Method and apparatus for deriving a packet select probability value
View Patent ↗A method and apparatus for deriving a packet select probability value for a data packet. The method comprises determining a queue length value for a target buffer of the data packet, calculating a queue congestion value based at least partly on the queue length value and a packet select queue length range, and calculating the packet select probability value for the data packet based at least partly on an exponential function e −x , where x is computed based at least partly on the queue congestion value.
1. A data packet routing device comprising a signal processing component, the signal processing component configured to:
receive an indication of a data packet received at the data packet routing device;
determine a queue length value for a target buffer of the data packet;
calculate a queue congestion value based at least partly on the queue length value and a packet select queue length range;
calculate a packet select probability value for the data packet based at least partly on an exponential function e −x , where x is computed based at least partly on the queue congestion value; and
select the data packet based on the packet select probability value, wherein the data packet routing device drops or queues the data packet based on the selection of the data packet by the signal processing component.
2. The data packet routing device of claim 1 , wherein the queue congestion value Q con is calculated based on:
Q
con
=
max
TH
-
Av
max
TH
-
min
TH
where Av represents the determined queue length value, maxTH represents a maximum queue length threshold and minTH represents a minimum queue length threshold;
maxTH-minTH defining the packet select queue length range.
3. The data packet routing device of claim 1 , wherein x is further computed based on an aggressiveness factor K, such that x=K*Q con .
4. The data packet routing device of claim 3 , wherein the aggressiveness factor K comprises a user configurable aggressiveness factor.
5. The data packet routing device of claim 3 , wherein the aggressiveness factor K comprises an adaptively configurable aggressiveness factor.
6. The data packet routing device of claim 1 , wherein the queue length value comprises an average queue length for the target buffer of the data packet.
7. The data packet routing device of claim 6 , wherein the queue length value Av is calculated based on:
Av=Ao *(1−2 −n )+ Qc *(2 −n )
where n represents a user configurable weighting factor, Ao represents a previously determined average queue length value and Qc represents a current queue length.
8. The data packet routing device of claim 1 , wherein the signal processing component is further configured to: determine a class of traffic to which the data packet belongs, obtain a set of active queue management parameters for the determined class of traffic, and derive a packet select probability value for the data packet based at least partly on the obtained set of active queue management parameters.
9. The data packet routing device of claim 8 , wherein the set of active queue management parameters comprises at least one from a group comprising at least one of:
a maximum queue length threshold maxTH;
a minimum queue length threshold minTH; and
an aggressiveness factor K.
10. The data packet routing device of claim 1 , wherein the signal processing component implements a random early detection active queue management process using the packet select probability value.
11. A non-transitory computer program product comprising executable program code stored therein for deriving a packet select probability value for a data packet and selecting the data packet based on the packet select probability value, the program code executable to:
receive an indication of receipt of the data packet;
determine a queue length value for a target buffer of the data packet;
calculate a queue congestion value based at least partly on the queue length value and a packet select queue length range;
calculate the packet select probability value for the data packet based at least partly on an exponential function e −x , where x is computed based at least partly on the queue congestion value;
select the data packet based on the packet select probability value; and
drop or queue the data packet based on the selection of the data packet.
12. The non-transitory computer program product of claim 11 , wherein the non-transitory computer program product comprises at least one from a group including: a hard disk, a CD-ROM, an optical storage device, a magnetic storage device, a Read Only Memory, ROM, a Programmable Read Only Memory, PROM, an Erasable Programmable Read Only Memory, EPROM, an Electrically Erasable Programmable Read Only Memory, EEPROM, and a Flash memory.
13. The non-transitory computer program product of claim 11 , wherein the queue congestion value Q con is calculated based on:
Q
con
=
max
TH
-
Av
max
TH
-
min
TH
where Av represents the determined queue length value, maxTH represents a maximum queue length threshold and minTH represents a minimum queue length threshold;
maxTH-minTH defining the packet select queue length range.
14. The non-transitory computer program product of claim 11 , wherein x is further computed based on an aggressiveness factor K, such that x=K*Q con .
15. The non-transitory computer program product of claim 14 , wherein the aggressiveness factor K comprises a user configurable aggressiveness factor.
16. The non-transitory computer program product of claim 14 , wherein the aggressiveness factor K comprises an adaptively configurable aggressiveness factor.
17. The non-transitory computer program product of claim 11 , wherein the queue length value comprises an average queue length for the target buffer of the data packet.
18. The non-transitory computer program product of claim 17 , wherein the queue length value Av is calculated based on:
Av=Ao *(1−2 −n )+ Qc *(2 −n )
where n represents a user configurable weighting factor, Ao represents a previously determined average queue length value and Qc represents a current queue length.