Measurement of packet delay variation

Details Measurement of packet delay variation Measurement of packet delay variation

2002-07-22

2004-04-27

Kizou, Hassan (Department: 2662)

Multiplex communications

Data flow congestion prevention or control

Control of data admission to the network

C370S232000, C370S412000

Reexamination Certificate

active

06728209

ABSTRACT:

FIELD OF THE INVENTION
This invention relates to communications systems and methods, in particular, to packet communication systems and methods.
REFERENCES
[1] ATM Forum, “Traffic Management Specification Version 4.1”, AF-TM-0121.000, March 1999.
[2] Stallings, “High-Speed Networks—TCP/IP and ATM Design Principles”, Prentice Hall, ISBN 0-13-525965-7, 1998.
The references are provided here to illustrate the state of the art and specific portions of the references are discussed below. The references do not constitute a portion of the invention disclosed herein.
BACKGROUND OF THE INVENTION
Delay and Delay Variation in Packet Communications Systems
Packet communication systems, or networks, are commonly used for the conveyance of information for data applications. In general, these data applications are insensitive to absolute propagation delay (APD—the time it takes for a packet to propagate through the network) and propagation delay variation (PDV—changes in the APD, also known as jitter or wander).
Packet communications systems can also be used for transport of applications that are sensitive to APD and PDV. Examples include:
Direct voice applications such as VoIP
Leased line applications transported via circuit emulation
Video applications
Certain data protocols such as SNA
FIG. 1A
illustrates the general progression from transmit bits
1010
through encapsulation
1014
to transmit packets
1020
through the packet network
1024
to arriving packets
1030
through the JAB
1034
and de-encapsulation
1038
to become a stream of receive bits
1040
. Consider a CBR (Constant Bit Rate) application where the bits are created at constant rate R. The rate R remains constant because there are no pauses in the data stream. The application at the receiving end is typically set to receive and process bits at the same rate R. On the path from creation to processing at the receive end the transmit bits
1010
first arrive at a device that encapsulates them into packets and injects the transmit packets
1020
into a packet network
1024
at rate P. Just as the bits arrive from the application at regular intervals (line
1010
of FIG.
1
B), the encapsulating device
1014
sends out packets at regular interval (line
1020
of FIG.
1
B). However, the intervening packet network is not perfect, so it introduces PDV due to congestion.
In some situations, packets from one set of packets may travel along different routes from point A to point B, increasing PDV. In other cases switches may re-order packets such that packet N, which was sent before packet N+1, arrives after packet N+1 (see for example packets
2
and
3
in line
1030
of FIG.
1
B).
Thus, the arriving packets arrive at a rate that over a large period of time averages out to be creation rate P. But from moment to moment, the receive rate varies as congestion in the network causes variation in the amount of time for a packet to traverse the network. The received packets are processed at the receive end and the encapsulated bits are extracted and placed into the JAB.
Definition and Measurement of CTD and CDV
We will base our definitions of APD and PDV on the existing definitions of Cell Transfer Delay (CTD) and Cell Delay Variation (CDV) for Asynchronous Transfer Mode (ATM) devices. Reference [1] defines CTD as the time that it takes for an ATM cell to traverse the network, and CDV as the range between the minimum and maximum values of CTD. The graph depicting a cell transfer delay probability density model shown in
FIG. 2
is a reproduction of
FIGS. 3-2
from reference [1].
As shown in
FIG. 2
, there is a fixed delay through the network that gives the lower bound on CTD. There is also a variable component that changes based on network conditions. The variable delay is bounded by a maximum value of CTD, above which cells will be discarded because they are too late to use. The difference between the minimum and maximum values of CTD gives the peak-to-peak value of CDV:
CDV
P
=max
CTD
−Fixed Delay  (1)
Since delay and congestion in the network will change over time, a useful measurement of peak-to-peak CDV should be taken over a long period of time. Another way to look at this is in the frequency domain, where we are looking at the low-frequency components of CDV.
Section 3.6.1.2.1 of [1] gives a “one point” means of measuring an estimate of CDV:
The one-point CDV describes the variability in the pattern of cell arrival events observed at a single measurement point with reference to the negotiated peak rate 1/T (as defined in ITU-T Recommendation I.371).
The one-point CDV for cell k (y
k
) at a measurement point is defined as the difference between the cell's reference arrival time (c
k
) and actual arrival time (a
k
) at the measurement point: y
k
=c
k
−a
k
. The reference arrival time (c
k
) is defined as follows:
c
0
=a
0
c
k
+
1
=
{
a
k
+
T
⁢
 
⁢
if
⁢
 
⁢
c
k
≤
a
k
c
k
+
T
⁢
 
⁢
otherwise
Positive values of the one-point CDV correspond to cell clumping; negative values of the one-point CDV correspond to gaps in the cell stream. The reference arrival time defined above eliminates the effect of gaps and provides a measurement of cell clumping.
Note that the value 1/T mentioned above is the same as the rate Constant Bit Rate R mentioned above in connection with FIG.
1
A.
TABLE 1
Example of CDV Calculation
Actual
Reference
One
Arrival
Arrival
Point
Time
Time
CDV
k
A
k
C
k
Y
k
0
0.00
0
0
1
2.09
2.00
−0.09
2
3.95
4.09
0.14
3
6.09
6.09
0.00
4
7.98
8.09
0.11
5
10.06
10.09
0.03
6
11.97
12.09
0.12
7
13.90
14.09
0.19
8
16.10
16.09
−0.01
9
17.97
18.10
0.12
10 
20.06
20.10
0.04
Table 1 shows an example of how this method works, where T has a value of 2 and R has a value of 1/T=½. The estimate of CDV is found by taking the maximum of all of the values of Y
k
, or 0.19 for the values in Table 1.
Note that while this calculation only provides an estimate CDV, it does have the advantage of not requiring an actual measurement of CTD. Its drawback is that it requires a calculation to be made on each packet in order to create an estimate of CDV.
Note on Time Versus Packets Versus Bytes
In different situations it is convenient to discuss the size of the JAB in terms of time, packets or bytes.
Time—Because APD and PDV are normally discussed in units of microseconds (us) or milliseconds (ms), it may useful to discuss the state of the JAB in terms of time.
Packets—It is more convenient to talk about the JAB in terms of packets when considering the current depth or fullness of the JAB.
Bytes—The JAB feeds a circuit interface, so it is drained byte-by-byte. Also a discussion of a physical implementation is also more convenient in terms of bytes.
Here are some useful conversion formulas:
JAB Depth (time)=8*JAB Depth (bytes)/Circuit Bit Rate R (bps)
Packet Period (time)=1/Packet Rate P (pps)
Packet Payload (bytes)=Circuit Bit Rate R (bps)*Packet Period (time)/8
JAB Physical Memory (bytes)=JAB Depth (time)*Circuit Bit Rate R (bps)/8
Examples for common circuits are shown in Table 2 below. The packet periods shown are typical, but they could be higher or lower for a given implementation.
TABLE 2
Comparison of Time, Packets and Bytes for Common Transmission Circuits
Circuit
Packet
Packet
Physical memory (Kbytes) for a
Circuit
Rate
Packet Frame
Payload
Packet
Rate P
JAB of this depth in ms
Type
(Mbps)
Count
(bytes)
Period (&mgr;s)
(pps)
32
64
128
T1
1.544
8
1  
193
1000
1000
6.2
12.4
24.7
T3
44.736
1
2  
699
125
8000
178.9
357.9
715.8
OC3
155.52
0.5
3
1215 
62.5
16000 
622.1
1244.2
2488.3
Notes:
1
8 frames gives a good balance between efficiency (~75% with 50 bytes overhead) and capture delay (1 ms)
2
2 frames would exceed the 1508 byte maximum packet size for Ethernet
This real time measurement of PDV is useful when reported to the user of the service as a metric on the quality of the service provided by the network

Affiliated with

Also associated with

Rating

Measurement of packet delay variation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Measurement of packet delay variation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Measurement of packet delay variation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3190702