Alarm prediction in a telecommunication network

Patent metadata

Field	Value
Publication number	US-9716633-B2
Application number	US-201315029834-A
Country	US
Kind code	B2
Filing date	Oct 18, 2013
Priority date	Oct 18, 2013
Publication date	Jul 25, 2017
Grant date	Jul 25, 2017

Abstract

The present disclosure relates to a method performed by a network node configured for making automatic predictions in a telecommunication network. The method comprises obtaining a first value of a first key performance indicator (KPI) for a first network entity (NE) in the telecommunication network. The method also comprises obtaining a second value of a second KPI for a communication route between said first NE and a second NE. The method also comprises predicting, automatically and based on the obtained first and second values, that an alarm will be triggered at the second NE.

First claim

The invention claimed is:

1. A method performed by a network node configured for making automatic predictions in a telecommunication network, the method comprising:
obtaining a first value of a first key performance indicator (KPI) for a first Network Element (NE) in the telecommunication network;
obtaining a second value of a second KPI for a communication route between said first NE and a second NE; and
predicting, automatically and based on the obtained first and second values, that an alarm will be triggered at the second NE,
wherein the network node is configured for automatic learning in the form of Machine Learning (ML), and
wherein the predicting that an alarm will be triggered at the second NE is based on the ML.

2. The method of claim 1 , further comprising:
obtaining a fourth value of a fourth KPI for a third NE;
wherein the predicting that an alarm will be triggered at the second NE is based also on the obtained fourth value.

3. The method of claim 1 , further comprising:
obtaining a fifth value of a fifth KPI for the first NE;
wherein the predicting that an alarm will be triggered at the second NE is further based on the obtained fifth value.

4. The method of claim 1 , wherein the network node is a network management node comprising a Network Operations Centre (NOC).

5. The method of claim 1 , wherein the first KPI is one from the group consisting of: amount of used memory, call answer rate, amount of used processing power, power level, number of dropped calls, number of data sessions, number of session freezes, and number of connected calls.

6. The method of claim 1 , wherein the predicting that an alarm will be triggered is done by operations according to a Markov Random Field (MRF) model or a Bayesian Networks model.

7. The method of claim 1 , wherein the second value relates to a combination of a plurality of communication routes between the first NE and the second NE.

8. The method of claim 1 , wherein the telecommunication network is a Global System for Mobile Communications (GSM) network.

9. The method of claim 8 , wherein the first and/or second NE is one from the group consisting of: a Mobile Switching Center (MSC), a media gateway (MGW), a base station controller (BSC), a base transceiver station (BTS) and a mobile station (MS).

10. The method of claim 1 , wherein the telecommunication network is a Universal Mobile Telecommunications System (UMTS) network.

11. The method of claim 10 , wherein the first and/or second NE is one from the group consisting of: a Mobile Switching Center (MSC), a Radio Network Controller (RNC), a Node B and a User Equipment (UE).

12. The method of claim 1 , wherein the telecommunication network is a Long Term Evolution (LTE) network.

13. The method of claim 12 , wherein the first and/or second NE is one from the group consisting of: a Mobility Management Entity (MME), a public data network (PDN) gateway, a serving gateway, an evolved Node B (eNB), and a User Equipment (UE).

14. A computer program product comprising a non-transitory computer readable storage medium storing program code that when executed by processor circuitry of a network node causes the network node to perform the method of claim 1 .

15. A method performed by a network node configured for making automatic predictions in a telecommunication network, the method comprising:
obtaining a first value of a first key performance indicator (KPI) for a first Network Element (NE) in the telecommunication network;
obtaining a second value of a second KPI for a communication route between said first NE and a second NE;
predicting, automatically and based on the obtained first and second values, that an alarm will be triggered at the second NE;
obtaining a third value of a third KPI for the second NE;
determining that the alarm should be triggered at the second NE based on the third value; and
determining as part of automatic learning, that the prediction was correct.

16. A network node configured for making automatic predictions in a telecommunication network, the node comprising:
processor circuitry; and
a storage unit storing instructions that, when executed by the processor circuitry, cause the node to perform operations comprising:
obtaining a first value of a first key performance indicator (KPI) for a first Network Element (NE) in the telecommunication network;
obtaining a second value of a second KPI for a communication route between said first NE and a second NE; and
predicting, automatically and based on the obtained first and second values, that an alarm will be triggered at the second NE,
wherein the network node is configured for automatic learning in the form of Machine Learning (ML), and
wherein the predicting that an alarm will be triggered at the second NE is based on the ML.

17. The network node of claim 16 , wherein the network node is a network management node.

18. A non-transitory computer readable storage medium storing a computer program including program code that when run on processor circuitry of a network node configured for making automatic predictions in a telecommunication network, cause the network node to perform operations comprising:
obtaining a first value of a first key performance indicator (KPI) for a first Network Element (NE) in the telecommunication network;
obtaining a second value of a second KPI for a communication route between said first NE and a second NE; and
predicting, automatically and based on the obtained first and second values, that an alarm will be triggered at the second NE,
wherein the network node is configured for automatic learning in the form of Machine Learning (ML), and
wherein the predicting that an alarm will be triggered at the second NE is based on the ML.

Assignees

• ERICSSON TELEFON AB L M (publ)

Inventors

• Premkumar Karthikeyan
• Shivashankar Subramanian

Classifications

• H04L41/069

  using logs of notifications; Post-processing of notifications · CPC title

• H04L43/16

  Threshold monitoring · CPC title

• H04L41/142

  using statistical or mathematical methods · CPC title

• H04L41/0681

  Configuration of triggering conditions · CPC title

• H04L41/0677

  Localisation of faults · CPC title