TY - JOUR
T1 - L26GC
T2 - Evolving the Low-Latency Core for Future Cellular Networks
AU - Qi, Shixiong
AU - Ramakrishnan, K. K.
AU - Chen, Jyh Cheng
N1 - Publisher Copyright:
© 1997-2012 IEEE.
PY - 2024/3/1
Y1 - 2024/3/1
N2 - With the deployment of higher speed radio (e.g., millimeter-wave) channels, emerging cellular use cases will place a heightened emphasis on performance of the cellular core (we call it "6GC"). Based on our earlier work on designing a low-latency, high-throughput 5G cellular core, we outline a design for L26GC, a 6G cellular core preserving the current trend to disaggregate core network functions (NFs) while ensuring low-latency communication between them. L26GC leverages shared memory processing for low-latency control plane communication, providing an equivalent service to the 3rd Generation Partnership Project service-based interface and supports information exchange between NFs for each user session. L26GC offloads data plane processing to Smart Network Interface Cards, exploiting scalable, flow-level packet classifiers to expedite forwarding-rule lookups when dealing with multiple user sessions. Overall, L26GC optimizes the cellular core, improving latency, scalability, and the user’s quality of experience.
AB - With the deployment of higher speed radio (e.g., millimeter-wave) channels, emerging cellular use cases will place a heightened emphasis on performance of the cellular core (we call it "6GC"). Based on our earlier work on designing a low-latency, high-throughput 5G cellular core, we outline a design for L26GC, a 6G cellular core preserving the current trend to disaggregate core network functions (NFs) while ensuring low-latency communication between them. L26GC leverages shared memory processing for low-latency control plane communication, providing an equivalent service to the 3rd Generation Partnership Project service-based interface and supports information exchange between NFs for each user session. L26GC offloads data plane processing to Smart Network Interface Cards, exploiting scalable, flow-level packet classifiers to expedite forwarding-rule lookups when dealing with multiple user sessions. Overall, L26GC optimizes the cellular core, improving latency, scalability, and the user’s quality of experience.
UR - http://www.scopus.com/inward/record.url?scp=85188520334&partnerID=8YFLogxK
U2 - 10.1109/MIC.2024.3376655
DO - 10.1109/MIC.2024.3376655
M3 - Article
AN - SCOPUS:85188520334
SN - 1089-7801
VL - 28
SP - 29
EP - 36
JO - IEEE Internet Computing
JF - IEEE Internet Computing
IS - 2
ER -