Open AccessLearning-based Buffer Starvation Modeling for Packets Prefetching Strategies of Video Streaming Services
Author(s) -
Yu Su,
Shuijie Wang,
Qianqian Cheng,
Yuhe Qiu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1827/1/012128
Subject(s) - computer science , network packet , reinforcement learning , quality of experience , real time computing , computer network , video quality , task (project management) , packet loss , buffer (optical fiber) , transmission (telecommunications) , quality of service , artificial intelligence , telecommunications , metric (unit) , operations management , management , economics
Improving the quality of experience (QoE) of video streaming is a significant task in the wireless network scenario. Buffer starvation in the transmission process will cause playback freeze, and a certain number of packets must be prefetched before the service restarts. Taking into account the shortcomings of buffer in video streaming services, this paper proposes a deep learning-based starvation probability calculation model and a reinforcement learning-based packet prefetching model. The deep learning approach extracts the correlation between different timing inputs through the recurrent neural network module to return an explicit result and the precise distribution of the number of buffer starvation. The reinforcement learning approach leverages a better trade-off between start-up/rebuffering delay and buffer starvation by adjusting the packet prefetching strategy, so that the long-term objective quality of experience (QoE) of the video stream is optimized. Our framework can be applied to actual scenarios including finite video streaming and long video streaming transmission.