Inferring radio type from clustering algorithms
Described embodiments provide systems and methods for inferring a network type and network conditions. The system includes a packet capturing engine configured to capture a plurality of network packets from a plurality of TCP network connections. The system includes a packet analyzer configured to analyze the plurality of network packets to generate a plurality of metrics. The system includes a network classifier configured to infer network types of the plurality of TCP connections based on the plurality of metrics and at least one classification model. The system also includes a conditions ranking engine configured to estimate a level of network congestion for each TCP connection based on the plurality of metrics and the network types.
1. A method comprising:
determining, by a device, an inter-arrival interval or an inter-sending interval between packets received via a transport layer connection;
selecting, from a plurality of thresholds, a threshold based on the inter-arrival interval or the inter-sending interval, each threshold of the plurality of thresholds determined using intervals between packets corresponding to a respective type of network; and
identifying, from the plurality of types of networks, a type of network for the transport layer connection based at least on the threshold.
2. The method of claim 1 , wherein the inter-arrival interval or the inter-sending interval used to determine the threshold is within a range of interval times.
3. The method of claim 1 , wherein the inter-arrival interval or the inter-sending interval is within a range of averages of interval times.
4. The method of claim 1 , further comprising determining a plurality of inter-arrival intervals or inter-sending intervals by determining, for each of a plurality of packets, a respective inter-arrival interval or inter-sending interval between a packet and a preceding or subsequent packet, and wherein determining the inter-arrival interval or the inter-sending interval between packets includes determining the inter-arrival interval or the inter-sending interval from the plurality of inter-arrival intervals or inter-sending intervals.
5. The method of claim 1 , wherein the type of network is one of a mobile network or a fixed network.
6. The method of claim 1 , wherein the type of network is one of a 2G, 3G, 4G or 5G network.
7. The method of claim 1 , further comprising identifying the type of network by using the inter-arrival interval or the inter-sending interval as an input to a classifier.
8. A device comprising:
one or more processors, coupled to memory, and configured to:
identify an inter-arrival interval or the inter-sending interval between packets received via a transport layer connection;
select, from a plurality of thresholds, a threshold based on the inter-arrival interval or the inter-sending interval, each threshold of the plurality of thresholds determined using intervals between packets corresponding to a respective type of network; and
identify, from the plurality of types of networks, a type of network for the transport layer connection based at least on the threshold.
9. The device of claim 8 , wherein the inter-arrival interval or the inter-sending interval used to determine the threshold is within a range of interval times.
10. The device of claim 8 , wherein the inter-arrival interval or the inter-sending interval is within a range of averages of interval times.
11. The device of claim 8 , wherein the one or more processors are further configured to determine a plurality of inter-arrival intervals or inter-sending intervals by determining, for each of a plurality of packets, a respective inter-arrival interval or inter-sending interval between a packet and a preceding or subsequent packet, and wherein determining the inter-arrival interval or inter-sending interval between packets includes determining the inter-arrival interval or inter-sending interval from the plurality of inter-arrival intervals or inter-sending intervals.
12. The device of claim 8 , wherein the type of network is one of a mobile network or a fixed network.
13. The device of claim 8 , wherein the type of network is one of a 2G, 3G, 4G or 5G network.
14. The device of claim 8 , wherein the one or more processors are further configured to identify the type of network by using the inter-arrival interval or the inter-sending interval as an input to a classifier.
15. A non-transitory computer readable medium storing program instructions for causing one or more processors to:
identify an inter-arrival interval or the inter-sending interval between packets received via a transport layer connection;
select, from a plurality of thresholds, a threshold based on the inter-arrival interval or the inter-sending interval, each threshold of the plurality of thresholds determined using intervals between packets corresponding to a respective type of network; and
identify, from the plurality of types of networks, a type of network for the transport layer connection based at least on the threshold.
16. The non-transitory computer readable medium of claim 15 , wherein the inter-arrival interval or the inter-sending interval used to determine the threshold is within a range of interval times.
17. The non-transitory computer readable medium of claim 15 , wherein the inter-arrival interval or the inter-sending interval is within a range of averages of interval times.
18. The non-transitory computer readable medium of claim 15 , wherein the program instructions further cause the one or more processors to identify the type of network by using the inter-arrival interval or the inter-sending interval as an input to a classifier.
19. The non-transitory computer readable medium of claim 15 , wherein the type of network is one of a mobile network or a fixed network.
20. The non-transitory computer readable medium of claim 15 , wherein the type of network is one of a 2G, 3G, 4G or 5G network.