Date: Wednesday 20th January 2016
Speaker: Ognen Ognenoski, Research Associate, Wireless Multimedia and Networking research group
Chair: Professor Maria Martini, Communications Theme Leader
Title: Communication Theme Presentation – HTTP video streaming adaptation
Despite all the advancements in video compression and transmission technologies, several challenges arise in maintaining the video quality, due to varying transmission conditions. The emerging MPEG-DASH standard for adaptive HTTP video streaming over Internet addresses this challenge via quality adaptation over time.
The talk will address some aspects of HTTP video streaming adaptation, including a novel teletraffic model for adaptive HTTP video streaming systems based on the emerging MPEG-DASH standard. The general functionalities and specifications of the standard’s framework are mapped on the proposed model for which probability-based metrics are derived. In particular, the probabilities of buffer overflow, empty buffer and active buffer are investigated as relevant performance metrics. These metrics describe the MPEG-DASH streaming from the teletraffic viewpoint and are observed for different segment sizes of the encoded video at the server and different buffer sizes at the client. The results show that small segment sizes of the encoded video increase the probabilities of empty buffer and active buffer, while decreasing the probability of buffer overflow, whereas large segment sizes are suitable for decreasing the probabilities of empty buffer and active buffer, while increasing the probability of buffer overflow. Regardless of the segment sizes, the performance metrics are further improved when the buffer size at the client is increased. In the end, the obtained results are discussed in the context of the communication protocol stack used for adaptive HTTP video streaming.