Neighbor relation conflict prediction

1. A computer-readable storage medium including instructions executable by a computer to cause the computer to perform operations comprising:

receiving, from a serving Master Cell Group (MCG) of a terminal, a measurement report of the terminal, the measurement report including a plurality of signal measurements, each signal measurement associated with a Secondary Cell Group (SCG) represented by a Physical Cell Identifier (PCI) and an Absolute Radio-Frequency Channel Number (ARFCN);

identifying an unlisted SCG among the plurality of signal measurements, the unlisted SCG represented by a PCI and an associated ARFCN that do not correspond to any single SCG in a Neighbor Relations Table (NRT) of the serving MCG;

identifying one or more nearby MCG within a threshold distance of the serving MCG;

counting a number of SCG in the NRT of each nearby MCG having the PCI and the ARFCN of the unlisted SCG; and

applying a classification model to the counted number of SCG and an MCG-PCI-ARFCN identifier representing the serving MCG, the PCI, and the ARFCN to obtain a prediction value, the prediction value being a binary value indicating whether provisioning the unlisted SCG with the serving MCG and the plurality of nearby MCG will result in PCI conflict.

2. The computer-readable storage medium of claim 1 , wherein the instructions are further configured to cause the computer to perform applying the classification model to at least one of a geographic location of the serving MCG or a frequency type of the ARFCN to obtain the prediction.

3. The computer-readable storage medium of claim 1 , wherein the instructions are further configured to cause the computer to perform:

storing the counted number and the MCG-PCI-ARFCN identifier as a training sample;

determining whether the PCI and the ARFCN are included in the NRT of the serving MCG;

labeling the training sample with a ground-truth prediction value indicating the determination; and

training the classification model with the labeled training sample.

4. The computer-readable storage medium of claim 3 , wherein the determining is performed a period of time after the storing, wherein the period of time ranges between one and ten days.

5. The computer-readable storage medium of claim 3 , wherein

the determining, labeling, and training are performed in batches for a plurality of stored training samples per batch once per a period of time ranging between 15 minutes and one day.

6. The computer-readable storage medium of claim 3 , wherein the instructions are further configured to cause the computer to perform:

initializing the classification model;

generating a plurality of initial training samples, each of the plurality of initial training samples including an arbitrarily selected MCG-PCI-ARFCN identifier;

identifying, for each of the plurality of initial training samples, one or more nearby MCG within the threshold distance of the MCG represented by the MCG-PCI-ARFCN identifier;

counting, for each of the plurality of initial training samples, a number of SCG in the NRT of each nearby MCG having the PCI and the ARFCN represented by the MCG-PCI-ARFCN identifier;

labeling the training sample with one of a ground-truth prediction value indicating PCI conflict in response to the counted number being not less than a threshold count or a ground-truth prediction value indicating no PCI conflict in response to the counted number being less than the threshold count; and

training the initialized classification model with the plurality of initial training samples.

7. The computer-readable storage medium of claim 1 , wherein the classification model is a support vector machine classification model.

8. The computer-readable storage medium of claim 1 , wherein the instructions are further configured to cause the computer to perform:

obtaining a geographic location for each of a plurality of MCG in a cellular network;

forming a plurality of MCG pairings, each of the plurality of MCG pairings including a first MCG among the plurality of MCG and a second MCG among the plurality of MCG;

calculating, for each of the plurality of MCG pairings, a distance between the first MCG and the second MCG based on the geographic location of the first MCG and the geographic location of the second MCG; and

storing data representing the first MCG in correspondence with the second MCG, the geographic location of the first MCG, and a vicinity value, the vicinity value being a binary value indicating whether the calculated distance is within the threshold distance;

wherein the identifying the one or more nearby MCG includes accessing the stored data to retrieve one or more second MCG corresponding to the serving MCG as the stored first MCG and the vicinity value representing that the calculated distance is within the threshold distance.

9. The computer-readable storage medium of claim 8 , wherein the obtaining, forming, calculating, and storing are performed once per a period of time ranging between 6 hours and one week.

10. The computer-readable storage medium of claim 8 , wherein the instructions are further configured to cause the computer to perform applying a regression model to the calculated distance to obtain the vicinity value.

11. The computer-readable storage medium of claim 10 , wherein the instructions are further configured to cause the computer to perform:

initializing the regression model;

generating a plurality of initial training samples, each of the plurality of initial training samples including a pairing among the plurality of pairings;

labeling each of the plurality of initial training samples with a ground-truth vicinity value indicating whether the calculated distance is within the threshold distance; and

training the initialized regression model with the plurality of initial training samples.

12. A method comprising:

receiving, from a serving Master Cell Group (MCG) of a terminal, a measurement report of the terminal, the measurement report including a plurality of signal measurements, each signal measurement associated with a Secondary Cell Group (SCG) represented by a Physical Cell Identifier (PCI) and an Absolute Radio-Frequency Channel Number (ARFCN);

identifying an unlisted SCG among the plurality of signal measurements, the unlisted SCG represented by a PCI and an associated ARFCN that do not correspond to any single SCG in a Neighbor Relations Table (NRT) of the serving MCG;

identifying one or more nearby MCG within a threshold distance of the serving MCG;

counting a number of SCG in the NRT of each nearby MCG having the PCI and the ARFCN of the unlisted SCG; and

applying a classification model to the counted number of SCG and an MCG-PCI-ARFCN identifier representing the serving MCG, the PCI, and the ARFCN to obtain a prediction value, the prediction value being a binary value indicating whether provisioning the unlisted SCG with the serving MCG and the plurality of nearby MCG will result in PCI conflict.

13. The method of claim 12 , wherein the applying includes further applying the classification model to at least one of a geographic location of the serving MCG or a frequency type of the ARFCN to obtain the prediction.

14. The method of claim 12 , further comprising

storing the counted number and the MCG-PCI-ARFCN identifier as a training sample;

determining whether the PCI and the ARFCN are included in the NRT of the serving MCG;

labeling the training sample with a ground-truth prediction value indicating the determination; and

training the classification model with the labeled training sample.

15. The method of claim 14 , wherein the determining is performed a period of time after the storing, wherein the period of time ranges between one and ten days.

16. The method of claim 14 , wherein

the determining, labeling, and training are performed in batches for a plurality of stored training samples per batch once per a period of time ranging between 15 minutes and one day.

17. The method of claim 14 , further comprising

initializing the classification model;

generating a plurality of initial training samples, each of the plurality of initial training samples including an arbitrarily selected MCG-PCI-ARFCN identifier;

identifying, for each of the plurality of initial training samples, one or more nearby MCG within the threshold distance of the MCG represented by the MCG-PCI-ARFCN identifier;

counting, for each of the plurality of initial training samples, a number of SCG in the NRT of each nearby MCG having the PCI and the ARFCN represented by the MCG-PCI-ARFCN identifier;

labeling the training sample with one of a ground-truth prediction value indicating PCI conflict in response to the counted number being not less than a threshold count and a ground-truth prediction value indicating no PCI conflict in response to the counted number being less than the threshold count; and

training the initialized classification model with the plurality of initial training samples.

18. The method of claim 12 , wherein the classification model is a support vector machine classification model.

19. The method of claim 12 , further comprising:

obtaining a geographic location for each of a plurality of MCG in a cellular network;

forming a plurality of MCG pairings, each of the plurality of MCG pairings including a first MCG among the plurality of MCG and a second MCG among the plurality of MCG;

calculating, for each of the plurality of MCG pairings, a distance between the first MCG and the second MCG based on the geographic location of the first MCG and the geographic location of the second MCG; and

storing data representing the first MCG in correspondence with the second MCG, the geographic location of the first MCG, and a vicinity value, the vicinity value being a binary value indicating whether the calculated distance is within the threshold distance;

wherein the identifying the one or more nearby MCG includes accessing the stored data to retrieve one or more second MCG corresponding to the serving MCG as the stored first MCG and the vicinity value representing that the calculated distance is within the threshold distance.

20. An apparatus comprising:

a controller including circuitry configured to

receive, from a serving Master Cell Group (MCG) of a terminal, a measurement report of the terminal, the measurement report including a plurality of signal measurements, each signal measurement associated with a Secondary Cell Group (SCG) represented by a Physical Cell Identifier (PCI) and an Absolute Radio-Frequency Channel Number (ARFCN);

identify an unlisted SCG among the plurality of signal measurements, the unlisted SCG represented by a PCI and an associated ARFCN that do not correspond to any single SCG in a Neighbor Relations Table (NRT) of the serving MCG;

identify one or more nearby MCG within a threshold distance of the serving MCG;

count a number of SCG in the NRT of each nearby MCG having the PCI and the ARFCN of the unlisted SCG; and

apply a classification model to the counted number of SCG and an MCG-PCI-ARFCN identifier representing the serving MCG, the PCI, and the ARFCN to obtain a prediction value, the prediction value being a binary value indicating whether provisioning the unlisted SCG with the serving MCG and the plurality of nearby MCG will result in PCI conflict.