Service Performance in Communications Network

• US 20130290525A1
• Filed: 11/17/2010
• Published: 10/31/2013
• Est. Priority Date: 10/29/2010
• Status: Abandoned Application

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Telefonaktiebolaget LM Ericsson
• Inventors: Fedor, Szymon, Handurukande, Sidath
• Application Number:
  US13/881,964
• Publication Number:
  US 20130290525A1
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/5009 Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
• CPC Class Codes: H04L 41/5067 Customer-centric QoS measurements
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 43/091 Measuring contribution of individual network components to actual service level

Abstract

A method for monitoring performance of a service delivered to user equipment devices via a communications network as perceived by a user comprising the steps of collecting Resource Service Key Performance Indicators from network resources and collecting System Service Key Performance Indicators from a representative sample of reporting user equipment devices using the service. In the next step relationship between the collected values of R-KPIs and S-KPIs is determined and then userr equipment from the representative sample is clustered. In the following step non-reporting user equipment devices are assigned to the clusters and then the method comprises collecting R-KPIs from network resources to estimate S-KPI values based on the R-KPIs collected after determination of the relationship and the relationship.

Claims

1. A method for monitoring performance of a service delivered to user equipment devices via a communications network as perceived by a user;

the method comprising;

collecting Resource Service Key Performance Indicators, R-KPIs, from network resources;

collecting System Service Key Performance Indicators, S-KPIs, from a representative sample of reporting user equipment devices using the service;

determining relationship between the collected values of R-KPIs and S-KPIs;

clustering the user equipment devices from the representative sample based on the relationship between the R-KPIs and S-KPIs;

assigning non-reporting user equipment devices to the clusters;

collecting R-KPIs from network resources; and

estimating S-KPIs values based on the relationship and the R-KPIs collected after the relationship is determined.

2. The method according to claim 1, further comprising repeating the steps periodically.

3. The method according to claim 1 wherein the step of determining the relationship comprises:

selecting a subset of S-KPIs reported by a single user equipment device;

time-correlating the values of S-KPIs reported by the single user equipment device and the R-KPIs; and

for every S-KPI reported by the single user equipment device, determining a function defining the relationship using Machine Learning and/or Data Mining methods.

4. The method according to claim 3, further comprising repeating the steps of determining the relationship for every user equipment device that reported S-KPIs.

5. The method according to claim 1 comprising mapping the estimated S-KPI values onto Quality of System Service, QoSS, classes to correlate the QoSS classes with the users'"'"' perception of the service performance reported in User Reported-QoSS.

6. The method according to claim 5, wherein the QoSS classes used in the mapping are determined on the basis of User Reported-QoSS received from at least part of the users of the service.

7. The method according to claim 1, wherein in the step of clustering a user equipment device from the representative sample is assigned to a cluster if a function defining the relationship between R-KPIs and S-KPIs for this user equipment device is within a range defined for this cluster.

8. The method according to claim 1, wherein the non-reporting user equipment devices are assigned to clusters based on geographical proximity or network topology proximity, or performance of a user equipment device, codec used or any combination of these.

9. A monitoring server for use in a communications network for monitoring performance of a service delivered to user equipment devices via the communications network, the monitoring server comprising:

a collecting module adapted to collect Resource Service Key Performance Indicators, R-KPIs, from network resources and System Service Key Performance Indicators, S-KPIs, from a representative sample of reporting user equipment devices using the service;

a calculating module adapted to determine relationship between the collected values of R-KPIs and S-KPIs; and

a clustering module adapted to cluster the user equipment devices from the representative sample based on relationship between the R-KPIs and S-KPIs and to assign non-reporting user equipment devices to the clusters, wherein

the collecting module is adapted to collect R-KPIs after the relationship between the R-KPIs and S-KPIs is determined and the monitoring server is adapted to estimate S-KPIs values based on the relationship and the R-KPIs collected after the relationship is determined.

10. The monitoring server according to claim 9, wherein the calculating module is implemented in a processor and in the step of determining the relationship the calculating module is adapted to select a subset of S-KPIs reported by a single user equipment device and time-correlate the values of S-KPIs reported by the single user equipment device and the R-KPIs;

wherein for every S-KPI reported by the single user equipment device the calculating module is adapted to define the relationship using Machine Learning and/or Data Mining methods.

11. The monitoring server according to claim 10, wherein the processor is adapted to determine the relationship for every user equipment device that reported S-KPIs.

12. The monitoring server according to claim 9, wherein the processor is adapted to map the estimated S-KPI values onto Quality of System Service, QoSS, classes to correlate the QoSS classes with the users'"'"' perception of the service performance reported in User Reported-QoSS.

13. The monitoring server according to claim 12, wherein the QoSS classes used in the mapping are determined on the basis of User Reported-QoSS received from at least part of the users of the service.

14. The monitoring server according to claim 9, wherein the clustering module is adapted to assign a user equipment device from the representative sample to a cluster if a function defining the relationship between R-KPIs and S-KPIs for this user equipment device is within a range defined for this cluster.

15. A communications network for monitoring performance of a service delivered to user equipment devices via the communications network, the communications network comprising:

a plurality of network nodes; and

a monitoring server;

wherein

the monitoring server comprises;

a collecting module adapted to collect Resource Service Key Performance Indicators, R-KPIs, from network resources and System Service Key Performance Indicators, S-KPIs, from a representative sample of reporting user equipment devices using the service;

a calculating module adapted to determine relationship between the collected values of R-KPIs and S-KPIs; and

a clustering module adapted to cluster the user equipment devices from the representative sample based on relationship between the R-KPIs and S-KPIs and to assign non-reporting user equipment devices to the clusters, wherein

the collecting module is adapted to collect R-KPIs after the relationship between the R-KPIs and S-KPIs is determined and the monitoring server is adapted to estimate S-KPIs values based on the relationship and the R-KPIs collected after the relationship is determined.