Signal Processing.

[19]  Nick Feamster,et al.  The road to SDN: an intellectual history of programmable networks , 2014, CCRV.

[20]  Huynh Tu Dang,et al.  P4FPGA: A Rapid Prototyping Framework for P4 , 2017, SOSR.

[21]  Nor Badrul Anuar,et al.  Intrusion response systems: Foundations, design, and challenges , 2016, J. Netw. Comput. Appl..

[22]  Xiaowei Yang,et al.  High performance network virtualization with SR-IOV , 2010, HPCA - 16 2010 The Sixteenth International Symposium on High-Performance Computer Architecture.

[23]  Georgios Xilouris,et al.  An NFV-Based Video Quality Assessment Method over 5G Small Cell Networks , 2017, IEEE MultiMedia.

[24]  Martín Casado,et al.  The Design and Implementation of Open vSwitch , 2015, NSDI.

[25]  Ryan Kastner,et al.  RIFFA 2.0: A reusable integration framework for FPGA accelerators , 2013, 2013 23rd International Conference on Field programmable Logic and Applications.

[26]  Raimo Kantola,et al.  Data plane protocols and fragmentation for 5G , 2017, 2017 IEEE Conference on Standards for Communications and Networking (CSCN).

[27]  Jose M. Alcaraz Calero,et al.  Towards an open source architecture for multi-operator LTE core networks , 2016, J. Netw. Comput. Appl..

[28]  George Varghese,et al.  P4: programming protocol-independent packet processors , 2013, CCRV.

[29]  I Chih-Lin,et al.  5G RAN Architecture: C-RAN with NGFI , 2017 .