[Yixuan Ban Notes]Machine Learning Based Rate Adaptation With Elastic Feature Selection For HTTP-Based Streaming

2017-09-09

Posted by 班怡璇

Challenges:

  1. The video quality experienced by a client is determined by many conflicting performance metrics which is difficult to find a way to optimize all of them.
  2.  All the algorithms now are derived according to high-level intuition, which do not take all comprehensive factors into consideration, yet only use one or few factors as their input.

Specific Method:

  1. To cope with these problems above, the writer proposed a machine learning adaptive streaming over HTTP (MLASH)
  2. The method trains a classification model for any existing rate adaptation algorithm to improve them(use them to label the best rate rather than predict).
  3. Unlike the previous methods that utilize the estimated information, this approach adopts the true information to train.
  4. The writer uses the latest k segments to train. The first k-1 segments are used as features and the true k-th segment’s rate is used as the corresponding result. As for the features considered in the model, the writer uses 1>estimated bandwidth(LSB,SAB,WAB and variation) 2> buffer size(current and maximal) 3> RTT 4>current video rate.
  5. Two things are worth noting here: 1> the model can be offline or online 2> to keep the model flexible, the server can use its preferable labeling algorithm(expected best rate)
  6. Labeling algorithm: 1>bandwidth-based 2>buffer-considered 3>smooth rate adaptation(absence of buffer-based)

Evaluation:

  1. The traces are provided by an article ” Measuring DASH streaming performance from the end users perspective using neubot”in MMSys. The buffer size is set to 10 seconds and the segment is about 2 seconds.
  2. The writer compares the MLASH with 4 methods: 1>bandwidth-based adaptation 2>buffer-based adaptation 3>rate smoothness-based adaptation 4>buffer-based adaptation(d sec). The first 3 methods use 3 measures SAB,LAB,WAB as the estimate of bandwidth.
  3. Because the buffer-based approach dose not consider the bandwidth, the MLASH alternately combines with the first 3 methods and compares it with the 4 methods above. (3 experiments)
  4. The metric are average rate, average prediction error, rebuffer rate and over estimation rate.
  5. The last experiment is the curve of prediction error caused by the training data of the 3 methods.(to explore the convergence of training process)

Conclusion:

This paper is organized clearly. The challenges and methods are all listed orderly. But the innovation is little I think.