# US 2020/0396135 A1 · Automatic prediction of behavior and topology of a network using limited information

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

- Number: US 2020/0396135 A1
- Document ID: US20200396135A1
- Status: Published application
- Kind: A1
- Application number: 16/443,121
- Filed: 2019-06-17
- Published: 2020-12-17
- Earliest claimed: 2019-06-17
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: LIANG MA; MUDHAKAR SRIVATSA
- Web page: https://patentgrep.com/patent/US20200396135A1

## CPC

- H04L 41/12: Discovery or management of network topologies
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 41/16: using machine learning or artificial intelligence
- H04L 45/02: Topology update or discovery
- H04L 45/08: {Learning-based routing, e.g. using neural networks or artificial intelligence}
- H04L 45/124: {using a combination of metrics}
- H04L 45/70: {Routing based on monitoring results}
- H04L 43/0852: Delays
- H04L 43/10: Active monitoring, e.g. heartbeat, ping or trace-route
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure provides a method for automatically predicting a topology of a network comprising a plurality of nodes. The method includes: selecting a path performance metric among a plurality of available metrics; obtaining path performance metrics of selected node pairs among the plurality of nodes; using the obtained path performance metrics to train a machine-learning model to predict the path performance metric for the remaining node pairs; and using the obtained and predicted path performance metrics to construct a topology of the network.

## Claims

### Claim 1

A computer-implemented method for automatically predicting a topology of a network comprising a plurality of nodes, the method comprising:
selecting, by a processor, a path performance metric among a plurality of available metrics;
obtaining, by the processor, path performance metrics of selected node pairs among the plurality of nodes;
using, by the processor, the obtained path performance metrics to train a machine-learning model to predict the path performance metric for the remaining node pairs; and
using, by the processor, the obtained and predicted path performance metrics to construct a topology of the network.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the selected node pairs number less than the remaining node pairs.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the machine-learning model is a neural network including a plurality of layers, where each layer includes a plurality of neurons corresponding to an estimated number of links within the network.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein the estimated number of links is twice the number of nodes within the plurality.

### Claim 5 (depends on 3)

The computer-implemented method of claim 3, wherein each neuron is associated with a corresponding one of the selected node pairs, and when the neural network is operated on input data indicating a given remaining node pair of the remaining node pairs, a given neuron among the neurons indicates a probability that a link associated with the given neuron is present within a path between nodes of the given remaining node pair.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the path performance metric indicates a delay between two nodes of one of the selected node pairs.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the path performance metric indicates a congestion level associated with a link between two nodes of one of the selected node pairs.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the processor obtains the path performance metrics by performing on operating system command to send a message to each node of the selected node pairs.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the machine-learning model is trained using the obtained path performance metrics and at least one additional path performance metric derived from the obtained path performance metrics.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the topology is constructed by comparing each of the obtained and predicted path performance metrics with a predefined range.

### Claim 11 (depends on 19)

The computer-implemented method of claim 19, wherein the topology includes a link between a node pair associated with a given path performance metric among the obtained and predicted performance metrics when the given path performance metric is within the predefined range and excludes the link when the given path performance metric is outside the predefined range.

### Claim 12

A system for automatically predicting a topology of a network comprising a plurality of nodes, the system comprising:
a memory storing a computer program; and
a processor configured to execute the computer program,
wherein the computer program selects a path performance metric among a plurality of available metrics, obtains path performance metrics of selected node pairs among the plurality of nodes, uses the obtained path performance metrics to train a machine-learning model to predict the path performance metric for the remaining node pairs, and uses the obtained and predicted path performance metrics to construct a topology of the network.

### Claim 13 (depends on 12)

The system of claim 12, wherein the selected node pairs number less than the remaining node pairs.

### Claim 14 (depends on 12)

The system of claim 12, the machine-learning model is a neural network including a plurality of layers, where each layer includes a plurality of neurons corresponding to an estimated number of links within the network.

### Claim 15 (depends on 14)

The system of claim 14, wherein each neuron is associated with a corresponding one of the selected node pairs, and when the neural network is operated on input data indicating a given remaining node pair of the remaining node pairs, a given neuron among the neurons indicates a probability that a link associated with the given neuron is present within a path between nodes of the given remaining node pair.

### Claim 16 (depends on 12)

The system of claim 12, wherein the machine-learning model is trained using the obtained path performance metrics and at least one additional path performance metric derived from the obtained path performance metrics.

### Claim 17 (depends on 12)

The system of claim 12, wherein the topology is constructed by comparing each of the obtained and predicted path performance metrics with a predefined range.

### Claim 18 (depends on 17)

The system of claim 17, wherein the topology includes a link between a node pair associated with a given path performance metric among the obtained and predicted performance metrics when the given path performance metric is within the predefined range and excludes the link when the given path performance metric is outside the predefined range.

### Claim 19

A computer program product for automatically predicting a topology of a network comprising a plurality of nodes, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by a processor, to perform method steps comprising instructions for:
selecting a path performance metric among a plurality of available metrics;
obtaining path performance metrics of selected node pairs among the plurality of nodes;
using the obtained path performance metrics to train a machine-learning model to predict the path performance metric for the remaining node pairs; and
using the obtained and predicted path performance metrics to construct a topology of the network.

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein the selected node pairs number less than the remaining node pairs.
