Bandwidth allocation using machine learning

1. A method comprising:

determining, for a terminal in a communication system, an amount of data pending for transmission by the terminal in the communication system;

providing, as input to a machine learning model, data indicative of (i) the amount of data pending for transmission by the terminal and (ii) a status of the communication system, wherein the machine learning model has been trained to predict resource allocation for individual terminals based on input indicative of amounts of data to be transmitted by the respective individual terminals;

receiving one or more outputs from the machine learning model that indicate an amount of bandwidth to allocate to the terminal; and

allocating, to the terminal, resources for the terminal to transmit data in the communication system, wherein the amount of resources allocated is based on the one or more outputs from the machine learning model.

2. The method of claim 1 , wherein the communication system comprises a satellite communication system.

3. The method of claim 1 , wherein the amount of data pending for transmission by the terminal is determined based on a report from the terminal indicating an amount of data transfer backlog for the terminal.

4. The method of claim 3 , wherein the report comprises an indication of an amount of data transfer backlog for the terminal for each of multiple priority levels.

5. The method of claim 1 , wherein allocating bandwidth to the terminal comprises allocating one or more slots in a time division multiple access (TDMA) communication frame.

6. The method of claim 1 , wherein the machine learning model comprises at least one of a neural network, a classifier, a decision tree, a support vector machine, a regression model, a nearest neighbor method such as K-means or K-nearest neighbor, a dimensionality reduction algorithm, or a boosting algorithm.

7. The method of claim 1 , comprising:

determining a number of terminals or a processor utilization; and

determining that the number of terminals or the processor utilization exceeds a threshold;

wherein allocating bandwidth to the terminal based on the one or more outputs from the machine learning model is performed at least in part based on determining that the number of terminals or the processor utilization exceeds a threshold.

8. The method of claim 1 , wherein the machine learning model is provided at least one of a priority of data to be transferred, a type of data to be transferred, a bandwidth limit associated with the terminal, a terminal identifier, a quality of service level, or an error correction rate.

9. The method of claim 1 , comprising providing, to the terminal, an indication of the amount of bandwidth allocated to the terminal.

10. One or more non-transitory machine-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

determining, for a terminal in a communication system, an amount of data pending for transmission by the terminal in the communication system;

providing, as input to a machine learning model, data indicative of (i) the amount of data pending for transmission by the terminal and (ii) a status of the communication system, wherein the machine learning model has been trained to predict resource allocation for individual terminals based on input indicative of amounts of data to be transmitted by the respective individual terminals;

receiving one or more outputs from the machine learning model that indicate an amount of bandwidth to allocate to the terminal; and

allocating, to the terminal, resources for the terminal to transmit data in the communication system, wherein the amount of resources allocated is based on the one or more outputs from the machine learning model.

11. The one or more non-transitory machine-readable of claim 10 , wherein the communication system comprises a satellite communication system.

12. The one or more non-transitory machine-readable of claim 10 , wherein the amount of data pending for transmission by the terminal is determined based on a report from the terminal indicating an amount of data transfer backlog for the terminal.

13. The one or more non-transitory machine-readable of claim 12 , wherein the report comprises an indication of an amount of data transfer backlog for the terminal for each of multiple priority levels.

14. The one or more non-transitory machine-readable of claim 10 , wherein allocating bandwidth to the terminal comprises allocating one or more slots in a time division multiple access (TDMA) communication frame.

15. A system comprising:

one or more processors; and

one or more machine-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

determining, for a terminal in a communication system, an amount of data pending for transmission by the terminal in the communication system;

providing, as input to a machine learning model, data indicative of (i) the amount of data pending for transmission by the terminal and (ii) a status of the communication system, wherein the machine learning model has been trained to predict resource allocation for individual terminals based on input indicative of amounts of data to be transmitted by the respective individual terminals;

receiving one or more outputs from the machine learning model that indicate an amount of bandwidth to allocate to the terminal; and

allocating, to the terminal, resources for the terminal to transmit data in the communication system, wherein the amount of resources allocated is based on the one or more outputs from the machine learning model.

16. The system of claim 15 , wherein the communication system comprises a satellite communication system.

17. The system of claim 15 , wherein the amount of data pending for transmission by the terminal is determined based on a report from the terminal indicating an amount of data transfer backlog for the terminal.

18. The system of claim 17 , wherein the report comprises an indication of an amount of data transfer backlog for the terminal for each of multiple priority levels.

19. The system of claim 15 , wherein allocating bandwidth to the terminal comprises allocating one or more slots in a time division multiple access (TDMA) communication frame.

20. The system of claim 15 , wherein the machine learning model comprises at least one of a neural network, a classifier, a decision tree, a support vector machine, a regression model, a nearest neighbor method such as K-means or K-nearest neighbor, a dimensionality reduction algorithm, or a boosting algorithm.