OFDM系统中基于内容感知的SVC视频流调度算法

Content Aware Scheduling Algorithm for SVC Streaming over OFDM

针对多用户视频流在下行正交频分多址(Orthogonal Frequency Division Multiplexing,OFDM)系统中的资源调度问题,重点研究基于可伸缩视频编码(Scalable Video Coding,SVC)的视频流调度机制。SVC作为一种具有空间、时间和质量3个维度的可伸缩性视频编码方案,能够为视频流在无线环境中提供灵活的传输方式,因此,研究提出一种OFDM系统中基于内容感知的SVC视频流调度算法,充分考虑不同SVC视频流分组的优先级与延迟约束,并利用OFDM技术在无线资源(时域、频域及功率)分配上的灵活性对分组进行调度。最后,研究通过仿真实验,对比了基于内容感知的SVC视频流调度算法与传统算法的性能特性,仿真结果表明所提出的调度机制相对于传统算法最高有3.2d B的平均峰值信噪比(PSNR,Peak Signal to Noise Ratio)增益。

In this paper, we study the problem of packet scheduling and resource allocation for multi-user video streaming over downlink orthogonal frequency division multiplexing （OFDM） wireless channels. The video streams are pre-coded using the scalable video coding （SVC） scheme which offers spatial, temporal and quality scalabilities. SVC provides flexible solutions for transmission over wireless networks. Hence, we propose a content aware scheduling algorithm, which prioritizes the scheduling by considering distortion impact, deadline requirements and fully exploits the flexibility of resource allocation provided by the OFDM technology in terms of time, frequency and power. Our experimental results demonstrate that the proposed algorithm outperforms the benchmark algorithms with a gain of as much as 3.2dB in terms of average peak signal to noise ratio （PSNR）.