TY - JOUR
T1 - Towards an FPGA-Accelerated programmable data path for edge-to-core communications in 5G networks
AU - Ricart-Sanchez, Ruben
AU - Malagon, Pedro
AU - Salva Garcia, Pablo
AU - Chirivella Perez, Enrique
AU - Wang, Qi
AU - Alcaraz Calero, Jose M.
PY - 2018/12/15
Y1 - 2018/12/15
N2 - 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.
AB - 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.
KW - Data path
KW - FPGA
KW - 5G
KW - Mobile edge computing
KW - Reconfigurable hardware
KW - Network architecture and design
UR - https://www.sciencedirect.com/science/article/pii/S1084804518302923?via%3Dihub
U2 - 10.1016/j.jnca.2018.09.012
DO - 10.1016/j.jnca.2018.09.012
M3 - Article
SN - 1084-8045
VL - 124
SP - 80
EP - 93
JO - Journal of Network and Computer Applications
JF - Journal of Network and Computer Applications
ER -