Method for congestion detection in packet transmission networks

1. A method for measuring a degree of packet congestion on a channel of a packet communication network, comprising:

simulating a degree of packet congestion on a channel of a packet communication network, the packet communication network having a plurality of measurable features;

repeatedly varying each of the plurality of measurable features of the packet communication network and simulating the degree of packet congestion on the channel of the packet communication network a predetermined number of times to determine a mathematical relationship between the degree of packet congestion on the channel and each varied measurable feature of the network;

periodically measuring the plurality of measurable features during a subsequent normal operating mode of the packet communication network; and

applying the mathematical relationship to the periodically measured plurality of measurable features to determine an actual degree of congestion on the channel of the packet communication network; and

wherein the actual degree of congestion on the channel is compared to a predetermined threshold;

wherein packet traffic is controlled or shaped to reduce packet congestion if the actual degree of congestion on the channel exceeds the predetermined threshold; and

wherein the packet traffic is controlled based on controlling for an average arrival time between two interfering signals and an average duration of interfering signals.

2. The method of claim 1 wherein the degree of packet congestion on the channel is a saturation level of the channel.

3. The method of claim 2 wherein the saturation level is a function of packet arrival rate at a receiver on the channel and total packet throughput on the channel.

4. The method of claim 3 wherein the function is that if there is a set of decreases in the packet arrival rates at each receiver that produces an increase in the total throughput, the channel is at the saturation level of the channel.

5. The method of claim 1 wherein the measurable features of the network comprise at least one of:

a time delay between transmission starts of a station on the channel and termination of the previously transmitted packet from such station;

a fraction of time the channel is busy with transmissions, regardless of the origin of the transmission or whether packets were correctly transmitted and received; and

an average number of packet transmission retries on the channel.

6. The method of claim 1 wherein the packet communication network is an 802.11 wireless network.

7. The method of claim 1 wherein the actual degree of congestion on the channel is compared to a predetermined threshold.

8. The method of claim 7 wherein packet traffic is controlled or shaped to reduce packet congestion if the actual degree of congestion on the channel exceeds the predetermined threshold.

9. The method of claim 1 wherein the measurable features comprise:

a time delay between transmission starts of a station on the channel and termination of a previously transmitted packet from the station;

a fraction of time the channel is busy with transmissions; and

an average number of packet transmission retries on the channel.

10. The method of claim 1 wherein the varied measurable features of the network include at least one of:

system loading in numbers of client VoIP/Video stream stations;

channel quality in terms of Frame Error Rate under various corresponding signal-to-noise ratios;

interference; and

traffic type.

11. The method of claim 1 wherein packet traffic is controlled by adjusting present packet traffic to mitigate congestion.

12. The method of claim 1 further comprising:

determining which of noise, congestion, or both noise and congestion are main causes of packet congestions; and

predicting packet congestion based on a classification approach utilizing a boundary of saturated and unsaturated points throughout all simulations.

13. An access point configured to measure packet congestion, the access point utilizing a method to measure packet congestion comprising:

simulating a degree of packet congestion on a channel of a packet communication network, the packet communication network having a plurality of measurable features;

repeatedly varying each of the plurality of measurable features of the packet communication network and simulating the degree of packet congestion on the channel of the packet communication network a predetermined number of times to determine a mathematical relationship between the degree of packet congestion on the channel and each varied measurable feature of the network;

periodically measuring the plurality of measurable features during a subsequent normal operating mode of the packet communication network; and

applying the mathematical relationship to the periodically measured plurality of measurable features to determine an actual degree of congestion on the channel of the packet communication network; and

the actual degree of congestion on the channel is compared to a predetermined threshold;

packet traffic is controlled or shaped to reduce packet congestion if the actual degree of congestion on the channel exceeds the predetermined threshold; and

the packet traffic is controlled based on controlling for an average arrival time between two interfering signals at a duration exponentially distributed with an average duration of interfering signals.

14. The access point of claim 13 wherein:

the degree of packet congestion on the channel is a saturation level of the channel;

the saturation level is a function of packet arrival rate at a receiver on the channel and total packet throughput on the channel; and

the function is that if there is a set of decreases in the packet arrival rates at each receiver that produces an increase in the total throughput, the channel is at the saturation level of the channel.

15. The access point of claim 13 wherein packet traffic is controlled by adjusting present packet traffic to mitigate congestion.

16. An access point configured to measure packet congestion, the access point utilizing a method to measure packet congestion comprising:

simulating a degree of packet congestion on a channel of a packet communication network, the packet communication network having a plurality of measurable features;

repeatedly varying each of the plurality of measurable features of the packet communication network and simulating the degree of packet congestion on the channel of the packet communication network a predetermined number of times to determine a mathematical relationship between the degree of packet congestion on the channel and each varied measurable feature of the network;

periodically measuring the plurality of measurable features during a subsequent normal operating mode of the packet communication network; and

applying the mathematical relationship to the periodically measured plurality of measurable features to determine an actual degree of congestion on the channel of the packet communication network; and

controlling packet traffic by controlling for an average arrival time between interfering signals and an average duration of interfering signals when the actual degree of congestion is over or at a pre-determined threshold.

17. The access point of claim 16 wherein the method to measure packet congestion further comprises:

determining which of noise, congestion, or both noise and congestion are main causes of packet congestions; and

predicting packet congestion based on a classification approach utilizing a boundary of saturated and unsaturated points throughout all simulations.