IP Library Granted Patent US 12695673
Granted Patent B2
US 12695673 · App. 17/900,653 · Granted Jul 28, 2026

Flow-specific network slicing

Inventors: Akhilesh S. Thyagaturu (Tempe, AZ); Francesc Guim Bernat (Barcelona, ES); Xiangyang Zhuang (Santa Clara, CA); Karthik Kumar (Chandler, AZ); Petar Torre (Feldkirchen, DE)
Assignee: Intel Corporation
H04L41/122H04L41/5025
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 12695673
App. No.
17/900,653
Granted
Jul 28, 2026
Kind
B2
Abstract

The present disclosure is generally related to edge computing technologies (ECTs), communications networking, network slicing, and in particular, to techniques and technologies for providing flow-specific network slices. In particular, the present disclosure describes mechanisms that expand existing end-to-end architectures in order to include quality of service and monitoring mechanisms that connect network slicing technologies with infrastructure and/or network data center quality of service provider domains. The described mechanisms provide data center bridging to enable network, edge computing, and cloud computing domains.

Claims (88)

1 . A method of operating a data center network (DCN) orchestrator in a DCN to provide flow-specific slicing, the method comprising:

instantiating a virtual lane in the DCN, wherein the virtual lane is to be used for a flow-specific slice for a service hosted by a service provider environment;

sending, to a network (NW) orchestrator in a communication NW, a request for network slice creation, wherein the request includes quality of service (QoS) parameters for the flow-specific slice, and the request is to cause the NW orchestrator to create a network slice instance (NSI);

receiving, from the NW orchestrator, a response based on the request for network slice creation, wherein the response includes network slice configuration information for the NSI, and the network slice configuration information includes a network slice identifier (ID) assigned to the NSI;

mapping the NSI in the NW to the instantiated virtual lane;

provisioning a service provider application operated by the service provider environment with a flow-specific slice configuration based on the network slice configuration information; and

establishing an end-to-end (e2e) connection for the flow-specific slice, wherein the e2e connection is established between a user application operated by a user device and the service provider application, and the flow-specific slice includes the instantiated virtual lane and the NSI based on the mapping:

wherein:

a network function or an application function is to insert metadata into a network packet header section or a network packet payload section:

the metadata is to be based upon packet mapping to the QoS parameters; and

the metadata is to be used by one or more layers in flow-specific packet routing.

2 . The method of claim 1 , wherein the method also comprises:

receiving network slice feedback from the NW, wherein the feedback includes metrics related to operation of the network slice in the NW;

updating the flow-specific slice configuration based on the received feedback; and

provisioning the service provider application with the updated flow-specific slice configuration, wherein the updated flow-specific slice configuration is to cause changes to QoS parameters of the flow-specific slice or cause changes to resources allocated to the flow-specific slice.

3 . The method of claim 1 , wherein the flow-specific slice belongs to a data flow, and flow-specific packets belonging to the data flow are communicated between the user application and the service provider application in the flow-specific slice, and the method also comprises:

determining whether received packets belong to the data flow based on the metadata, wherein the metadata is to be included in the received packets, and wherein, to determine whether received packets belong to the data flow, the method also comprises:

extracting the metadata from the received packets;

comparing the extracted metadata with flow-specific slice information of the flow-specific slice; and

routing the received packets to be sent over the flow-specific slice when the extracted metadata matches the flow-specific slice information.

4 . The method of claim 3 , wherein the method also comprises:

receiving packets from the service provider application that belong to the data flow; and

inserting the metadata into the network packet header section or the network packet payload section of the received packets, wherein the inserted metadata is to cause the received packets to be routed through the flow-specific slice to the user application, wherein the metadata includes one or both of a flow-specific slice ID assigned to the flow-specific slice and a network operator ID assigned to the NW.

5 . An apparatus to provide flow-specific slicing, the apparatus comprising:

processor circuitry connected to memory circuitry, wherein the processor circuitry is to execute instructions, the instructions, when executed, resulting in the apparatus being configured for performance of operations comprising:

instantiating a virtual lane in a data center network (DCN) to be used for a flow-specific slice for a service hosted by a service provider environment;

mapping a network slice instance (NSI) in a communication network (NW) to the instantiated virtual lane; and

establishing an end-to-end (e2e) connection for the flow-specific slice, wherein the e2e connection is established between a user application operated by a user device and a service provider application operated by the service provider environment, and the flow-specific slice includes the instantiated virtual lane and the NSI based on the mapping;

wherein:

a network function or an application function is to insert metadata into a network packet header section or a network packet payload section:

the metadata is to be based upon packet mapping to quality of service (Qos) parameters; and

the metadata is to be used by one or more layers in flow-specific packet routing.

6 . The apparatus of claim 5 , wherein the processor circuitry is to execute the instructions to:

send a request for network slice creation to an NW orchestrator in the NW, wherein the request is to cause the NW orchestrator to create the NSI; and

receive, from the NW orchestrator, a response based on the request for network slice creation, wherein the response includes network slice configuration information for the NSI.

7 . The apparatus of claim 6 , wherein the NW orchestrator is one or more of an RAN intelligent controller (RIC) in an Open RAN Alliance (O-RAN) framework; a Network Slice Management Function (NSMF) in a Third Generation Partnership Project (3GPP) Fifth Generation (5G) system, a 3GPP 5G Network Slice Orchestrator, a Zero-touch System Management (ZSM) function in a ZSM framework, an Open Network Automation Platform (ONAP) module in an ONAP framework, a Network Slice Controller in an IETF Network Slice framework, a Network Slice Orchestrator in an IETF Network Slice framework, and a container orchestration engine in a containerization framework.

8 . The apparatus of claim 6 , wherein the request is to cause the NW orchestrator to instruct a radio access network (RAN) to provision resources for the network slice or instruct a core network (CN) to provision resources for the network slice.

9 . The apparatus of claim 6 , wherein the request includes QoS parameters for the flow-specific slice or the NSI, wherein the QoS parameters for the flow-specific slice or the NSI are based on a service level agreement (SLA) defined for the flow-specific slice.

10 . The apparatus of claim 9 , wherein the request includes user information related to the user device, and a length of time or a set of time periods during which the flow-specific slice is to be active or inactive.

11 . The apparatus of claim 6 , wherein the response includes a network slice identifier (ID) assigned to the NSI.

12 . The apparatus of claim 6 , wherein the processor circuitry is to execute the instructions to:

provision the service provider application with a flow-specific slice configuration based on the network slice configuration information.

13 . The apparatus of claim 12 , wherein the processor circuitry is to execute the instructions to:

receive network slice feedback from the NW, wherein the feedback includes metrics related to operation of the network slice in the NW;

update the flow-specific slice configuration based on the received feedback; and

provision the service provider application with the updated flow-specific slice configuration, wherein the updated flow-specific slice configuration is to cause changes to QoS parameters of the flow-specific slice or cause changes to resources allocated to the flow-specific slice.

14 . The apparatus of claim 5 , wherein the flow-specific slice belongs to a data flow, and flow-specific packets belonging to the data flow are communicated between the user application and the service provider application in the flow-specific slice, and wherein the processor circuitry is to execute the instructions to:

determine whether received packets belong to the data flow based on the metadata, wherein the metadata is to be included in the received packets.

15 . The apparatus of claim 14 , wherein, to determine whether received packets belong to the data flow, the processor circuitry is to execute the instructions to:

extract the metadata from the received packets;

compare the extracted metadata with flow-specific slice information of the flow-specific slice; and

route the received packets to be sent over the flow-specific slice when the extracted metadata matches the flow-specific slice information.

16 . The apparatus of claim 15 , wherein a service mesh is used to route the received packets to the service provider application, and route packets processed by the service provider application to the flow-specific slice.

17 . The apparatus of claim 14 , wherein the processor circuitry is to execute the instructions to:

receive packets from the service provider application that belong to the data flow; and

insert the metadata into the network packet header section or the network packet payload section of the received packets, wherein the inserted metadata is to cause the received packets to be routed through the flow-specific slice to the user application.

18 . The apparatus of claim 17 , wherein the metadata includes one or both of a flow-specific slice ID assigned to the flow-specific slice and a network operator ID assigned to the NW.

19 . The apparatus of claim 5 , wherein the NW is a cellular network or a wireless local area network (WLAN), the DCN includes a cloud computing service or an edge computing network, and the apparatus is a service provider orchestrator in the service provider environment or a DCN orchestrator in the DCN.

20 . The apparatus of claim 19 , wherein:

the service provider orchestrator is one or more of a RIC in an O-RAN framework, an NSMF in a 3GPP 5G system, a Network Slice Orchestrator in a 3GPP 5G system, a ZSM function in a ZSM framework, an ONAP module in an ONAP framework, a Network Slice Controller in an IETF Network Slice framework, a Network Slice Orchestrator in an IETF Network Slice framework, and a container orchestration engine in a containerization framework; and

the DCN orchestrator is one or more of a RIC in an O-RAN framework; an NSMF in a 3GPP 5G system, a Network Slice Orchestrator in a 3GPP 5G system, a ZSM function in a ZSM framework, an ONAP module in an ONAP framework, a Network Slice Controller in an IETF Network Slice framework, a Network Slice Orchestrator in an IETF Network Slice framework, and a container orchestration engine in a containerization framework.

21 . One or more non-transitory computer-readable media (NTCRM) comprising instructions for flow-specific slicing, wherein execution of the instructions by one or more processors of a compute node is to result in the compute node being configured to perform operations comprising:

of instantiating a virtual lane in a data center network (DCN) to be used for a flow-specific slice for a service hosted by a service provider environment;

sending a request for network slice creation to a network (NW) orchestrator in communication NW, wherein the request is to cause the NW orchestrator to create a network slice instance (NSI);

receiving, from the NW orchestrator, a response based on the request for network slice creation, wherein the response includes network slice configuration information for the NSI;

mapping the NSI in the NW to the instantiated virtual lane;

provisioning a service provider application operated by the service provider environment with a flow-specific slice configuration based on the network slice configuration information; and

establishing an end-to-end (e2e) connection for the flow-specific slice, wherein the e2e connection is established between a user application operated by a user device and the service provider application, and the flow-specific slice includes the instantiated virtual lane and the NSI based on the mapping:

wherein:

a network function or an application function is to insert metadata into a network packet header section or a network packet payload section:

the metadata is to be based upon packet mapping to quality of service (QoS) parameters; and

the metadata is to be used by one or more layers in flow-specific packet routing.

22 . The one or more NTCRM of claim 21 , wherein the request is to cause the NW orchestrator to instruct a radio access network (RAN) to provision resources for the network slice or instruct a core network (CN) to provision resources for the network slice.

23 . The one or more NTCRM of claim 21 , wherein:

the request includes QoS parameters for the flow-specific slice or the NSI, user information related to the user device, and a length of time or a set of time periods during which the flow-specific slice is to be active or inactive, and wherein the QoS parameters for the flow-specific slice are based on a service level agreement (SLA) defined for the flow-specific slice; and

the network slice configuration information includes a network slice identifier (ID) assigned to the NSI.

24 . The one or more NTCRM of claim 21 , wherein execution of the instructions is to cause the compute node to:

receive network slice feedback from the NW, wherein the feedback includes metrics related to operation of the network slice in the NW;

update the flow-specific slice configuration based on the received feedback; and

provision the service provider application with the updated flow-specific slice configuration, wherein the updated flow-specific slice configuration is to cause changes to QoS parameters of the flow-specific slice or cause changes to resources allocated to the flow-specific slice.

25 . The one or more NTCRM of claim 21 , wherein the flow-specific slice belongs to a data flow, and flow-specific packets belonging to the data flow are communicated between the user application and the service provider application in the flow-specific slice, and wherein execution of the instructions is to cause the compute node to:

determine whether received packets belong to the data flow based on the metadata, wherein the metadata is to be included in the received packets, and wherein, to determine whether received packets belong to the data flow, the processor circuitry is to execute the instructions to:

extract the metadata from the received packets;

compare the extracted metadata with flow-specific slice information of the flow-specific slice; and

route the received packets to be sent over the flow-specific slice when the extracted metadata matches the flow-specific slice information.

26 . The one or more NTCRM of claim 25 , wherein execution of the instructions is to cause the compute node to:

receive packets from the service provider application that belong to the data flow; and

insert the metadata into the network packet header section or the network packet payload section of the received packets, wherein the inserted metadata is to cause the received packets to be routed through the flow-specific slice to the user application, wherein the metadata includes one or both of a flow-specific slice ID assigned to the flow-specific slice and a network operator ID assigned to the NW.