# US 2019/0294996 A1 · Method and system to dynamically enable sdn network learning capability in a user-defined cloud network

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0294996 A1
- Document ID: US20190294996A1
- Status: Published application
- Kind: A1
- Application number: 16/436,103
- Filed: 2019-06-10
- Published: 2019-09-26
- Earliest claimed: 2016-03-03
- Assignees: AT&T Intellectual Property I, L.P.
- Applicants: AT&T Intellectual Property I, L.P.
- Inventors: Zhi Cui; Sangar Dowlatkhah
- Web page: https://patentgrep.com/patent/US20190294996A1

## CPC

- G06N 20/00: Machine learning
- H04L 41/0896: Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities (flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76)
- H04L 41/40: using virtualisation of network functions or resources, e.g. SDN or NFV entities
- H04L 43/0876: Network utilisation, e.g. volume of load or congestion level
- H04L 43/20: the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV
- H04W 24/08: Testing, {supervising or monitoring} using real traffic
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A software defined network controller for controlling a radio access network has a leaning capability by which usage characteristics are learned for each service provided by the radio access network. For example, bandwidth data, connection duration data and latency data may be used to learn usage characteristics for each radio access network service. The learned usage characteristics are then used in allocating network resources in response to a service request.

## Claims

### Claim 1

A software defined network controller, comprising:
a database store comprising bandwidth usage data, connection duration usage data and latency usage data, wherein each of the bandwidth usage data, connection duration usage data and latency usage data is collected on a per-flow basis for each of a plurality of radio access network services provided on a radio access network;
a processor configured to perform an intelligent data collection function including collecting the bandwidth usage data, connection duration usage data and latency usage data on a per-flow basis for each of the plurality of radio access network services, and storing the bandwidth usage data, connection duration usage data and latency usage data in the database store; and
a network resource allocation engine comprising an interface with the database store, a processor and at least one memory device storing computer readable instructions that, when executed by the processor, cause the processor to execute operations comprising:
receiving, from the intelligent data collection function, the bandwidth usage data, connection duration usage data and latency usage data;
for each of the plurality of radio access network services, applying to the bandwidth usage data, connection duration usage data and latency usage data, a learning algorithm to determine, for each of the radio access network services individually, learned network characteristics of the radio access network service, including network usage changes resulting from previous resource allocations;
recognizing a service need for a requested radio access network service of radio access network services, the recognizing being based on the learned network characteristics of the requested radio access network service; and
allocating resources for the requested radio access network service based on the learned network characteristics of the requested radio access network service and based on bandwidth and latency requirements computed from service requirements of the requested radio access network service.

### Claim 2 (depends on 1)

The software defined network controller of claim 1, wherein the operations further comprise:
receiving the service requirements from a control, orchestration management and policy server.

### Claim 3 (depends on 1)

The software defined network controller of claim 1, wherein the radio access network services comprise at least voice communications services, video content delivery services and video communications services.

### Claim 4 (depends on 1)

The software defined network controller of claim 1, wherein the bandwidth usage data, connection duration usage data and latency usage data is collected via a backhaul network from user devices of the radio access network.

### Claim 5 (depends on 1)

The software defined network controller of claim 1, wherein the bandwidth usage data, connection duration usage data and latency usage data is collected independently of a backhaul network of the radio access network.

### Claim 6 (depends on 1)

The software defined network controller of claim 1, wherein the learned network characteristics of the radio access network service further include current trends in streaming and traffic patterns, bandwidth and latency requirements and preferred codec.

### Claim 7 (depends on 1)

The software defined network controller of claim 1, wherein the allocating resources comprises allocating bandwidth per service of the radio access network.

### Claim 8

A method for allocating resources in a radio access network using a software defined network controller, comprising:
collecting bandwidth usage data, connection duration usage data and latency usage data for each of a plurality of radio access network services provided on the radio access network, the bandwidth usage data, connection duration usage data and latency usage data being collected on a per-flow basis for each of the plurality of radio access network services;
computing bandwidth and latency requirements from service requirements for a requested radio access network service of the plurality of radio access network services;
for each of the plurality of radio access network services, applying to the bandwidth usage data, connection duration usage data and latency usage data, a learning algorithm to determine, for each of the radio access network services individually, learned network characteristics of the radio access network service, including network usage changes resulting from previous resource allocations;
recognizing a service need for the requested radio access network service, the recognizing being based on the learned network characteristics of the requested radio access network service; and
allocating resources for the requested radio access network service based on the learned network characteristics of the requested radio access network service and based on the bandwidth and latency requirements.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
receiving the service requirements from a control, orchestration management and policy server.

### Claim 10 (depends on 8)

The method of claim 8, wherein the radio access network services comprise at least voice communications services, video content delivery services and video communications services.

### Claim 11 (depends on 8)

The method of claim 8, wherein the bandwidth usage data, connection duration usage data and latency usage data is collected via a backhaul network from user devices of the radio access network.

### Claim 12 (depends on 8)

The method of claim 8, wherein the bandwidth usage data, connection duration usage data and latency usage data is collected independently of a backhaul network of the radio access network.

### Claim 13 (depends on 8)

The method of claim 8, wherein the learned network characteristics of the radio access network service further include current trends in streaming and traffic patterns, bandwidth and latency requirements and preferred codec.

### Claim 14 (depends on 8)

The method of claim 8, wherein the allocating resources comprises allocating bandwidth per service of the radio access network.

### Claim 15

A computer-readable storage device having stored thereon computer readable instructions for allocating resources in a radio access network using a software defined network controller, wherein execution of the computer readable instructions by a processor causes the processor to perform operations comprising:
collecting bandwidth usage data, connection duration usage data and latency usage data for each of a plurality of radio access network services provided on the radio access network, the bandwidth usage data, connection duration usage data and latency usage data being collected on a per-flow basis for each of the plurality of radio access network services;
receiving service requirements from a control, orchestration management and policy server;
computing bandwidth and latency requirements from service requirements for a requested radio access network service of the plurality of radio access network services;
for each of the plurality of radio access network services, applying to the bandwidth usage data, connection duration usage data and latency usage data, a learning algorithm to determine, for each of the radio access network services individually, learned network characteristics of the radio access network service, including network usage changes resulting from previous resource allocations;
recognizing a service need for the requested radio access network service, the recognizing being based on the learned network characteristics of the requested radio access network service; and
allocating resources for the requested radio access network service based on the learned network characteristics of the requested radio access network service and based on the bandwidth and latency requirements.

### Claim 16 (depends on 15)

The computer-readable storage device of claim 15, wherein the radio access network services comprise at least voice communications services, video content delivery services and video communications services.

### Claim 17 (depends on 15)

The computer-readable storage device of claim 15, wherein the bandwidth usage data, connection duration usage data and latency usage data is collected via a backhaul network from user devices of the radio access network.

### Claim 18 (depends on 15)

The computer-readable storage device of claim 15, wherein the bandwidth usage data, connection duration usage data and latency usage data is collected independently of a backhaul network of the radio access network.

### Claim 19 (depends on 15)

The computer-readable storage device of claim 15, wherein the learned network characteristics of the radio access network service further include current trends in streaming and traffic patterns, bandwidth and latency requirements and preferred codec.

### Claim 20 (depends on 15)

The computer-readable storage device of claim 15, wherein the allocating resources comprises allocating bandwidth per service of the radio access network.
