Dynamic network resource allocation using multimedia content features and traffic features
A method for dynamically allocating network resources while transferring multimedia at variable bit-rates in a network extracts first content features from the multimedia to determine renegotiation points and observation periods. Second content features and traffic features are extracted from the multimedia bit stream during the observation periods. The second content features and the traffic features are combined in a neural network to predict the network resources to be allocated at the renegotiation points.
1. A method for dynamically allocating network resources while transferring a bit stream in a network, comprising:
extracting first content features from the bit stream to determine renegotiation points and observation periods, in which the bit stream is compressed;
extracting second content features and traffic features from the bit stream during the observation periods; and
combining the second content features and the traffic features to predict the network resources to be allocated at the renegotiation points.
2. The method of claim 1 wherein the bit stream is transferred at a variable bit-rate.
3. The method of claim 1 wherein the bit stream is transferred at piece-wise constant bit-rates.
4. The method of claim 1 wherein the bit stream includes multimedia data.
5. The method of claim 1 wherein the second content features and the traffic features are combined in a prediction neural network.
6. The method of claim 1 further comprising:
identifying a set of candidate features; and
selecting a subset of the candidate features as the second content features and the traffic features.
7. The method of claim 6 wherein the set of candidate features are identified in a training bit stream.
8. The method of claim 6 wherein the subset of features is selected by sequential forward selection.
9. The method of claim 8 further comprising:
evaluating a relevancy of the selected subset of features using a selection neural network.
10. The method of claim 9 wherein the selection neural network is a general regression neural network.
11. The method of claim 6 wherein the subset of features is selected statically prior to transferring the bit stream.
12. The method of claim 6 wherein the subset of features are selected dynamically as the bit stream is transferred.
13. The method of claim 1 further comprising:
classifying a training bit stream into traffic clusters based on the set of candidate features; and
determining a consistency measure for each candidate feature based on said traffic clusters; and
selecting a predetermined number of candidate features with the highest consistency measure as the subset of features.
14. The method of claim 13 further comprising:
determining a mean inter-class distance for each candidate features;
determining a mean intra-class distance for each candidate features; and
dividing the mean inter-class distance by the mean intra-class distance to determine the consistency measure for each content features.
15. The method of claim 6 wherein the selected subset of features include an I-frame spatial complexity, a mean magnitude of acceleration vectors, a mean magnitude of motion vectors, and a spatial variance of the motion vectors.
16. The method of claim 13 wherein the consistency measure considers content features that are related to the traffic features in a monotonic way.
17. The method of claim 15 further comprising:
estimating the I-frame spatial complexity by a weighted sum of magnitudes of AC coefficients for each macroblock of the I-frame.
18. The method of claim 15 further comprising:
subtracting motion vectors from adjacent P frames to form acceleration vectors; and
determining the mean magnitude of the acceleration vectors by:
||
accel
_
||
=
1
M
N
∑
i
j
||
m
→
k
(
i
,
j
)
-
m
→
k
-
1
(
i
,
j
)
||
where {right arrow over (m)} is a forward motion vector for macroblock (i, j) of frame k, and M and N are dimensions of the frame in terms of macroblocks.
19. The method of claim 6 wherein the subset of features is selected by sequential forward selection, and further comprising:
classifying the training bit stream into traffic clusters based on the set subset of features;
determining a consistency measure for feature of the subset of features;
selecting a predetermined number of features of the subset with the highest consistency measure as a final subset of features.
20. The method of claim 1 further comprising:
expressing the traffic features as a vector that includes a maximum allowed arrival rate for bits for various time intervals.
21. The method of claim 5 further comprising:
applying principal component analysis to the subset features; and
providing the first N principal components as input descriptors to the prediction neural network.
22. The method of claim 5 further comprising:
determining cross-correlations between pairs of the subset of features to reduce the size of the subset.
23. The method of claim 8 further comprising:
constructing a plurality of candidate subsets of features;
determining a mean square error between actual and estimated values of features of each candidate subset of features; and
selecting the candidate subset of features with a minimum number of features that yield a lowest mean square error as the subset of features.
24. A system for dynamically allocating network resources while transferring a bit stream in a network, comprising:
a feature extraction unit configured to extract first content features, second content features, and traffic features from the bit stream during the observation periods, in which the bit stream is compressed;
means determining renegotiation points and observation periods in the bit stream from the first content features; and
a prediction neural network configured to combine the second content features and the traffic features to predict the network resources to be allocated at the renegotiation points.