基于残差学习的XR网络流量与体验质量预测框架
ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality
- 分两阶段建模：主模型加残差分支，分别处理流量预测与体验风险估计
- 流量预测误差降低17.84%，体验风险估计误差降低87.8%
- 支持加密流量分析，适合网络运维与XR服务优化场景
我们提出ResLearn-XR，一种用于预测扩展现实（XR）网络流量并评估体验质量（QoE）风险的残差学习框架。该框架采用两阶段时间建模结构，包含基础序列预测模型及任务特异的残差学习组件，以提升对突发性、非平稳的XR流量动态的适应能力。残差学习在值空间用于连续流量预测，在对数几率空间用于概率性QoE风险估计。针对QoE风险分支，我们引入数据描述符算法（DDA），一个因果特征构建模块，将应用层包级可观测数据转换为帧时序感知的描述符，适用于加密流量分析。我们还构建了XR Traffic-QoE数据集，包含连续的XR流量轨迹与会话级用户报告的QoE标签。ResLearn-XR在帧数、帧大小和帧间间隔预测中，最大减少SMAPE 17.84%；在QoE风险估计中，相较单阶段基线最大减少SMAPE 87.8%。
原文摘要 · Abstract (English)
We present ResLearn-XR, a residual learning framework for predicting eXtended Reality (XR) network traffic and estimating Quality-of-Experience (QoE) risk. ResLearn-XR adopts a two-stage temporal learning structure comprising a base sequence prediction model augmented with task-specific residual learning components to improve adaptability to bursty, non-stationary XR traffic dynamics. The residual learning stages operate in the value space for continuous XR traffic forecasting and in the logit space for probabilistic QoE risk estimation. \rev{For the QoE-risk branch, we introduce a Data Descriptor Algorithm (DDA), a causal feature-construction module that converts packet-level application-layer observables into frame-timing-aware descriptors suitable for encrypted traffic analysis. We also construct an XR Traffic-QoE dataset that pairs continuous XR traffic traces with session-level user-reported QoE labels. ResLearn-XR reduces SMAPE by up to 17.84% across frame-count, frame-size, and inter-arrival-time prediction, while reducing QoE-risk estimation SMAPE by up to 87.8% over single-stage baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。