Cell accessibility prediction and actuation

Patent metadata

Field	Value
Publication number	US-11271797-B2
Application number	US-202016925242-A
Country	US
Kind code	B2
Filing date	Jul 9, 2020
Priority date	Jul 9, 2020
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

A method for predicting cell accessibility issues for a mobile network. The method includes receiving a set of metrics from the mobile network, processing a set of key performance indicators (KPIs) derived from the set of metrics in an ensemble machine learning model, the ensemble machine learning model including an RRC model, an RACH model, an ERAB model, and an S1 signaling model to generate at least one cell accessibility degradation prediction and a confidence score, and applying a root cause mapping to the at least one cell accessibility degradation prediction and the confidence score to identify at least one recommended action to correct a correlated cell accessibility issue.

First claim

What is claimed is:

1. A method for predicting cell accessibility issues for a mobile network, the method comprising:
receiving a set of metrics from the mobile network;
processing a set of key performance indicators (KPIs) derived from the set of metrics in an ensemble machine learning model, the ensemble machine learning model including a radio resource channel (RRC) model, a random access channel (RACH) model, an Evolved Universal Telecommunication Systems (UMTS) Terrestrial Radio Access Network (E-UTRAN) Radio Access Bearer (ERAB) model, and an S1 signaling model to generate at least one cell accessibility degradation prediction and a confidence score; and
applying a root cause mapping to the at least one cell accessibility degradation prediction and the confidence score to identify at least one recommended action to correct a correlated cell accessibility issue.

2. The method of claim 1 , further comprising:
normalizing the received set of metrics including computing moving averages of the set of metrics for multiple preceding time periods.

3. The method of claim 1 , further comprising:
selecting the at least one cell accessibility degradation prediction for the root cause mapping.

4. The method of claim 1 , further comprising:
applying a set of logic rules to the least one recommended action to determine whether to actuate the least one recommended action.

5. The method of claim 4 , wherein the set of logic rules are also applied to parameters including prior recommended actions to determine whether to actuate the least one recommended action.

6. The method of claim 1 , further comprising:
applying the root cause mapping to multiple cell accessibility degradation predictions.

7. A non-transitory machine-readable storage medium that provides instructions that, if executed by a processor, will cause said processor to perform operations comprising:
receiving a set of metrics from a mobile network;
processing a set of key performance indicators (KPIs) derived from the set of metrics in an ensemble machine learning model, the ensemble machine learning model including a radio resource channel (RRC) model, a random access channel (RACH) model, an Evolved Universal Telecommunication Systems (UMTS) Terrestrial Radio Access Network (E-UTRAN) Radio Access Bearer (ERAB) model, and an S1 signaling model to generate at least one cell accessibility degradation prediction and a confidence score; and
applying a root cause mapping to the at least one cell accessibility degradation prediction and the confidence score to identify at least one recommended action to correct a correlated cell accessibility issue.

8. The non-transitory machine-readable storage medium of claim 7 , wherein the operations further comprising:
normalizing the received set of metrics including computing moving averages of the set of metrics for multiple preceding time periods.

9. The non-transitory machine-readable storage medium of claim 7 , wherein the operations further comprising:
selecting the at least one cell accessibility degradation prediction for the root cause mapping.

10. The non-transitory machine-readable storage medium of claim 7 , wherein the operations further comprising:
applying a set of logic rules to the least one recommended action to determine whether to actuate the least one recommended action.

11. The non-transitory machine-readable storage medium of claim 10 , wherein the set of logic rules are also applied to parameters including prior recommended actions to determine whether to actuate the least one recommended action.

12. The non-transitory machine-readable storage medium of claim 7 , wherein the operations further comprising:
applying the root cause mapping to multiple cell accessibility degradation predictions.

13. An electronic device to for predicting cell accessibility issues for a mobile network, the electronic device comprising:
a machine-readable storage medium having stored there in a cell accessibility predictor; and
a processor coupled to the machine-readable storage medium, the processor to execute the cell accessibility predictor, the cell accessibility predictor to receive a set of metrics from the mobile network, process a set of key performance indicators (KPIs) derived from the set of metrics in an ensemble machine learning model, the ensemble machine learning model including a radio resource channel (RRC) model, a random access channel (RACH) model, an Evolved Universal Telecommunication Systems (UMTS) Terrestrial Radio Access Network (E-UTRAN) Radio Access Bearer (ERAB) model, and an S1 signaling model to generate at least one cell accessibility degradation prediction and a confidence score, and apply a root cause mapping to the at least one cell accessibility degradation prediction and the confidence score to identify at least one recommended action to correct a correlated cell accessibility issue.

14. The electronic device of claim 13 , wherein the cell accessibility predictor to further normalize the received set of metrics including computing moving averages of the set of metrics for multiple preceding time periods.

15. The electronic device of claim 13 , wherein the cell accessibility predictor to further select the at least one cell accessibility degradation prediction for the root cause mapping.

16. The electronic device of claim 13 , wherein the cell accessibility predictor to further apply a set of logic rules to the least one recommended action to determine whether to actuate the least one recommended action.

17. The electronic device of claim 16 , wherein the set of logic rules are also applied to parameters including prior recommended actions to determine whether to actuate the least one recommended action.

18. The electronic device of claim 13 , wherein the cell accessibility predictor to further applying the root cause mapping to multiple cell accessibility degradation predictions.

Assignees

• Ericsson Telefon Ab L M

Inventors

• Yadav Niharika
• Goyal Paluk
• Sen Aritra
• Kochar Barjinder
• Kao Amos

Classifications

• G06N20/20

  Ensemble learning · CPC title

• H04L41/0636 Primary

  based on a decision tree analysis · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• H04W24/04 Primary

  Arrangements for maintaining operational condition · CPC title

• H04W24/02

  Arrangements for optimising operational condition · CPC title