Network quality evaluation based on network metrics

1. A method for evaluating performance of a Passive Optical Network (PON), the method comprising:

obtaining a plurality of network performance metrics for an optical network terminal (ONT) for a customer in the PON, the PON including an optical line terminal (OLT) optically connected to a plurality of optical network terminals (ONTs) via a plurality of optical fibers;

analyzing each of the plurality of network performance metrics to assign an individual quality metric to each of the plurality of network performance metrics;

analyzing the individual quality metrics assigned to each of the plurality of network performance metrics to determine an overall quality metric for the ONT, including:

determining that none of a plurality of rules for determining overall quality metrics applies to the ONT based on the individual quality metrics; and

inputting the plurality of network performance metrics into a machine learning model to obtain the overall quality metric; and

providing an indication of the overall quality metric for the ONT to at least one of a user interface or another computing device.

2. The method of claim 1 , further comprising:

determining that the overall quality metric for the ONT is below a threshold overall quality; and

transmitting a control signal to automatically reboot a component of the PON in response to determining that the overall quality metric is below the threshold overall quality.

3. The method of claim 1 , wherein the machine learning model is trained with training sets of network performance metrics labelled with known overall quality metrics.

4. The method of claim 1 , wherein analyzing each of the plurality of network performance metrics includes:

applying at least one rule, of a plurality of rules for assigning individual quality metrics, to at least one of the network performance metrics to assign an individual quality metric to the at least one of the network performance metrics.

5. The method of claim 4 , wherein:

the plurality of rules for assigning individual quality metrics includes at least a first rule and a second rule, wherein:

the first rule provides that an individual quality metric assigned to at least one of the network performance metrics is categorized as excellent if the at least one of the network performance metrics falls within a first range associated with the at least one of the network performance metrics; and

the second rule provides that an individual quality metric assigned to at least one of the network performance metrics is categorized as good or fair if the at least one of the network performance metrics falls within a second range associated with the at least one of the network performance metrics.

6. The method of claim 5 , wherein:

the plurality of rules for assigning individual quality metrics further includes a third rule, wherein:

the third rule provides that an individual quality metric assigned to at least one of the network performance metrics is categorized as bad if the at least one of the network performance metrics falls within a third range associated with the at least one of the network performance metrics.

7. The method of claim 1 , wherein the network performance metrics include at least one of a customer light level, an alarm duration, a number of alarms, a session duration, a number of session stops, or a packet discard rate.

8. A computing device for evaluating performance of a Passive Optical Network (PON), the computing device comprising:

one or more processors; and

a non-transitory computer-readable memory storing instructions thereon that, when executed by the one or more processors, cause the computing device to:

obtain a plurality of network performance metrics for an optical network terminal (ONT) for a customer in the PON, the PON including an optical line terminal (OLT) optically connected to a plurality of optical network terminals (ONTs) via a plurality of optical fibers;

analyze each of the plurality of network performance metrics to assign an individual quality metric to each of the plurality of network performance metrics;

analyze the individual quality metrics assigned to each of the plurality of network performance metrics to determine an overall quality metric for the ONT, including:

determining whether at least one of a plurality of rules for determining overall quality metrics applies to the ONT based on the individual quality metrics; and

when none of the plurality of rules for determining overall quality metrics applies to the ONT based on the individual quality metrics; and, inputting the plurality of network performance metrics into a machine learning model to obtain the overall quality metric; and

provide an indication of the overall quality metric for the ONT to at least one of a user interface or another computing device.

9. The computing device of claim 8 , wherein the instructions, when executed by the one or more processors, further cause the computing device to:

determine that the overall quality metric for the ONT is below a threshold overall quality; and

transmit a control signal to automatically reboot a component of the PON in response to determining that the overall quality metric is below the threshold overall quality.

10. The computing device of claim 8 , wherein to analyze the individual quality metrics to determine the overall quality metric for the ONT, the instructions, when executed by the one or more processors, cause the computing device to:

when at least one rule of the plurality of rules for determining overall quality metrics applies to the ONT based on the individual quality metrics, apply the at least one rule to the ONT to determine the overall quality metric based on the individual quality metrics.

11. The computing device of claim 10 , wherein:

the plurality of rules includes at least a first rule and a second rule, wherein:

the first rule provides that the overall quality metric is excellent if each of the individual quality metrics is categorized as excellent, and

the second rule provides that the overall quality metric is bad if at least one of the individual quality metrics is categorized as bad.

12. The computing device of claim 8 , wherein the machine learning model is trained with training sets of network performance metrics labelled with known overall quality metrics.

13. The computing device of claim 8 , wherein to analyze each of the plurality of network performance metrics, the instructions, when executed by the one or more processors, cause the computing device to:

apply at least one rule, of a plurality of rules for assigning individual quality metrics, to at least one of the network performance metrics to assign an individual quality metric to the at least one of the network performance metrics.

14. The computing device of claim 13 , wherein:

the plurality of rules for assigning individual quality metrics includes at least a first rule and a second rule, wherein:

the first rule provides that an individual quality metric assigned to at least one of the network performance metrics is categorized as excellent if the at least one of the network performance metrics falls within a first range associated with the at least one of the network performance metrics; and

the second rule provides that an individual quality metric assigned to at least one of the network performance metrics is categorized as good or fair if the at least one of the network performance metrics falls within a second range associated with the at least one of the network performance metrics.

15. The computing device of claim 14 , wherein:

the plurality of rules for assigning individual quality metrics further includes a third rule, wherein:

the third rule provides that an individual quality metric assigned to at least one of the network performance metrics is categorized as bad if the at least one of the network performance metrics falls within a third range associated with the at least one of the network performance metrics.

16. The computing device of claim 8 , wherein the network performance metrics include at least one of a customer light level, an alarm duration, a number of alarms, a session duration, a number of session stops, or a packet discard rate.