Method to determine average number of packets per burst for transmission of data packets through a network
View Patent ↗The data packets with a maximum allowable delay and an average packet rate are aggregated in a node of the network of a burst and the burst is transmitted with a number of packets. The number of packets per burst is determined by the result of plus/minus twenty percent of the sum of the value one plus a product of the maximum allowable delay, the average packet rate and the value two.
1. A method for transmitting data packets through a communications network, the packets having a maximum allowable delay (mad), and average packet rate (apr) and an average packet size (aps), the method comprising:
aggregating a plurality of data packets in a node of the network into a burst, the burst having an average number of packets; and
transmitting the burst with a link speed (ls) into the network via at least one switch having a number of channels (noc), a switching time (ts) and a given burst blocking probability (bbp),
wherein the average number of packets per burst (ppb) is between an upper and a lower limit,
wherein the upper limit (ppb u ) is calculated with the formula:
80%(1+2· mad·apr )≦ ppb u ≦120%(1+2· mad·apr ), and
wherein the lower limit (ppb l ) is calculated with the formula:
80
%
·
t
s
E
noc
-
1
(
bbp
)
apr
-
aps
ls
≤
ppb
l
≤
120
%
·
t
s
E
noc
-
1
(
bbp
)
apr
-
aps
ls
where E noc −1 is an inverse Erlang B formula for the noc.
2. The method according to claim 1 , wherein the number of packets per burst is within the lower limit.
3. The method according to claim 1 , wherein the number of packets per burst is within the upper limit.
4. The method according to claim 1 , wherein the average burst size (abs) is abs=aps·ppb.
5. The method according to claim 4 ,
wherein during the aggregation of packets a burst size is compared to a value and if the burst size is equal to or exceed this value, the burst is transmitted,
wherein the value is in the range between ±20%·abs.
6. The method according to claim 4 , wherein the packets are aggregated into a buffer, the minimum size of the buffer is determined by aps·(ppb−d), where d is a constant between 0 and 5.
7. The method according to claim 6 , wherein d is equal to 1.
8. The method according to claim 4 , wherein the packets are aggregated into a buffer, the maximum size of the buffer is determined by aps·(ppb+e), where e is a constant between 0 and 5.
9. The method according to claim 8 , wherein e is equal to 1.
10. The method according to claim 1 , wherein when the packet is stored, a random binary digit with a probability for a first and second value of the binary digit is generated and compared with the first value of the binary digit, if equal the stored packets are sent as a burst, the probability for the first value is determined by:
1
ppb
.
11. The method according to claim 1 , wherein an average burst rate is determined by:
apr
ppb
.
12. The method according to claim 1 , wherein an average burst rate is determined by:
1
1
apr
+
2
·
mad
.
13. The method according to claim 1 , wherein the average burst rate(abr) is determined by:
abr
≤
E
noc
-
1
(
bbp
)
ts
+
td
where td is a burst duration time.
14. The method according to claim 1 , wherein the packets are Internet Protocol (IP) packets.
15. The method according to claim 1 , wherein the network is formed as an Optical Burst Switched network.
16. The method according to claim 1 , wherein the node is an edge node of the network.
17. The method according to claim 13 , wherein the burst is transformed and sent by the edge node as and optical burst into the Optical Burst Switched network.