Visualizing predicted customer bandwidth utilization based on utilization history

1. A method for providing a predicting bandwidth utilization for a customer of a connectivity service provider, the method comprising:

receiving bandwidth utilization data over time for the customer;

training a machine learning model for the bandwidth utilization data during a time period based on the received data, wherein the training the machine learning model comprises determining values for a set of parameters, and wherein the bandwidth utilization is substantially periodic over the time period thereby generating periodically repeated bandwidth utilization patterns observable by the machine learning model; and

predicting, using the trained model, future bandwidth utilization over time, wherein the predicting is based on the periodically repeated bandwidth utilization patterns.

2. The method of claim 1 , further comprising:

providing a visualization of the predicted bandwidth utilization over time to the customer.

3. The method of claim 1 , wherein the time period is a day, a week, or a month.

4. The method of claim 1 , wherein the model is a kernel-based model.

5. The method of claim 1 , wherein the bandwidth utilization data corresponds to a class of service (CoS).

6. The method of claim 1 , wherein the bandwidth utilization data corresponds to one of ingress data or egress data.

7. The method of claim 1 , further comprising:

comparing a previously predicted bandwidth utilization over time for the customer during the time period with a received bandwidth utilization data for the same time period and determining a difference between the two; and

determining whether the difference exceeds a pre-determined threshold value, and

sending, when the difference exceeds the pre-determined threshold value, a notification to the customer.

8. The method of claim 1 , wherein the utilization data corresponds to a portion of the time cycle.

9. The method of claim 1 , wherein the received utilization data corresponds to a duration of a previous time period.

10. A system for providing a predicting bandwidth utilization for a customer of a connectivity service provider, the system comprising:

a utilization database;

a data collector configured to receive bandwidth utilization data from a router within the connectivity service provider and store the received bandwidth utilization data on the utilization database; and

a machine learning server comprising:

a data access module configured to retrieve bandwidth utilization data from the utilization database and the data collector,

a machine learning module configured to train a machine learning model for the bandwidth utilization data during a time period based on the received data, wherein the training the machine learning model comprises determining a value for a parameter, and wherein the bandwidth utilization is substantially periodic over the time period thereby generating periodically repeated bandwidth utilization patterns observable by the machine learning model, and

a prediction module configured to predict, using the trained model, future bandwidth utilization over time, wherein the predicting is based on the periodically repeated bandwidth utilization patterns observable by the machine learning model.

11. The system of claim 10 , wherein the time period is a day, a week, or a month.

12. The system of claim 10 , wherein the model is a kernel-based model.

13. The system of claim 10 , wherein the bandwidth utilization data corresponds to a class of service (CoS).

14. The system of claim 10 , wherein the bandwidth utilization data corresponds to one of ingress data or egress data.

15. A program storage device tangibly embodying a program of instructions executable by at least one machine to perform a method for providing a predicting bandwidth utilization for a customer of a connectivity service provider, the method comprising:

receiving bandwidth utilization data representing a customer's bandwidth utilization;

training a machine learning model for the bandwidth utilization data during a time period based on the received data, wherein the training the machine learning model comprises determining a value for a parameter, and wherein the bandwidth utilization is substantially periodic over the time period thereby generating periodically repeated bandwidth utilization patterns observable by the machine learning model; and

predicting, using the trained model, future bandwidth utilization over time, wherein the predicting is based on the periodically repeated bandwidth utilization patterns.

16. The program storage device of claim 15 , the method further comprising:

providing a visualization of the predicted bandwidth utilization over time to the customer.

17. The program storage device of claim 15 , the method further comprising:

comparing a previously predicted bandwidth utilization over time for the customer during the time period with the received bandwidth utilization data for the same time period; and

in response to determining that a difference between the predicted bandwidth utilization and the received bandwidth utilization data is greater than a predetermined threshold value, sending a notification to the customer.

18. The program storage device of claim 15 , wherein the model is a kernel-based model.

19. The program storage device of claim 15 , wherein the bandwidth utilization data corresponds to a class of service (CoS).

20. The program storage device of claim 15 , wherein the bandwidth utilization data corresponds to one of ingress data or egress data.