NETWORK PERFORMANCE PREDICTION METHOD AND APPARATUS

• US 20160191336A1
• Filed: 03/04/2016
• Published: 06/30/2016
• Est. Priority Date: 09/06/2013
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: ZHANG, Yaokun
• Granted Patent: US 10,298,464 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 41/0604 using filtering, e.g. reduction of information by using priority, element types, position or time
• CPC Class Codes: H04L 41/0654 using network fault recovery ring fault isolation or reconfiguration in loop networks without recovery actions by a network management system H04L12/437
• CPC Class Codes: H04L 41/0695 the faulty arrangement being the maintenance, administration or management system
• CPC Class Codes: H04L 41/142 using statistical or mathematical methods
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• 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 43/16 Threshold monitoring
• CPC Class Codes: H04L 47/127 by using congestion prediction

Abstract

The present application relates to a method and apparatus of predicting network performance, wherein the method includes: obtaining M performance parameter data of a link; calculating a cloud model digital feature of network performance of the link according to the M performance parameter data; calculating N predicted performance parameter data of the network performance of the link according to the cloud model digital feature; and raising a prediction alarm that the link has a risk of exceeding a limit if there is data exceeding a preset upper limit value in the N predicted performance parameter data, wherein M and N are preset positive integers. A change trend of network performance is analyzed according to real-time monitored data of the network performance of the link to predict future performance parameter data, and whether an alarm is raised and protection switching is performed is determined based on the prediction.

Claims

1. A method of predicting network performance, comprising:

obtaining M performance parameter data of a link;

calculating a cloud model digital feature of network performance of the link according to the M performance parameter data;

calculating N predicted performance parameter data of the network performance of the link according to the cloud model digital feature; and

raising a prediction alarm that the link has a risk of exceeding a limit if there is data exceeding a preset upper limit value in the N predicted performance parameter data, wherein M and N are preset positive integers.

2. The method of claim 1, wherein the cloud model digital feature of the network performance of the link comprises:

an expected value E_x, an entropy E_n and a hyper entropy H_e; and

wherein the calculating a cloud model digital feature of network performance of the link according to the M performance parameter data comprises;

calculating a sample mean of the M performance parameter data by using

3. The method of claim 2, wherein the calculating N predicted performance parameter data of the network performance of the link according to the cloud model digital feature comprises:

generating a normal random number E_n′

, which takes the entropy E_n as an expected value and the hyper entropy H_e as a standard deviation, by using the entropy E_n and the hyper entropy H_e in the cloud model digital feature {E_x, E_n, H_e};

generating a normal random number x, which takes the expected value E_x as the expected value and the normal random number E_n′

as the standard deviation, by using the expected value E_x and the normal random number E_n′

in the cloud model digital feature {E_x, E_n, H_e};

calculating a certainty y of the normal random number x belonging to the network performance by using

4. The method of claim 1, wherein after the obtaining M performance parameter data of a link, the method further comprises:

raising an alarm that the link exceeds the limit if there is data exceeding the preset upper limit value in the M performance parameter data.

5. The method of claim 2, wherein after the obtaining M performance parameter data of a link, the method further comprises:

raising an alarm that the link exceeds the limit if there is data exceeding the preset upper limit value in the M performance parameter data.

6. The method of claim 3, wherein after the obtaining M performance parameter data of a link, the method further comprises:

raising an alarm that the link exceeds the limit if there is data exceeding the preset upper limit value in the M performance parameter data.

7. The method of claim 4, further comprising:

executing, when the data in the M performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.

8. The method of claim 4, further comprising:

executing, when the data in the N predicted performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.

9. The method of claim 5, further comprising:

executing, when the data in the M performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.

10. The method of claim 5, further comprising:

executing, when the data in the N predicted performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.

11. A network performance prediction apparatus, comprising:

a processor and a memory having program code stored therein, wherein the program code executed on the processor configures the apparatus to;

obtain M performance parameter data of a link;

calculate a cloud model digital feature of network performance of the link according to the M performance parameter data obtained by the obtaining module;

calculate N predicted performance parameter data of the network performance of the link according to the cloud model digital feature calculated by the first calculating module;

determine whether there is data exceeding a preset upper limit value in the N predicted performance parameter data calculated by the second calculating module;

raise a prediction alarm that the link has a risk of exceeding a limit if the first determining module determines there is the data exceeding the preset upper limit value in the N predicted performance parameter data, wherein M and N are preset positive integers.

12. The apparatus of claim 11, wherein the cloud model digital feature of the network performance of the link calculated by the first calculating module comprises:

an expected value E_x, an entropy E_n and a hyper entropy H_e;

the code executed on the processor configures the apparatus to calculate a sample mean of the M performance parameter data by using

13. The apparatus of claim 12, wherein the code executed on the processor configures the apparatus to generate a normal random number E_n′

, which takes the entropy E_n as an expected value and the hyper entropy H_e as a standard deviation, by using the entropy E_n and the hyper entropy H_e in the cloud model digital feature {E_x, E_n, H_e};

the code executed on the processor further configures the apparatus to generate a normal random number x, which taking the expected value E_x as the expected value and the normal random number E_n′

as the standard deviation, by using the expected value E_x and the normal random number E_n′

in the cloud model digital feature {E_x, E_n, H_e};

the code executed on the processor further configures the apparatus to calculate a certainty y of the normal random number x belonging to the network performance by using

14. The apparatus of claim 11, wherein the code executed on the processor further configures the apparatus to determine whether there is data exceeding the preset upper limit value in the M performance parameter data obtained by the obtaining module;

the code executed on the processor further configures the apparatus to raise an alarm that the link exceeds a limit when the data in the M performance parameter data exceeds the preset upper limit value.

15. The apparatus of claim 12, wherein the code executed on the processor further configures the apparatus to determine whether there is data exceeding the preset upper limit value in the M performance parameter data obtained by the obtaining module;

the code executed on the processor further configures the apparatus to raise an alarm that the link exceeds a limit when the data in the M performance parameter data exceeds the preset upper limit value.

16. The apparatus of claim 13, wherein the code executed on the processor further configures the apparatus to determine whether there is the data exceeding the preset upper limit value in the M performance parameter data obtained by the obtaining module;

the code executed on the processor further configures the apparatus to raise an alarm that the link exceeds a limit when the data in the M performance parameter data exceeds the preset upper limit value.

17. The apparatus of claim 14, wherein the code executed on the processor further configures the apparatus to execute, when the data in the M performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.

18. The apparatus of claim 15, wherein,

the code executed on the processor further configures the apparatus to execute, when the data in the N predicted performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.

19. The apparatus of claim 14, wherein the code executed on the processor further configures the apparatus to execute, when the data in the M performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.

20. The apparatus of claim 15, wherein,

the code executed on the processor further configures the apparatus to execute, when the data in the N predicted performance parameter data exceeds the preset upper limit value, active-standby link switching if there is a standby link for the link.