Joint beam hopping and coverage control optimization algorithm for multibeam satellite system

Joint beam hopping and coverage control optimization algorithm for multibeam satellite system

Blog Article

To improve the performance of multibeam satellite (MBS) systems, a deep reinforcement learning-based algorithm to jointly optimize the beam hopping and coverage control (BHCC) algorithm for MBS was proposed.Firstly, the resource allocation problem in MBS was transformed to a multi-objective optimization problem with the objective maximizing the system throughput and minimizing the packet loss rate of the MBS.Secondly, the MBS environment was characterized as a tonic shower cap multi-dimensional matrix, and the objective problem was modelled as a Markov decision process considering stochastic communication requirements.Finally, the objective problem was solved by combining the powerful feature extraction and learning capabilities of deep reinforcement learning.

In addition, a single-intelligence polling multiplexing mechanism was proposed to reduce the search space and convergence difficulty and accelerate the training of BHCC.Compared with the genetic algorithm, the simulation results read more show that BHCC improves the throughput of MBS and reduces the packet loss rate of the system, greedy algorithm, and random algorithm.Besides, BHCC performs better in different communication scenarios compared with a deep reinforcement learning algorithm, which do not consider the adaptive beam coverage.