LTE interference detection and mitigation for Wi-Fi links
A method of adjusting a communication link of a client device of a wireless local area network is described. The method includes monitoring two or more communication links between two or more client devices and a network device in a wireless local area network. The two or more client devices including a first client device and a second client device. The method also includes detecting a degradation in a first communication link between the first client device and the network device. The communication link degradation is not detected in a second communication link between the second client device and the network device. The method further includes determining the degradation in the first communication link is caused at least in part by interference from cellular network communications. The method includes adjusting one or more parameters of the first communication link without affecting the second communication link in response to determining the degradation is cause at least in part by the interference from the cellular network communications.
1. A method comprising:
monitoring, by a network device, two or more communication links between two or more client devices and the network device in a wireless local area network, the two or more client devices including a first client device and a second client device;
detecting, by the network device, a degradation in a first communication link between the first client device and the network device and no degradation in a second communication link between the second client device and the network device;
determining, by the network device, the degradation in the first communication link is caused at least in part by an interference from cellular network communications,
wherein determining the degradation in the first communication link is caused by the interference from cellular network communications is based on one or more of a first distribution of excessive retries, a second distribution of short retries, and a third distribution of long retries, and wherein determining that the degradation in the first communication link is caused by the interference from cellular network communications further includes:
training a machine learning program based on a first plurality of statistical data of the first communication link acquired in a second plurality of predefined intervals of time, wherein each statistical data includes the first distribution of excessive retries, the second distribution of short retries, and the third distribution of long retries, acquired in each of the second plurality of predefined intervals of time, wherein the machine learning program includes a neural network having an input layer, the input layer having a first number of nodes equal to a sum of a number of excessive retries, a number of short retries, and a number of long retries, wherein the neural network includes an output layer with one or more nodes, and wherein the neural network includes a predetermined number of hidden layers; and
applying the first distribution of excessive retries, the second distribution of short retries, and the third distribution of long retries, acquired in a predefined interval of time different from the second plurality of predefined intervals of time to the trained machine-learning program to determine an interference in the predefined interval of time is caused by cellular network communications; and
adjusting, by the network device, one or more parameters of the first communication link without affecting the second communication link in response to determining the degradation is caused at least in part by the interference from the cellular network communications.
2. The method of claim 1 , wherein the adjustment includes reducing a bandwidth of the first communication link.
3. The method of claim 1 , wherein the first communication link comprises a primary channel and a secondary channel, and wherein the method further comprises:
reducing, by the network device, a bandwidth of the secondary channel.
4. The method of claim 3 , wherein reducing the bandwidth of the secondary channel includes releasing the secondary channel.
5. The method of claim 1 , wherein detecting the degradation is based on one or more of a first distribution of excessive retries, a second distribution of short retries, and a third distribution of long retries in a predefined interval of time or for a predetermined number of transmitted packets.
6. A network device, comprising:
a memory; and
a processor executing instructions from the memory to:
monitor two or more communication links between two or more client devices and the network device in a wireless local area network, the two or more client devices including a first client device and a second client device;
detect a degradation in a first communication link between the first client device and the network device;
determine the degradation in the first communication link is caused at least in part by an interference from cellular network communications,
wherein determining the degradation in the first communication link is caused by the interference from cellular network communications is based on one or more of a first distribution of excessive retries, a second distribution of short retries, and a third distribution of long retries, and wherein determining that the degradation in the first communication link is caused by the interference from cellular network communications further includes:
train a machine learning program based on a first plurality of statistical data of the first communication link acquired in a second plurality of predefined intervals of time, wherein each statistical data includes the first distribution of excessive retries, the second distribution of short retries, and the third distribution of long retries, acquired in each of the second plurality of predefined intervals of time, wherein the machine learning program includes a neural network having an input laver, the input laver having a first number of nodes equal to a sum of a number of excessive retries, a number of short retries, and a number of long retries, wherein the neural network includes an output laver with one or more nodes, and wherein the neural network includes a predetermined number of hidden layers; and
apply the first distribution of excessive retries, the second distribution of short retries, and the third distribution of long retries, acquired in a predefined interval of time different from the second plurality of predefined intervals of time to the trained machine-learning program to determine an interference in the predefined interval of time is caused by cellular network communications;
determine no degradation in a second communication link between the second client device and the network device caused by interference from the cellular network communications; and
adjust one or more parameters of the first communication link without affecting the second communication link in response to determining the degradation is caused at least in part by the interference from the cellular network communications.
7. The network device of claim 6 , wherein the adjustment includes reducing a bandwidth of the first communication link, wherein by reducing the bandwidth, a modification to a modulation and coding scheme or a modification to a number of spatial streams is avoided.
8. The network device of claim 6 , wherein the first communication link comprises a primary channel and a secondary channel, and wherein the processor executes instructions to:
reduce a bandwidth of the secondary channel.
9. The network device of claim 8 , wherein reducing the bandwidth of the secondary channel includes releasing the secondary channel.
10. The network device of claim 6 , wherein to detect the degradation is further based on one or more of excessive retries, short retries, and long retries in a predefined interval of time or for a predetermined number of transmitted packets.
11. The network device of claim 6 , wherein to determine the degradation in the first communication link is caused by the interference from cellular network communications is further based on one or more of excessive retries, short retries, and long retries.
12. A non-transitory machine-readable storage medium encoded with instructions executable by at least one processor of a network device, the machine-readable storage medium comprising instructions to:
monitor two or more communication links between two or more client devices and the network device in a wireless local area network, the two or more client devices including a first client device and a second client device;
detect a degradation in a first communication link between the first client device and the network device;
determine the degradation in the first communication link is caused at least in part by an interference from cellular network communications,
wherein determining the degradation in the first communication link is caused by the interference from cellular network communications is based on one or more of a first distribution of excessive retries, a second distribution of short retries, and a third distribution of long retries, and wherein determining that the degradation in the first communication link is caused by the interference from cellular network communications further includes:
training a machine learning program based on a first plurality of statistical data of the first communication link acquired in a second plurality of predefined intervals of time, wherein each statistical data includes the first distribution of excessive retries, the second distribution of short retries, and the third distribution of long retries, acquired in each of the second plurality of predefined intervals of time, wherein the machine learning program includes a neural network having an input layer, the input layer having a first number of nodes equal to a sum of a number of excessive retries, a number of short retries, and a number of long retries, wherein the neural network includes an output layer with one or more nodes, and wherein the neural network includes a predetermined number of hidden layers; and
applying the first distribution of excessive retries, the second distribution of short retries, and the third distribution of long retries, acquired in a predefined interval of time different from the second plurality of predefined intervals of time to the trained machine-learning pro-ram to determine an interference in the predefined interval of time is caused by cellular network communications;
determine a degradation in a second communication link between the second client device and the network device is caused by another network device; and
adjust one or more parameters of the first communication link without affecting the second communication link in response to determining the degradation is caused at least in part by the interference from the cellular network communications.
13. The non-transitory machine-readable storage medium of claim 12 , wherein the adjustment includes reducing a bandwidth of the first communication link.
14. The non-transitory machine-readable storage medium of claim 12 , wherein the first communication link comprises a primary channel and a secondary channel, and wherein the processor further executes instructions to:
reduce a bandwidth of the secondary channel.
15. The non-transitory machine-readable storage medium of claim 14 , wherein to reduce the bandwidth of the secondary channel includes to release the secondary channel.
16. The non-transitory machine-readable storage medium of claim 12 , wherein to detect the degradation is further based on one or more of excessive retries, short retries, and long retries in a predefined interval of time or for a predetermined number of transmitted packets.
17. The non-transitory machine-readable storage medium of claim 12 , wherein to determine the degradation in the first communication link is caused by interference from cellular network communications is further based on one or more of excessive retries, short retries, and long retries.