Machine Learning (ML)-based network models provide fast and accurate predictions for complex network behaviors but require substantial training data. Collecting such data from real networks is often costly and limited, especially for critical scenarios like failures. As a result, researchers commonly rely on simulated data, which reduces accuracy when models are deployed in real environments. We propose a hybrid approach leveraging transfer learning to combine simulated and real-world data. Using RouteNet-Fermi, we show that fine-tuning a pre-trained model with a small real dataset significantly improves performance. Our experiments with OMNeT++ and a custom testbed reduce the Mean Absolute Percentage Error (MAPE) in packet delay prediction by up to 88%. With just 10 real scenarios, MAPE drops by 37%, and with 50 scenarios, by 48%.

翻译：基于机器学习（ML）的网络模型能够为复杂网络行为提供快速而准确的预测，但需要大量训练数据。从真实网络中收集此类数据通常成本高昂且数量有限，尤其在故障等关键场景下。因此，研究者通常依赖仿真数据，但这会导致模型部署到真实环境时准确性下降。我们提出一种结合迁移学习的混合方法，以融合仿真数据与真实世界数据。通过使用RouteNet-Fermi模型，我们证明使用少量真实数据集对预训练模型进行微调可显著提升性能。我们在OMNeT++仿真平台与定制化测试平台上进行的实验表明，该方法将数据包延迟预测的平均绝对百分比误差（MAPE）最高降低了88%。仅使用10个真实场景时，MAPE下降37%；使用50个场景时，MAPE下降48%。