Neural adaptive video streaming with pensieve

Hongzi Mao, Ravi Netravali, Mohammad Alizadeh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

425 Scopus citations

Abstract

Client-side video players employ adaptive bitrate (ABR) algorithms to optimize user quality of experience (QoE). Despite the abundance of recently proposed schemes, state-of-the-art ABR algorithms suffer from a key limitation: they use fixed control rules based on simplified or inaccurate models of the deployment environment. As a result, existing schemes inevitably fail to achieve optimal performance across a broad set of network conditions and QoE objectives. We propose Pensieve, a system that generates ABR algorithms using reinforcement learning (RL). Pensieve trains a neural network model that selects bitrates for future video chunks based on observations collected by client video players. Pensieve does not rely on pre-programmed models or assumptions about the environment. Instead, it learns to make ABR decisions solely through observations of the resulting performance of past decisions. As a result, Pensieve automatically learns ABR algorithms that adapt to a wide range of environments and QoE metrics.We compare Pensieve to state-of-theart ABR algorithms using trace-driven and real world experiments spanning a wide variety of network conditions, QoE metrics, and video properties. In all considered scenarios, Pensieve outperforms the best state-of-the-art scheme, with improvements in average QoE of 12%-25%. Pensieve also generalizes well, outperforming existing schemes even on networks for which it was not explicitly trained.

Original languageEnglish (US)
Title of host publicationSIGCOMM 2017 - Proceedings of the 2017 Conference of the ACM Special Interest Group on Data Communication
PublisherAssociation for Computing Machinery, Inc
Pages197-210
Number of pages14
ISBN (Electronic)9781450346535
DOIs
StatePublished - Aug 7 2017
Externally publishedYes
Event2017 Conference of the ACM Special Interest Group on Data Communication, SIGCOMM 2017 - Los Angeles, United States
Duration: Aug 21 2017Aug 25 2017

Publication series

NameSIGCOMM 2017 - Proceedings of the 2017 Conference of the ACM Special Interest Group on Data Communication

Other

Other2017 Conference of the ACM Special Interest Group on Data Communication, SIGCOMM 2017
Country/TerritoryUnited States
CityLos Angeles
Period8/21/178/25/17

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Electrical and Electronic Engineering
  • Communication

Keywords

  • Bitrate adaptation
  • Reinforcement learning
  • Video streaming

Fingerprint

Dive into the research topics of 'Neural adaptive video streaming with pensieve'. Together they form a unique fingerprint.

Cite this