TOOL FOR PREDICTING CAPACITY DEMANDS ON AN ELECTRONIC SYSTEM

• US 20150248610A1
• Filed: 02/28/2014
• Published: 09/03/2015
• Est. Priority Date: 03/13/2006
• Status: Active Grant

• Current Assignee: Comcast Cable Communications LLC (Comcast Corporation)
• Original Assignee: Comcast Cable Communications LLC (Comcast Corporation)
• Inventors: BOU-ABBOUD, Claude H.
• Granted Patent: US 10,108,905 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level

Abstract

Method of predicting capacity demands on a desired device used to support services for a number of subscribers within a market area having a number of devices. The method includes predicting the capacity demands as a function of historical capacity demands for the desired device and average subscriber capacity demands on the number of devices in the market area.

Claims

1. A method comprising:

determining, by an analysis computing device, a slope of circuit-based bandwidth capacity forecast for a circuit;

determining a slope of a user-based bandwidth capacity forecast for a market area of the circuit;

predicting which of the circuit-based and user-based bandwidth capacity forecasts will be the first to reach a predetermined circuit bandwidth capacity threshold based on their respective slopes; and

outputting an alert message regarding the prediction.

2. The method of claim 1 herein the circuit is a network communications circuit.

3. The method of claim 1 wherein the circuit is a data processing device.

4. The method of claim 1 wherein the circuit is a memory unit.

5. A non-transitory computer-readable medium storing computer-readable instructions that, when executed, cause a system to perform:

determining a slope of historical capacity demand on a circuit;

determining a slope of a bandwidth forecast for the circuit;

determining a predetermined bandwidth capacity threshold;

determining a planned circuit upgrade; and

generating an alert message indicating whether the bandwidth forecast will reach the predetermined bandwidth capacity threshold before the planned circuit upgrade based on the respective slopes of the bandwidth forecast and the predetermined bandwidth capacity.

6. The computer-readable medium of claim 5, further storing instructions for receiving a value associated with the historical capacity demand and receiving a value associated with the average user capacity demand, and automatically predicting a capacity demand as a function thereof.

7. The computer-readable medium of claim 6, further storing instructions to communicate the values to the computer-readable medium for receipt.

8. The computer-readable medium of claim 5, further storing instructions for determining a capacity overload point as a function of the predetermined capacity threshold and predicted capacity demand.

9. The computer-readable medium of claim 8, further storing instructions for determining corrective action as a function of the capacity overload point and predicted capacity demand.

10. The computer-readable medium of claim 8, further storing instructions for calculating a period time until the overload point is surpassed by the predicted capacity demand.

11. The computer-readable medium of claim 5, wherein the desired device is a network communications circuit.

12. The computer-readable medium of claim 5, wherein the desired device is a data processing unit.

13. The computer-readable medium of claim 5, wherein the desired device is a memory unit.

14. The computer-readable medium of claim 5, further storing instructions for averaging the slopes of the historical capacity demand and bandwidth forecast, and determining the predicted capacity demand as a function of the average slope.

15. The computer-readable medium of claim 14, further storing instructions for determining a slope of average user capacity demands as a function of a slope of a user trend, wherein the user trend is associated with a number of users predicted to be supported by the circuit multiplied by a predetermined capacity demand for each user.

16. A method comprising:

determining, by an analysis tool processing device, a slope of historical capacity demand on a circuit;

determining a slope of average user capacity demand in a market area of the circuit; and

predicting a capacity demand on the circuit as a function of the slope of the historical capacity demand on the circuit and the slope of the average user capacity demand in the market area of the circuit.

17. The method of claim 16 further comprising determining a desired capacity threshold for the circuit and determining a capacity overload point as a function of the desired capacity threshold and the predicted capacity demand.

18. The method of claim 17 further comprising determining corrective action as a function of the capacity overload point and the predicted capacity demand.

19. The method of claim 17 further comprising calculating a period of time until the overload point is surpassed by the predicted capacity demand.

20. The method of claim 17, wherein the predicting comprises averaging the slope of the historical capacity demand with the slope of the average user capacity demand.