# US 2021/0334668 A1 · Locality-aware compressor-decompressor for keeping prediction models up-to-date in resource constrained networks

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

- Number: US 2021/0334668 A1
- Document ID: US20210334668A1
- Status: Published application
- Kind: A1
- Application number: 16/859,746
- Filed: 2020-04-27
- Published: 2021-10-28
- Earliest claimed: 2020-04-27
- Assignees: EMC IP Holding Company LLC
- Applicants: EMC IP Holding Company LLC
- Inventors: Paulo Abelha Ferreira; Adriana Bechara Prado; Pablo Nascimento da Silva; Tiago Salviano Calmon
- Web page: https://patentgrep.com/patent/US20210334668A1

## CPC

- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 20/00: Machine learning
- H04W 52/265: {taking into account the quality of service QoS}
- H04W 72/542: using measured or perceived quality
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A global prediction manager for generating predictions using data from data zones includes storage for storing a model repository comprising a global model set and a prediction manager. The prediction manager obtains a local model set from a data zone of the data zones indicating that the global model set is unacceptable; makes a determination that the local model set is acceptable; in response to the determination: distributes the local model set to at least one second data zone of the data zones; obtains compressed telemetry data, that was compressed using the local model set, from the data zone and the at least one second data zone; and generates a global prediction regarding a future operating condition of the data zones using: the compressed local telemetry data and the local model set.

## Claims

### Claim 1

A global prediction manager for generating predictions using data from data zones, comprising:
storage for storing a model repository comprising a global model set; and
a prediction manager programmed to:
obtain a local model set from a data zone of the data zones indicating that the global model set is unacceptable;
make a determination that the local model set is acceptable;
in response to the determination:
distribute the local model set to at least one second data zone of the data zones;
obtain compressed telemetry data, that was compressed using the local model set, from the data zone and the at least one second data zone; and
generate a global prediction regarding a future operating condition of the data zones using:
the compressed local telemetry data, and
the local model set.

### Claim 2 (depends on 1)

The global prediction manager of claim 1, wherein the prediction manager is further programmed to:
modify an operation of the data zones based on the global prediction.

### Claim 3 (depends on 1)

The global prediction manager of claim 1, wherein the local model set comprises:
a local prediction model trained on only local telemetry data of the data zone,
wherein the local prediction model is adapted to generate predictions based on telemetry data obtained from any number of sources.

### Claim 4 (depends on 3)

The global prediction manager of claim 3, wherein the global model set comprises:
a global prediction model trained on both local telemetry data of the data zone and second local telemetry data of the at least one second data zone,
wherein the global prediction model is adapted to generate second predictions based on the telemetry data obtained from any number of sources.

### Claim 5 (depends on 1)

The global prediction manager of claim 1, wherein making the determination that the local model set is acceptable comprises:
obtaining second local telemetry data from the at least one second data zone;
obtaining an operating condition associated with the second local telemetry data;
obtaining a local prediction of the operating condition using:
the local model set, and
the second local telemetry data;
obtaining compressed second local telemetry data using:
the local model set, and
the second local telemetry data;
obtaining decompressed second local telemetry data using the compressed second local telemetry data;
making the determination by analyzing:
the second local telemetry data,
the decompressed local telemetry data,
the operating condition, and
the local prediction of the operating prediction.

### Claim 6 (depends on 1)

The global prediction manager of claim 1, wherein the local model set comprises:
a local compression model trained on only local telemetry data of the data zone,
wherein the local compression model is adapted to generated compressed telemetry data based on telemetry data obtained from any number of sources.

### Claim 7 (depends on 6)

The global prediction manager of claim 6, wherein the global model set comprises:
a global compression model based on local telemetry data of the data zone and second local telemetry data of the at least one second data zone,
wherein the global compression model is adapted to generated second compressed telemetry data based on the telemetry data obtained from any number of sources.

### Claim 8

A method for generating predictions using data from data zones, comprising:
obtaining a local model set from a data zone of the data zones indicating that a global model set using to generate the predictions is unacceptable;
making a determination that the local model set is acceptable;
in response to the determination:
distributing the local model set to at least one second data zone of the data zones;
obtaining compressed telemetry data, that was compressed using the local model set, from the data zone and the at least one second data zone; and
generating a global prediction regarding a future operating condition of the data zones using:
the compressed local telemetry data, and
the local model set.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
modifying an operation of the data zones based on the global prediction.

### Claim 10 (depends on 8)

The method of claim 8, wherein the local model set comprises:
a local prediction model trained on only local telemetry data of the data zone,
wherein the local prediction model is adapted to generate predictions based on telemetry data obtained from any number of sources.

### Claim 11 (depends on 10)

The method of claim 10, wherein the global model set comprises:
a global prediction model trained on both local telemetry data of the data zone and second local telemetry data of the at least one second data zone,
wherein the global prediction model is adapted to generate second predictions based on the telemetry data obtained from any number of sources.

### Claim 12 (depends on 8)

The method of claim 8, wherein making the determination that the local model set is acceptable comprises:
obtaining second local telemetry data from the at least one second data zone;
obtaining an operating condition associated with the second local telemetry data;
obtaining a local prediction of the operating condition using:
the local model set, and
the second local telemetry data;
obtaining compressed second local telemetry data using:
the local model set, and
the second local telemetry data;
obtaining decompressed second local telemetry data using the compressed second local telemetry data;
making the determination by analyzing:
the second local telemetry data,
the decompressed local telemetry data,
the operating condition, and
the local prediction of the operating prediction.

### Claim 13 (depends on 8)

The method of claim 8, wherein the local model set comprises:
a local compression model trained on only local telemetry data of the data zone,
wherein the local compression model is adapted to generated compressed telemetry data based on telemetry data obtained from any number of sources.

### Claim 14 (depends on 13)

The method of claim 13, wherein the global model set comprises:
a global compression model based on local telemetry data of the data zone and second local telemetry data of the at least one second data zone,
wherein the global compression model is adapted to generated second compressed telemetry data based on the telemetry data obtained from any number of sources.

### Claim 15

A non-transitory computer readable medium comprising computer readable program code, which when executed by a computer processor enables the computer processor to perform a method for generating predictions using data from data zones, the method comprising:
obtaining a local model set from a data zone of the data zones indicating that a global model set using to generate the predictions is unacceptable;
making a determination that the local model set is acceptable;
in response to the determination:
distributing the local model set to at least one second data zone of the data zones;
obtaining compressed telemetry data, that was compressed using the local model set, from the data zone and the at least one second data zone; and
generating a global prediction regarding a future operating condition of the data zones using:
the compressed local telemetry data, and
the local model set.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the method further comprises:
modifying an operation of the data zones based on the global prediction.

### Claim 17 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the local model set comprises:
a local prediction model trained on only local telemetry data of the data zone,
wherein the local prediction model is adapted to generate predictions based on telemetry data obtained from any number of sources.

### Claim 18 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein the global model set comprises:
a global prediction model trained on both local telemetry data of the data zone and second local telemetry data of the at least one second data zone,
wherein the global prediction model is adapted to generate second predictions based on the telemetry data obtained from any number of sources.

### Claim 19 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein making the determination that the local model set is acceptable comprises:
obtaining second local telemetry data from the at least one second data zone;
obtaining an operating condition associated with the second local telemetry data;
obtaining a local prediction of the operating condition using:
the local model set, and
the second local telemetry data;
obtaining compressed second local telemetry data using:
the local model set, and
the second local telemetry data;
obtaining decompressed second local telemetry data using the compressed second local telemetry data;
making the determination by analyzing:
the second local telemetry data,
the decompressed local telemetry data,
the operating condition, and
the local prediction of the operating prediction.

### Claim 20 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the local model set comprises:
a local compression model trained on only local telemetry data of the data zone,
wherein the local compression model is adapted to generated compressed telemetry data based on telemetry data obtained from any number of sources.