# US 10,122,639 B2 · Systems and methods for managing a network

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

- Number: US 10,122,639 B2
- Document ID: US10122639B2
- Status: Granted
- Kind: B2
- Application number: 14/066,887
- Filed: 2013-10-30
- Published: 2015-04-30
- Granted: 2018-11-06
- Earliest claimed: 2013-10-30
- Assignees: Comcast Cable Communications, LLC
- Applicants: Comcast Cable Communications, LLC
- Inventors: Mehmet Toy
- Web page: https://patentgrep.com/patent/US10122639B2

## CPC

- H04L 47/283: in response to processing delays, e.g. caused by jitter or round trip time [RTT]
- H04L 12/4633: {Interconnection of networks using encapsulation techniques, e.g. tunneling}
- H04L 43/0852: Delays
- H04L 43/16: Threshold monitoring
- H04L 47/11: Identifying congestion
- H04L 47/263: Rate modification at the source after receiving feedback
- H04L 43/0858: {One way delays}
- H04L 43/0864: Round trip delays
- Y02D 30/50: in wire-line communication networks, e.g. low power modes or reduced link rate
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

Systems and methods for managing congestion in a network are disclosed. One method can comprise receiving a first congestion indicator at a network point and modifying a data transfer rate to an effective bandwidth in response to receiving the first congestion indicator. If a second congestion indicator is received within a predetermined time period, the data transfer rate can be reduced to a factor of a committed information rate. If a second congestion indicator is not received with the time period, the data transfer rate can be increased to a target transfer rate.

## Claims

### Claim 1

A method comprising:
receiving, by a network device, based on a sliding window delay measurement associated with a service flow, a first indicator of network congestion, wherein the sliding window delay measurement comprises a plurality of delay measurements, wherein at least one delay measurement of the plurality of delay measurements is associated with a randomly selected network point of a plurality of network points;
in response to the receiving the first indicator,
determining, based on a peak rate (PR) value and a maximum burst size (MBS) value associated with a first network point of the plurality of network points, an effective bandwidth for the service flow,
reducing a data transfer rate associated with the service flow to the effective bandwidth, and
determining, based on a factor of a roundtrip time between a source point and a destination point, a time period;
if a second indicator of network congestion is received within the time period, reducing the data transfer rate to a factor of a committed information rate, wherein the second indicator is associated with another sliding window delay measurement; and
if a second indicator of network congestion is not received within the time period, increasing the data transfer rate to a target transfer rate.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first network point is associated with a multipoint-to-multipoint network, a point-to-multipoint network, or a point-to-point network.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first indicator represents one or more of a one-way point-to-point delay measurement, or a round trip point-to-point delay measurement.

### Claim 4 (depends on 1)

The method of claim 1, wherein the first indicator comprises a discard eligible (DE) bit.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first network point comprises one of more of a user interface, a boundary of a domain associated with a packet-based network, a boundary of a domain associated with a label switched path (LSP) in a multiprotocol label switching (MPLS) network.

### Claim 6 (depends on 1)

The method of claim 1, wherein the target transfer rate is greater than the effective bandwidth.

### Claim 7 (depends on 1)

The method of claim 1, wherein, when the service flow is associated with a no loss agreement, the effective bandwidth is based on a delay variation between a pair of packets of the service flow traveling between the first network point and a second network point of the plurality of network points.

### Claim 8 (depends on 1)

The method of claim 1, wherein, when the service flow is associated with a loss agreement, the effective bandwidth is based on a frame loss ratio of the service flow traveling between the first network point and a second network point of the plurality of network points.

### Claim 9

A method comprising:
receiving, by a network device, based on a sliding window delay measurement associated with a service flow, first delay information, wherein the first delay information is associated with a sliding window delay measurement comprises a plurality of delay measurements, wherein at least one delay measurement of the plurality of delay measurements is associated with a randomly selected network point of a plurality of network points;
determining that the first delay information exceeds a threshold;
executing, based on the first delay information exceeding the threshold, a first congestion control process associated with the plurality of network points, wherein executing the first congestion control process comprises,
determining, based on a peak rate (PR) value and a maximum burst size (MBS) value associated with a connection between the plurality of network points, an effective bandwidth for the service flow, and
modifying, based upon the effective bandwidth, one or more of an ingress data rate associated with the service flow, or an egress data rate associated with the service flow;
determining, based on a factor of a roundtrip time between a source point and a destination point, a time period;
if second delay information is received within the time period, executing, based on another sliding window delay measurement associated with the service flow, a second congestion control process associated with the plurality of network points; and
if second delay information is not received within the time period, executing a third congestion control process associated with the plurality of network points.

### Claim 10 (depends on 9)

The method of claim 9, wherein the first delay information and the second delay information each represent one or more of a one-way point-to-point delay measurement or a round trip point-to-point delay measurement.

### Claim 11 (depends on 9)

The method of claim 9, wherein the first congestion control process, the second congestion control process, and the third congestion control process are different from each other.

### Claim 12 (depends on 9)

The method of claim 9, wherein executing the second congestion control process comprises reducing, based upon a committed information rate, one or more of the ingress data rate or the egress data rate.

### Claim 13 (depends on 9)

The method of claim 9, wherein executing the third congestion control process comprises increasing, based upon a congestion control algorithm, one or more of the ingress data rate or the egress data rate.

### Claim 14 (depends on 9)

The method of claim 9, wherein, when the service flow is associated with a no loss agreement, the effective bandwidth is based on a delay variation traveling between a pair of packets of the service flow between the plurality of network points.

### Claim 15

A method comprising:
receiving, by a network device, based on a sliding window delay measurement associated with a service flow, a first indication of network performance, wherein the sliding window delay measurement comprises a plurality of delay measurements, wherein at least one delay measurement of the plurality of delay measurements is associated with a randomly selected network point of a plurality of network points;
determining, based on a peak rate (PR) value and a maximum burst size (MBS) value, an effective bandwidth for the service flow;
causing, based on the effective bandwidth, a first modification of one or more of an ingress data rate associated with the service flow or an egress data rate associated with the service flow;
determining, based on a factor of a roundtrip time between a source point and a destination point, a time period; and
causing, in response to one or more of an expiration of the time period or receiving a second indication of network performance, a second modification, based on the effective bandwidth, of one or more of the ingress data rate or the egress data rate.

### Claim 16 (depends on 15)

The method of claim 15, wherein the first indication and the second indication each represent one or more of congestion, port level delay, connection level delay, or class of service level delay, wherein the second indication is based on another sliding window delay measurement.

### Claim 17 (depends on 15)

The method of claim 15, wherein the first indication and the second indication each represent one or more of a one-way point-to-point delay measurement or a round trip point-to-point delay measurement.

### Claim 18 (depends on 15)

The method of claim 15, wherein causing one or more of the first modification or the second modification of one or more of the ingress data rate or the egress data rate comprises reducing, based upon a congestion control algorithm, one or more of the ingress data rate or the egress data rate.