Edge networking devices and systems for identifying a software application
Edge networking router devices and systems for identifying a software application are described herein. One or more embodiments include an edge networking router device for identifying a software application comprising a packet collector to receive packet data in the edge networking router device and an artificial intelligence (AI) model configured to process the packet data received by the packet collector to identify the software application, wherein the artificial intelligence (AI) model is trained using a cloud entity and received from the cloud entity.
1. A thin edge networking router device, coupling one or more network links to one or more end devices, for identifying a software application, comprising:
a packet collector to receive packet data in the thin edge networking router device; and
a model configured to:
process the packet data received by the packet collector to identify the software application, wherein the model is trained using a cloud entity and received from the cloud entity, wherein the model uses a decision tree and includes at least one of a source port or a destination port to identify the software application from another software application; and
calculate a probability that the model correctly identified the software application, wherein the thin edge networking router device requests a new version of the model from the cloud entity in response to the probability that the model correctly identified the software application reaching a threshold.
2. The device of claim 1 , wherein the packet collector sends the packet data to the cloud entity to train the new version of the model.
3. The device of claim 1 , wherein the model is received from the cloud entity in response to the model completing training.
4. The device of claim 1 , wherein the model is updated according to a schedule.
5. The device of claim 1 , wherein the model assigns the software application to one or more categories in response to identifying the software application.
6. A thin edge networking router device, coupling one or more network links to one or more end devices, for identifying a software application, comprising:
a packet collector to receive packet data; and
a model configured to:
process the packet data received by the packet collector to identify the software application, wherein the model is trained using a cloud entity, and wherein the model uses a decision tree and includes at least one of a source port or a destination port to identify the software application from another software application;
generate a command in response to identifying the software application; and
calculate a probability that the model correctly identified the software application, wherein the thin edge networking router device requests a new version of the model from the cloud entity in response to the probability that the model correctly identified the software application reaching a threshold.
7. The device of claim 6 , wherein the command prioritizes the software application.
8. The device of claim 7 , wherein the software application receives network resources in response to the command prioritizing the software application.
9. The device of claim 7 , wherein the software application receives one or more of increased network bandwidth, increased link quality, or increased number of links in response to the command prioritizing the software application.
10. The device of claim 6 , wherein the command restricts the software application.
11. The device of claim 6 , wherein the command limits network bandwidth allocated to the software application.
12. The device of claim 6 , wherein the command directs the software application to a particular network.
13. The device of claim 12 , wherein increased quality of service (QoS) is provided in the particular network.
14. The device of claim 12 , wherein decreased quality of service (QoS) is provided in the particular network.
15. A system for identifying a software application, comprising:
a cloud entity configured to train a model using packet sample data; and
a thin edge networking router device, coupling one or more network links to one or more end devices, configured to:
capture packet data;
receive the model to process the packet data to identify the software application, and wherein the model uses a decision tree and includes at least one of a source port or a destination port to identify the software application from another software application; and
calculate a probability that the model correctly identified the software application, wherein the thin edge networking router device requests a new version of the model from the cloud entity in response to the probability that the model correctly identified the software application reaching a threshold.
16. The system of claim 15 , wherein the cloud entity is an element management server or device management server.
17. The system of claim 15 , wherein the packet sample data is collected from a number of edge devices.
18. The system of claim 15 , wherein the model assigns the software application to one or more categories.
19. The system of claim 18 , wherein network resources allocated to the software application can increase or decrease in response to the one or more categories the model assigns the software application to.