Device throughput determination
In one example, a system for device throughput determination includes a monitor engine to monitor an average packet size at a node of a cellular network designated for a device and a channel quality between the device and the node of the cellular network, a classification engine to classify the device based on the monitored average packet size at the node designated for the device and the channel quality, a prediction engine to predict a throughput for the device over a quantity of future transmission time intervals (TTI) based on the classification of the device and a number of resources requested by the device over a period of time.
1. A system for device throughput determination, comprising:
a monitor engine to monitor an average packet size at a node of a cellular network designated for a device and a channel quality between the device and the node of the cellular network;
a classification engine to classify the device based on the monitored average packet size at the node designated for the device and the channel quality; and
a prediction engine to predict a throughput for the device over a quantity of future transmission time intervals (TTI) based on the classification of the device and a number of resources requested by the device over a period of time; and
wherein the number of resources requested by the device is calculated based on a quotient of the average packet size at the node of the cellular network designated for the device and a transport block size.
2. The system of claim 1 , wherein the classification engine compares the number of resources requested by the device to a threshold value to classify the device.
3. The system of claim 1 , wherein the classification engine determines the transport block size for the device for the TTI under the monitored channel quality.
4. The system of claim 1 , wherein the prediction engine utilizes a linear function of a product of sub-frame share for the device and the monitored average packet size at the node of the cellular network designated for the device to predict the throughput for the device over the quantity of future TTIs.
5. The system of claim 1 , wherein the monitor engine determines a quantity of packets arriving at the node of the cellular network designated for the device in a single TTI.
6. The system of claim 1 , wherein the monitor engine monitors the channel quality between the device and the node of the cellular network for each TTI.
7. A non-transitory computer readable medium storing instructions executable by a processor for device throughput determination, wherein the instructions are executable to:
assign a classification to each of a plurality of devices communicating with a node of a cellular network based on a quantity of resources demanded by each of the plurality of devices communicating with the node, wherein the quantity of resources demanded by each of the plurality of devices communicating with the node is calculated based on a quotient of an average size of application packets at the node of the cellular network designated for each of the plurality of devices and a transport block size;
determine a sub-frame share for each of the plurality of devices communicating with the node of the cellular network based on the classification assigned to each of the plurality of devices; and
calculate a predicted throughput for each of the plurality of devices based on a product of the sub-frame share and the average size of application packets arriving at the node for each of the plurality of devices.
8. The medium of claim 7 , wherein the predicted throughput for each of the plurality of devices is calculated separately for each of the plurality of devices.
9. The medium of claim 7 , comprising instructions executable to monitor the average packet arrival rate for each of the plurality of devices and the average packet size of application packets arriving at the node for each of the plurality of devices.
10. The medium of claim 7 , wherein the predicted throughput is calculated with a linear function of a product of the sub-frame share and the average size of application packets over a period of time.
11. A method for device throughput determination, comprising:
determining a plurality of devices that are associated with a node of a cellular network;
classifying each of the plurality of devices based on a quantity of resources demanded by each of the plurality of devices from the node per a transmission time interval (TTI), wherein the quantity of resources demanded by each of the plurality of devices from the node is calculated based on a quotient of an average size of application packets at the node of the cellular network designated for each of the plurality of devices and a transport block size;
calculating a per-user resource share for each of the plurality of devices based on a sub-frame share and the average size of application packets received by each device over the TTI; and
calculating a predicted throughput individually for each of the plurality of devices associated with the node based on a linear function of the per-user resource share.
12. The method of claim 11 , wherein the quantity of resources demanded by one of the plurality of devices is less than the transport block size assigned to the one of the plurality of devices.
13. The method of claim 11 , comprising determining an application type utilized by each of the plurality of devices.
14. The method of claim 13 , wherein determining the application type includes determining the average size of application packets received by each device over the period of time based on the determined application type.