Sim-MSTNet: sim2real based Multi-task SpatioTemporal Network Traffic Forecasting
This addresses data scarcity and multi-task issues in network traffic forecasting for intelligent network operations, representing an incremental improvement with specific gains.
The paper tackles the problem of network traffic forecasting under limited data and multi-task learning challenges like task imbalance and negative transfer, proposing Sim-MSTNet which uses sim2real with domain randomization and attention mechanisms, and it shows improved accuracy and generalization over state-of-the-art baselines in experiments on two datasets.
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.