[论文解读] TAROT: Towards Optimization-Driven Adaptive FEC Parameter Tuning for Video Streaming

Jashanjot Singh Sidhu, Aman Sahu+1 more|arXiv (Cornell University)|Feb 10, 2026

Network Traffic and Congestion Control被引用 0

一句话总结

TAROT 提出了一种基于优化的跨层 FEC 控制器，可以自适应地调整冗余、块大小和符号化以适应视频分段，从而在流媒体中权衡开销与质量。

ABSTRACT

Forward Error Correction (FEC) remains essential for protecting video streaming against packet loss, yet most real deployments still rely on static, coarse-grained configurations that cannot react to rapid shifts in loss rate, goodput, or client buffer levels. These rigid settings often create inefficiencies: unnecessary redundancy that suppresses throughput during stable periods, and insufficient protection during bursty losses, especially when shallow buffers and oversized blocks increase stall risk. To address these challenges, we present TAROT, a cross-layer, optimization-driven FEC controller that selects redundancy, block size, and symbolization on a per-segment basis. TAROT is codec-agnostic--supporting Reed-Solomon, RaptorQ, and XOR-based codes--and evaluates a pre-computed candidate set using a fine-grained scoring model. The scoring function jointly incorporates transport-layer loss and goodput, application layer buffer dynamics, and block-level timing constraints to penalize insufficient coverage, excessive overhead, and slow block completion. To enable realistic testing, we extend the SABRE simulator 1 with two new modules: a high-fidelity packet-loss generator that replays diverse multi-trace loss patterns, and a modular FEC benchmarking layer supporting arbitrary code/parameter combinations. Across Low-Latency Live (LLL) and Video-on-Demand (VoD) streaming modes, diverse network traces, and multiple ABR algorithms, TAROT reduces FEC overhead by up to 43% while improving perceptual quality by 10 VMAF units with minimal rebuffering, achieving a stronger overhead-quality balance than static FECs.

研究动机与目标

• 解决在不同丢包、吞吐量和缓冲条件下视频流中静态 FEC 配置的低效问题。
• 开发一个跨层 FEC 控制器，使每个分段的参数自适应，以优化开销–质量的权衡。
• 支持编解码器无关的 FEC 方案（Reed-Solomon、RaptorQ、XOR），并集成到现实测试环境中。

提出的方法

• 扩展 SABRE 仿真器，加入高保真、多轨迹包丢失生成器。
• 实现一个模块化的 FEC 基准测试层，允许任意代码/参数组合。
• 使用细粒度评分模型评估预计算候选集，综合考虑传输丢包/吞吐、缓冲动态和块定时约束。
• 评分函数惩罚覆盖不足、开销过大和块完成过慢。
• 在低延迟直播与点播模式下评估性能，改变网络轨迹和不同 ABR 算法。

实验结果

研究问题

• RQ1 如何在每个分段基础上自适应地调整 FEC 参数，以在动态网络条件下提升流媒体效率？
• RQ2 与静态 FEC 配置相比，使用基于优化的跨层 FEC 控制器潜在的开销降低与质量提升是多少？
• RQ3 TAROT 的编解码器无关方法（RS、RaptorQ、XOR）是否能在多样化的流场景中提供鲁棒性能？

主要发现

• 与静态配置相比，FEC 开销降低高达 43%。
• 感知质量大约提升 10 个 VMAF 单位。
• TAROT 在实现更强的开销–质量平衡的同时保持最小化的重复缓冲。