Adaptive closed loop congestion avoidance and control

1. A method comprising:

receiving, from a mobility management device, user device information, wherein the user device information includes a location associated with a user device and an identifier of a base station associated with the location of the user device;

receiving, from the base station, load information associated with the base station;

determining, based on the user device information and the load information, whether congestion is predicted at the base station;

performing traffic throttling in response to determining that congestion is predicted, wherein performing the traffic throttling comprises:

instructing an application server associated with the user device to throttle traffic destined for the base station when the predicted congestion is at a first level, and

instructing the base station to throttle traffic originating from the user device and to block traffic destined for the user device when the predicted congestion is at a second level, wherein the second level is higher than the first level;

determining, based on the load information, a schedule for adjusting the traffic throttling; and

adjusting the traffic throttling based on the schedule.

2. The method of claim 1 , wherein the user device information includes an indication of the application server associated with the user device.

3. The method of claim 1 , further comprising:

determining, based on the load information and a congestion threshold associated with the base station, a level associated with the predicted congestion.

4. The method of claim 1 , wherein the load information includes an indication of a predicted duration of a congestion period, and wherein the schedule is based on the predicted duration of the congestion period.

5. The method of claim 4 , wherein the predicted duration of the congestion period is based on historic and heuristic network traffic and congestion data.

6. The method of claim 1 , wherein the load information includes an overall load associated with the base station and loads per type of user device attached to the base station.

7. The method of claim 1 , wherein the schedule includes a throttle back-off schedule.

8. A system comprising:

a memory to store instructions; and

one or more processors configured to execute the instructions to:

receive, from a mobility management device, user device information,

wherein the user device information includes a location associated with a user device and an identifier of a base station associated with the location;

receive, from the base station, load information associated with the base station;

determine, based on the user device information and the load information, whether congestion is predicted at the base station;

perform, based on the user device information, traffic throttling in response to determining the congestion is predicted,

wherein, when performing the traffic throttling, the one or more processors are configured to execute the instructions to:

instruct an application server associated with the user device to throttle traffic destined for the base station when the predicted congestion is at a first level, and

instruct the base station to throttle traffic originating from the user device and to block traffic destined for the user device when the predicted congestion is at a second level, wherein the second level is higher than the first level;

determine, based on the load information, a schedule for adjusting the traffic throttling; and

adjust the traffic throttling based on the schedule.

9. The system of claim 8 , wherein the user device information includes an indication of the application server associated with the user device.

10. The system of claim 8 , wherein the one or more processors is further configured to execute the instructions to:

determine, based on the load information and a congestion threshold associated with the base station, a level associated with the predicted congestion.

11. The system of claim 8 , wherein the load information includes an indication of a predicted duration of a congestion period, and wherein the schedule is based on the predicted duration of the congestion period.

12. The system of claim 11 , wherein the predicted duration of the congestion period is based on historic and heuristic network traffic and congestion data.

13. The system of claim 8 , wherein the load information includes an overall load associated with the base station and loads per type of user device attached to the base station.

14. The system of claim 8 , wherein the schedule includes a throttle back-off schedule.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by a processor, cause the processor to:

receive, from a mobility management device, user device information, wherein the user device information includes a location associated with the user device and an identifier of a base station associated with the location;

receive, from the base station, load information associated with the base station;

determine, based on the user device information and the load information, whether congestion is predicted at the base station;

perform traffic throttling in response to determining the congestion is predicted, wherein the one or more instructions that cause the processor to perform the traffic throttling includes one or more instructions that cause the processor to:

instruct an application server associated with the user device to throttle traffic destined for the base station when the predicted congestion is at a first level, and

instruct the base station to throttle traffic originating from the user device and to block traffic destined for the user device when the predicted congestion is at a second level, wherein the second level is higher than the first level;

determine a schedule for adjusting the traffic throttling; and

adjust the traffic throttling based on the schedule.

16. The non-transitory computer-readable medium of claim 15 , wherein the user device information includes an indication of the application server associated with the user device.

17. The non-transitory computer-readable medium of claim 15 , wherein the instructions further comprise:

one or more instructions that cause the processor to determine a level associated with the predicted congestion based on the load information and a congestion threshold associated with the base station.

18. The non-transitory computer-readable medium of claim 15 , wherein the load information includes an indication of a predicted duration of a congestion period, and wherein the schedule is based on the predicted duration of the congestion period.

19. The non-transitory computer-readable medium of claim 18 , wherein the predicted duration of the congestion period is based on historic and heuristic network traffic and congestion data.

20. The non-transitory computer-readable medium of claim 15 , wherein the schedule includes a throttle back-off schedule.