Method for predictive maintenance of a communication network

• US 7,822,417 B1
• Filed: 12/01/2005
• Issued: 10/26/2010
• Est. Priority Date: 12/01/2005
• Status: Expired due to Fees

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Eslambolchi, Hossein, Bajpay, Paritosh, McCanuel, John, Vasilescu, Mihail
• Primary Examiner(s): Phan, Huy
• Assistant Examiner(s): Huynh, Chuck
• Application Number:
  US11/290,845
• Time in Patent Office: 1,790 Days
• Field of Search: 455/423, 455/432.3, 370/228, 379/9
• US Class Current: 455/432.3
• CPC Class Codes: H04L 41/0681 Configuration of triggering conditions
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/149 for prediction of maintenance
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence

Abstract

Systems and methods for predicting one or more service problems in a communication network are described. In one implementation, a threshold is set and signal data are collected at an interface component. The collected data are compared to the threshold, and depending on the comparison between the collected data and the threshold, a trend analysis is performed on the collected data.

Claims

1. A method for automatically predicting one or more service problems in a communication network comprising:

setting a threshold for an interface component in a rules-based automated servicing platform;

receiving device performance data from said interface component;

tracking a count of each time that said device performance data indicates a signal anomaly;

generating at least one threshold crossing alert (TCA) if said count exceeds said threshold;

filtering a plurality of TCAs to remove one or more TCAs that do not need attention to generate at least one filtered TCA;

determining if said at least one filtered TCA is indicative of a negative trend regarding performance of said interface component over a configurable time period; and

comparing the device performance data to a previously collected device performance data that was collected over said configurable time period; and

automatically analyzing the device performance data and the previously collected device performance data in accordance with rules of said rules-based automated serving platform to determine whether a trend of service degradation exists.

2. The method of claim 1, wherein the trend of service degradation exists when the device performance data and the previously collected device performance data show a degraded signal quality at the interface component over the configurable time period.

3. The method of claim 1, wherein the filtering further comprises:

coordinating a repair of the interface component if the trend of degradation exists.

4. The method of claim 1, wherein the device performance data are performance monitoring data.

5. The method of claim 4, wherein the performance monitoring data are errored seconds data.

6. The method of claim 1, wherein the interface component is located at an end point of a network component.

7. The method of claim 6, wherein the end point is an optical transponder unit.

8. The method of claim 6, wherein the end point receives a signal from a customer installation or an Internet protocol backbone router.

9. The method of claim 6, wherein the end point sends a signal to a customer installation or an internet protocol backbone router.

10. The method of claim 1, wherein the device performance data is collected over a predetermined time period.

11. The method of claim 10, wherein the threshold is based on non-zero performance monitoring data that are collected during the predetermined time period.

12. A method comprising:

establishing a rules based engine for analyzing system performance data;

receiving data indicative of performance characteristics of a plurality of network devices;

analyzing said received data in accordance with the rules based engine, where a threshold is set for each of said plurality of network devices;

tracking a count of each time that said analyzing said received data indicates a signal anomaly;

generating at least one threshold crossing alert (TCA) if said count exceeds said threshold;

filtering a plurality of TCAs to remove one or more TCAs that do not need attention to generate at least one filtered TCA;

determining if said at least one filtered TCA is indicative of a negative trend regarding performance of said interface component over a configurable time period;

identifying one or more of said plurality of network devices as needing maintenance based on said filtering; and

prioritizing the one or more of said plurality of network devices needing maintenance in accordance with the rules based engine.