Information Technology Reference
In-Depth Information
0.8
0.4
Real
Predicted
Real
Predicted
0.6
0.2
0.4
0
0.2
0
-0.2
-0.2
-0.4
-0.4
-0.6
-0.6
0
10
20
30
40
50
60
0
20
40
60
80
100
120
140
DA2 wavelet coefficients
D1 wavelet coefficients
(e) (f)
Fig. 1.
(
Continued
)
Figure2 shows prediction of “News” traffic after inverse wavelet transform.
11
Predicted
Real
10.9
10.8
10.7
10.6
10.5
10.4
10.3
10.2
10.1
10
0
50
100
150
200
250
300
Fig. 2.
Prediction of “News” traffic after inverse wavelet transform
From Figure 1 and Figure 2, we can see that prediction of the wavelet coefficients
based on wavelet packet decomposition can accurately predict both the variation trend
and the bursty behavior of video traffic, which verifies the validity of this algorithm
on the long-term prediction.
5
Conclusions
In this paper, we propose a real-time video traffic prediction algorithm based on
wavelet packet decomposition. Compared with conventional video traffic prediction
method, the proposed algorithm greatly improves the accuracy of long-term predic-
tion. Owing to the ability of following the trend of the video traffic variation accu-
rately and the capability of capturing bursty traffic of real-time video signal, this
video traffic prediction algorithm provide a new method to realize bandwidth resource
management in a network with long delay and constrained bandwidth.
