Network performance assessment
There is provided a method for assessing network performance. The method includes acquiring network measurements indicative of any changes in a network following a change to a configuration of the network and data indicative of one or more factors capable of causing the changes in the network. The one or more factors are independent of the change to the configuration of the network. The method includes analysing the acquired network measurements and data to identify a contribution of the one or more factors to a key performance indicator (KPI) and a contribution of the change to the configuration of the network to the KPI. The KPI is predicted by a machine learning model and is a measure of the network performance following the change to the configuration of the network.
1. A method for assessing network performance, the method comprising:
acquiring network measurements indicative of any changes in a network following a change to a configuration of the network and data indicative of one or more factors capable of causing the changes in the network, the one or more factors being independent of the change to the configuration of the network, wherein the change to the configuration of the network comprises a remote electrical tilt;
analysing the acquired network measurements and data to identify a contribution of the one or more factors to a key performance indicator, KPI, and a contribution of the change to the configuration of the network to the KPI, wherein the KPI comprises:
a bearer drop ratio;
a handover success ratio;
an inter-cell interference level;
an uplink signal strength;
a downlink signal strength; or
a signal quality measure;
the KPI being predicted by a machine learning model and is a measure of the network performance following the change to the configuration of the network, wherein the machine learning model receives as input the network measurements and the data; and
comparing the predicted KPI to a reference KPI to identify a difference, wherein:
the difference is indicative of the contribution of the one or more factors and the change to the configuration of the network to the KPI;
the contribution of the one or more factors to the KPI is the contribution of the one or more factors to the difference;
the contribution of the change to the configuration of the network to the KPI is the contribution of the change to the configuration of the network to the difference; and
for each of the one or more factors, identifying the contribution of that factor to the difference,
wherein the one or more factors comprise any one or more of:
one or more configuration changes outside the network;
one or more faults in the network;
one or more service layer descriptors;
one or more data sources outside the network;
a location of one or more user equipments in the network; and
one or more environmental events; and
wherein the data indicative of the one or more factors comprises data other than:
a bearer drop ratio;
a handover success ratio;
an inter-cell interference level;
an uplink signal strength;
a downlink signal strength; and
a signal quality measure.
2. The method according to claim 1 , further comprising:
determining whether to maintain the change to the configuration of the network based on the contribution of the change to the configuration of the network to the KPI.
3. The method according to claim 2 , wherein:
determining whether to maintain the change to the configuration of the network comprises:
determining whether the change to the configuration of the network is an improvement based on the KPI and contribution of the change to the configuration of the network to the KPI; and
determining that the change is to be maintained if the change to the configuration of the network is determined to be an improvement.
4. The method according to claim 1 , further comprising
identifying an average of the contribution of the one or more factors to the difference; and
comparing the average of the contribution of the one or more factors to the difference to the contribution of the one or more factors to the difference.
5. The method according to claim 1 , the method further comprising:
filtering out the contribution of the one or more factors to the KPI to identify the contribution of the change to the configuration of the network to the KPI.
6. The method according to claim 1 , comprising:
performing the method for a plurality of different changes to the configuration of the network.
7. The method according to claim 6 , further comprising:
comparing the contributions of the different changes to the configuration of the network to the respective KPls.
8. The method according to claim 7 , further comprising:
selecting one of the plurality of different changes to the configuration of the network based on the comparison.
9. The method according to claim 1 , wherein:
the network measurements comprise network measurements indicative of any changes in one or more layers of the network.
10. The method according to claim 9 , wherein:
the network measurements indicative of any changes in the one or more layers of the network comprise network measurements indicative of any events in the one or more layers of the network.
11. The method according to claim 9 , wherein:
the one or more layers comprises a session layer of the network.
12. The method as claimed in claim 1 , wherein:
the network measurements comprise network measurements on one or more network elements.
13. The method according to claim 12 , wherein:
the one or more network elements are one or more network elements in respect of which the change to the configuration of the network is expected to have an impact.
14. The method according to claim 12 , wherein:
the network measurements on the one or more network elements comprise any one or more network element performance measurements and one or more network element event measurements.
15. The method as claimed in according to claim 1 , wherein:
the one or more factors further comprise any one or more of:
one or more configuration changes outside the network;
one or more data sources outside the network; and
one or more environmental events.
16. A first node, comprising:
processing circuitry configured to operate:
acquire network measurements indicative of any changes in a network following a change to a configuration of the network and data indicative of one or more factors capable of causing the changes in the network, the one or more factors being independent of the change to the configuration of the network, wherein the change to the configuration of the network comprises a remote electrical tilt;:
analyse the acquired network measurements and data to identify a contribution of the one or more factors to a key performance indicator, KPI, and a contribution of the change to the configuration of the network to the KPI, wherein the KPI comprises:
a bearer drop ratio;
a handover success ratio;
an inter-cell interference level;
an uplink signal strength;
a downlink signal strength; or
a signal quality measure;
the KPI being predicted by a machine learning model and is a measure of the network performance following the change to the configuration of the network, and
compare the predicted KPI to a reference KPI to identify a difference, wherein:
the difference is indicative of the contribution of the one or more factors and the change to the configuration of the network to the KPI;
the contribution of the one or more factors to the KPI is the contribution of the one or more factors to the difference;
the contribution of the change to the configuration of the network to the KPI is the contribution of the change to the configuration of the network to the difference; and
for each of the one or more factors, identifying the contribution of that factor to the difference,
wherein the one or more factors comprise any one or more of:
one or more configuration changes outside the network;
one or more faults in the network;
one or more service layer descriptors;
one or more data sources outside the network;
a location of one or more user equipments in the network; and
one or more environmental events, and
wherein the data indicative of the one or more factors comprises data other than:
a bearer drop ratio;
a handover success ratio;
an inter-cell interference level;
an uplink signal strength;
a downlink signal strength; and
a signal quality measure.
17. The first node according to claim 16 , wherein:
the first node further comprises:
at least one memory storing instructions which, when executed by the processing circuitry, cause the processing circuitry to perform the acquiring and the analysing.
18. The method according to claim 1 , further comprising:
acquiring training data comprising the network measurements indicative of any changes in the network following the change to the configuration of the network and the data indicative of one or more factors capable of causing the changes in the network; and
training the machine learning model to predict the KPI based on the acquired training data.
19. The method according to claim 18 , wherein:
the training data is acquired continuously or iteratively.
20. The method according to claim 18 , further comprising retraining the machine learning model based on updated training data.
21. The method according to claim 18 , wherein:
the training data is a vectorized set of training data.
22. The method according to claim 18 , wherein:
the network measurements comprise network measurements indicative of any changes in one or more layers of the network.
23. The method according to claim 22 , wherein:
the network measurements indicative of any changes in the one or more layers of the network comprise network measurements indicative of any events in the one or more layers of the network.
24. The method according to claim 22 , wherein:
the one or more layers comprises a session layer of the network.
25. The method according to claim 22 , wherein:
the network measurements comprise network measurements on one or more network elements.
26. The method according to claim 25 , wherein:
the one or more network elements are one or more network elements in respect of which the change to the configuration of the network is expected to have an impact.
27. The method according to claim 25 , wherein:
the network measurements on the one or more network elements comprise one or both of:
any one or more network element performance measurements; and
one or more network element event measurements.
28. The method according to claim 18 , wherein:
the one or more factors comprise one or more service layer descriptors, wherein one or more KPIs are obtained by deep packet inspection.
29. The method according to claim 1 , wherein the network measurements are acquired from the network and the data is acquired from one or more data sources outside the network.
30. The method according to claim 1 , wherein the difference is a positive KPI change from the reference KPI to the predicted KPI.