Dynamic Power Allocation in High Throughput Satellite Communications: A Two-Stage Advanced Heuristic Learning Approach

The dynamic radio resource management technology is an essential technology in high throughput satellite (HTS) communications. Aiming at the problem that the traditional static radio resource allocation is difficult to meet the dynamic traffic, the dynamic radio resource allocation based on the meta-heuristic algorithm has been extensively studied. Since wireless channel conditions, differentiated services have stochastic properties, and the environment's dynamics are unknown in HTS, the dynamic radio resource allocation based on model-free deep reinforcement learning (DRL) method was used to learn the optimal policy through interactions with the situation. However, the generalization ability of the existing DRL cannot fully meet the great dynamic change in HTS. To address this issue, we explore an advanced heuristic learning approach that combines DRL with one heuristic algorithm. In the proposed approach, we apply the DRL to accelerate the convergence of the heuristic algorithm and verify the proposed method in the dynamic power allocation (DPA) in HTS. Compared with the traditional methods, the simulation results show that the proposed approach can accelerate the convergence of the heuristic method for the allocation of power in HTS and has a low time complexity of the decision. Compared with the traditional methods, our proposed method can reduce the computational overhead by 6.2–94.8%.