Hierarchical DRL-empowered Network Slicing in Space-Air-Ground Networks

The space-air-ground integrated network (SAGIN) is an emerging architecture that has the potential to provide seamless, high data rates, and reliable transmission with vastly increased coverage for intelligent edge devices (iEDs). However, the SAGIN infrastructure is quite complex consisting of multiple network segments; it is thus critical to efficiently manage the network segments’ resources to ensure QoS satisfaction (e.g., delay and rate) for the various services provided to the iEDs. In this regard, network slicing (NS) and overall network softwarization technologies can play an essential role in addressing iEDs QoS and utility needs. In this work, we propose an optimal intelligent end-to-end resource allocation with network slicing in multi-tier SAGIN to maximize the network performance. We model the network depending on its service requirements. As the above optimization problem turns out to be NP-hard, we transform it into a stochastic game model and efficiently solve it through hierarchical multi-agent deep reinforcement learning (HMADRL). In particular, we decompose it into two parts, i.e., optimizing the mapping combined with slice adjustment and the resource allocation with association problem. Both problems are then solved using multi-agent DRL. The simulation results demonstrate that our proposed HMADRL algorithm outperforms the baseline algorithms in terms of maximizing the utility and QoS satisfaction of iEDs.