IP Library › Granted Patent US 12,744,739
Granted Patent B2
US 12,744,739 · App. 18/936,322 · Granted Sep 22, 2026

Device and method for processing traffic using switch

Inventors: Dowon Hyun (Suwon-si, KR); Seunghoon Park (Suwon-si, KR)
Assignee: Samsung Electronics Co., Ltd.
H04L47/2483G06F13/4022H04L12/4633H04L47/125
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,744,739
App. No.
18/936,322
Granted
Sep 22, 2026
Kind
B2
Abstract

A method, in a communication system, carried out by a switch server comprising a programmable switch and one or more field programmable gate arrays (FPGAs) is provided. The method includes receiving information related to a flow table from an offloading server, receiving data packets, identifying a FPGA corresponding to the data packets, identifying whether the data packets match a flow entry of a flow table of the FPGA, in case that the data packets match the flow entry of the flow table, processing the data packets based on the flow entry and transmitting the processed data packet, and in case that the data packets do not match the entry of the flow table, providing the data packets to the offloading server.

Claims (68)

1 . A method performed by a switch server including a programmable switch and one or more field programmable gate arrays (FPGAs) in a communication system, the method comprising:

receiving information on a flow table from an offloading server;

receiving data packets;

identifying an FPGA corresponding to the data packets;

identifying whether the data packets match a flow entry of the flow table of the FPGA;

if the data packets match the flow entry of the flow table, processing the data packets based on the flow entry and transmitting the processed data packets; and

if the data packets do not match the flow entry of the flow table, providing the data packets to the offloading server.

2 . The method of claim 1 ,

wherein the flow table includes an entry identifier (ID), a hash key, an action, action data, and usage, and

wherein the entry ID is associated with a user equipment ID and a packet detection rule (PDR).

3 . The method of claim 1 , wherein the information on the flow table includes an entry identifier (ID), a tunnel endpoint identifier (TEID), and a differentiated service code point (DSCP) value.

4 . The method of claim 1 ,

wherein, in case that the data packets are downlink packets, the processing of the data packets includes general packet radio service (GPRS) tunnelling protocol (GTP) capsulation and differentiated service code point (DSCP) marking, and

wherein, in case that the data packets are uplink packets, the processing of the data packets includes GTP decapsulation and DSCP marking.

5 . The method of claim 1 ,

wherein the information on the flow table is received from the offloading server in case that a header of a previous packet has a uniform resource indicator (URL) in a specified range, and

wherein the information on the flow table includes destination internet protocol (IP) address information of the URL in the specified range.

6 . The method of claim 1 , wherein the switch server and the offloading server are configured to perform operations of a user plane function (UPF).

7 . The method of claim 6 ,

wherein the offloading server is configured to process user plane data packets and perform processing of control signaling related to session management function (SMF), and

wherein the switch server is configured to process user plane data packets.

8 . A switch server in a communication system, comprising:

a processor;

a programmable switch; and

one or more field programmable gate arrays (FPGAs), wherein the programmable switch is configured to:

receive information on a flow table from an offloading server,

receive data packets,

identify an FPGA corresponding to the data packets,

identify whether the data packets are matched to a flow entry of the flow table of the FPGA or not,

if the data packets are matched to the flow entry of the flow table, process the data packets based on the flow entry and transmit the processed data packets, and

if the data packets are not matched to the flow entry of the flow table, provide the data packets to the offloading server.

9 . The switch server of claim 8 ,

wherein the flow table includes an entry identifier (ID), a hash key, an action, action data, and usage, and

wherein the entry ID is associated with a user equipment ID and a packet detection rule (PDR).

10 . The switch server of claim 8 , wherein the information on the flow table includes an entry identifier (ID), a tunnel endpoint identifier (TEID), and a differentiated service code point (DSCP) value.

11 . The switch server of claim 8 ,

wherein, in case that the data packets are downlink packets, the processing of the data packets includes general packet radio service (GPRS) tunnelling protocol (GTP) capsulation and differentiated service code point (DSCP) marking, and

wherein, in case that the data packets are uplink packets, the processing of the data packets includes GTP decapsulation and DSCP marking.

12 . The switch server of claim 8 ,

wherein the information on the flow table is received from the offloading server in case that a header of a previous packet has a uniform resource indicator (URL) in a specified range, and

wherein the information on the flow table includes destination internet protocol (IP) address information of the URL in the specified range.

13 . The switch server of claim 8 , wherein the switch server and the offloading server are configured to perform operations of a user plane function (UPF).

14 . The switch server of claim 13 ,

wherein the offloading server is configured to process user plane data packets and perform processing of control signaling related to session management function (SMF), and

wherein the switch server is configured to process user plane data packets.

15 . An offloading server in a communication system, the offloading server comprising:

at least one transceiver;

memory storing one or more computer programs; and

one or more processors communicatively coupled to the at least one transceiver and the memory, wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the offloading server to:

receive, from a switch server including a programmable switch and one or more field programmable gate arrays (FPGAs), data packets,

process the data packets,

determine whether to generate a flow table for the data packets,

if the flow table for the data packets is generated, provide information on the flow table and the processed packets to the switch server, and

if the flow table for the data packets is not generated, provide the processed packets to the switch server without the information on the flow table.

16 . The offloading server of claim 15 ,

wherein the flow table includes an entry identifier (ID), a hash key, an action, action data, and usage, and

wherein the entry ID is determined based on a user equipment ID and a packet detection rule (PDR).

17 . The offloading server of claim 15 , wherein the information on the flow table includes an entry identifier (ID), a tunnel endpoint identifier (TEID), and a differentiated service code point (DSCP) value.

18 . The offloading server of claim 15 ,

wherein, in case that the data packets are downlink packets, the processing of the data packets includes general packet radio service (GPRS) tunnelling protocol (GTP) capsulation and differentiated service code point (DSCP) marking, and

wherein, in case that the data packets are uplink packets, the processing of the data packets includes GTP decapsulation and DSCP marking.

19 . The offloading server of claim 15 ,

wherein the information on the flow table is transmitted to the switch server in case that a header of a previous packet has a uniform resource indicator (URL) in a specified range, and

wherein the information on the flow table includes destination internet protocol (IP) address information of the URL in the specified range.

20 . The offloading server of claim 15 ,

wherein the switch server and the offloading server are configured to perform operations of a user plane function (UPF),

wherein the offloading server is configured to process user plane data packets and perform processing of control signaling related to session management function (SMF), and

wherein the switch server is configured to process user plane data packets.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 4, 2024
From: HYUN, DOWON; PARK, SEUNGHOON
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 069127/0274 →
Priority Claims (1)
KR 10-2022-0056916 · May 9, 2022 · national
Continuity (2)
Continuation PCTKR2023003537 · Mar 16, 2023
Related Publication 20250062996A1 · Feb 20, 2025
References Cited (21)
US 9036636B1 · Sherwood · 2015 [cited by examiner]
US 9124526B2 · Ooishi · 2015 [cited by applicant]
US 9973400B2 · Su · 2018 [cited by examiner]
US 10382346B2 · Murugesan et al. · 2019 [cited by applicant]
US 10841838B2 · Zhang et al. · 2020 [cited by applicant]
US 11134416B2 · Kotecha et al. · 2021 [cited by applicant]
US 11431621B2 · Bagwell et al. · 2022 [cited by applicant]
US 20200371828A1 · Chiou et al. · 2020 [cited by applicant]
US 20210029586A1 · Zhu et al. · 2021 [cited by applicant]
US 20210385716A1 · Bae et al. · 2021 [cited by applicant]
US 20220021605A1 · Bagwell et al. · 2022 [cited by applicant]
CN 109962832A · 2019 [cited by examiner]
CN 113068175A · 2021 [cited by applicant]
CN 113852992A · 2021 [cited by applicant]
KR 1020130052031A · 2013 [cited by applicant]
KR 102261172B1 · 2021 [cited by applicant]
Translation of CN-109962832-A (Year: 2019). [cited by examiner]
Accton Technology Corporation, Accton announces the CSP-7551 server-switch appliance with dual 2nd Gen Intel Xeon Scalable processors, Intel Tofino programmable Ethernet switch ASIC, and up to four Intel Stratix 10MX FP… [cited by applicant]
Cho et al., SMORE: Software-defined networking mobile offloading architecture, All Things Cellular '14: Proceedings of the 4th workshop on All things cellular: operations, applications, & challenges, Aug. 2014. [cited by applicant]
Shen et al., A Programmable and FPGA-accelerated GTP Offloading Engine for Mobile Edge Computing in 5G Networks, IEEE INFOCOM 2019—IEEE Conference on Computer Communications Workshops, Sep. 2019. [cited by applicant]
International Search Report and Written Opinion dated Jun. 27, 2023, issued in International Application No. PCT/KR2023/003537. [cited by applicant]