基于强化学习的卫星网络路由方法

Reinforcement Learning Based Routing for Satellite Network

卫星网络的无线信号全球覆盖,已经成为现代通信技术的重要部分。低轨卫星网络因其覆盖范围广、传播时延低等特点受到广泛关注,卫星网络不受地面地理环境因素的限制,对于海洋环境和偏远地区的网络覆盖服务具有不可替代的重要地位,路由在其中至关重要。文章基于OPNET的仿真软件,进行了强化学习路由方法的设计,并且测试得到结果。结果表明,强化学习的路由方法也能同样实现和传统路由路径计算方法的一致效果,并且在输入数据的灵活度上更有优势。

The global coverage of satellite network has become an important part of modern communication technology.Low-orbit satellite network has attracted wide attention due to its features such as wide coverage,low propagation delay,flexible networking mode.Satellite network is not restricted by geographical factors on the ground,and plays an irreplaceable important role in network coverage services in special environment and remote areas,among which routing is crucial.In this paper,based on OPNET simulation software,The reinforcement learning routing method is designed and the test results are obtained.The results show that the reinforcement learning routing method can achieve the same effect as the traditional routing method,and has more advantages in the flexibility of input data.