用仿真数据提升小样本下的多任务流量预测精度
Sim-MSTNet: sim2real based Multi-task SpatioTemporal Network Traffic Forecasting
- 通过仿真生成数据并用领域随机化缩小真实与仿真数据差距
- 在两个数据集上优于现有方法，显著提升预测准确率和泛化能力
- 适合网络运维中数据稀缺场景的多服务类型流量预测
网络流量预测在智能网络运维中至关重要，但现有方法在数据有限时表现不佳。多任务学习在建模不同服务类型时也面临任务不平衡和负迁移问题。为此，我们提出Sim-MSTNet，一种基于sim2real范式的多任务时空流量预测模型。该方法利用模拟器生成合成数据，有效缓解数据稀缺导致的泛化性能下降问题。通过双层优化（样本权重与模型训练）实现领域随机化，降低合成数据与真实数据之间的分布差异。同时，Sim-MSTNet采用注意力机制选择性地在任务间共享知识，并引入动态损失加权以平衡各任务目标。在两个开源数据集上的大量实验表明，Sim-MSTNet持续优于当前最优基线，在准确率和泛化能力上均有提升。
原文摘要 · Abstract (English)
Network traffic forecasting plays a crucial role in intelligent network operations, but existing techniques often perform poorly when faced with limited data. Additionally, multi-task learning methods struggle with task imbalance and negative transfer, especially when modeling various service types. To overcome these challenges, we propose Sim-MSTNet, a multi-task spatiotemporal network traffic forecasting model based on the sim2real approach. Our method leverages a simulator to generate synthetic data, effectively addressing the issue of poor generalization caused by data scarcity. By employing a domain randomization technique, we reduce the distributional gap between synthetic and real data through bi-level optimization of both sample weighting and model training. Moreover, Sim-MSTNet incorporates attention-based mechanisms to selectively share knowledge between tasks and applies dynamic loss weighting to balance task objectives. Extensive experiments on two open-source datasets show that Sim-MSTNet consistently outperforms state-of-the-art baselines, achieving enhanced accuracy and generalization.
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。