TAROT: Towards Optimization-Driven Adaptive FEC Parameter Tuning for Video Streaming

2026-02-10

AI Summary

Static forward error correction (FEC) struggles to adapt to dynamic network conditions, often resulting in excessive redundancy or insufficient protection that degrades video streaming quality. This work proposes TAROT, a cross-layer adaptive FEC controller that dynamically adjusts redundancy, block size, and symbolization strategy per video segment through a joint optimization model driven by both transport- and application-layer metrics. TAROT is the first system to enable real-time parameter tuning across multiple coding schemes—Reed-Solomon, RaptorQ, and XOR—and introduces a high-fidelity packet loss replay framework alongside a modular benchmarking infrastructure. Experimental results demonstrate that, in both low-latency live streaming and video-on-demand scenarios, TAROT reduces overhead by up to 43% compared to static FEC, improves VMAF scores by 10 points, and virtually eliminates rebuffering events.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

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.

Problem

• Forward Error Correction
• adaptive streaming
• parameter tuning
• packet loss
• video quality

Innovation

• adaptive FEC
• optimization-driven control
• cross-layer design
• dynamic redundancy tuning
• video streaming quality