arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09392cs.MMcs.AI
收藏

LL-GABR:使用强化学习的节能直播视频流

LL-GABR: Energy Efficient Live Video Streaming Using Reinforcement Learning

University at Buffalo(布法罗大学);IBM Research(IBM研究院)

Adithya Raman, Bekir Turkkan, Tevfik Kosar

AI总结:

本文提出基于深度强化学习的直播视频流方法 LL-GABR,通过感知视频质量而非比特率建模 QoE 并结合能耗等指标,在无需额外重训练的情况下,较现有方法提升 44% 感知 QoE 和 73% 能效。

摘要:

近年来,直播视频流自适应比特率(ABR)算法的研究与开发成功提升了用户体验质量(QoE),通过将延迟降至近实时水平,同时提供更高比特率的视频并尽量减少重缓冲时间。然而,这些 ABR 算法使用的 QoE 模型未考虑到大部分直播视频流客户端使用移动设备,在这些设备上更高的比特率并不必然转化为更高的感知质量。忽略感知质量会导致以更高比特率播放视频,但感知视频质量并未显著提升,并因更高的能耗成为电池受限移动设备的负担。本文提出 LL-GABR,一种深度强化学习方法,使用感知视频质量而非比特率对 QoE 进行建模,并将能耗与延迟、重缓冲事件和流畅度等其他指标结合使用。LL-GABR 不对底层视频、环境或网络设置做任何假设,能灵活应用于不同视频,每个视频具有不同的比特率编码阶梯且无需额外重新训练,这与现有基于学习的 ABR 不同。基于轨迹的实验结果表明,LL-GABR 在感知 QoE 方面比最先进方法高出 44%,并因净能耗降低 11% 使能效提升 73%。

英文摘要:

Over the recent years, research and development in adaptive bitrate (ABR) algorithms for live video streaming have been successful in improving users' quality of experience (QoE) by reducing latency to near real-time levels while delivering higher bitrate videos with minimal rebuffering time. However, the QoE models used by these ABR algorithms do not take into account that a large portion of live video streaming clients use mobile devices where a higher bitrate does not necessarily translate into higher perceived quality. Ignoring perceived quality results in playing videos at higher bitrates without a significant increase in perceptual video quality and becomes a burden for battery-constrained mobile devices due to higher energy consumption. In this paper, we propose LL-GABR, a deep reinforcement learning approach that models the QoE using perceived video quality instead of bitrate and uses energy consumption along with other metrics like latency, rebuffering events, and smoothness. LL-GABR makes no assumptions about the underlying video, environment, or network settings and can operate flexibly on different video titles, each having a different bitrate encoding ladder without additional re-training, unlike existing learning-based ABRs. Trace-driven experimental results show that LL-GABR outperforms the state-of-the-art approaches by up to 44% in terms of perceptual QoE and a 73% increase in energy efficiency as a result of reducing net energy consumption by 11%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑