A study on deep reinforcement learning algorithms for inter-satellite communication link scheduling in low-Earth orbit
TL;DR
Experimental results demonstrate that this link scheduling model based on deep reinforcement learning exhibits superior performance in reducing transmission delay, enhancing system throughput, and improving load balancing, thereby validating its effectiveness and adaptability in complex inter-satellite link scheduling scenarios.
Abstract
Artificial intelligence-driven intelligent algorithms have demonstrated excellent adaptive optimization capabilities in complex network scheduling problems. To address the issues of dynamic topological changes and insufficient resource allocation efficiency in LEO satellite inter-satellite communication link scheduling, this study proposes a link scheduling model based on deep reinforcement learning. Building upon a dynamic time-varying network model, a Markov decision process is introduced to describe the scheduling process, and a deep neural network is employed to achieve a nonlinear mapping from states to actions. By integrating delay, throughput, and load balancing metrics through a multi-objective reward function, the scheduling strategy is optimized. Experimental results demonstrate that this method exhibits superior performance in reducing transmission delay, enhancing system throughput, and improving load balancing, thereby validating its effectiveness and adaptability in complex inter-satellite link scheduling scenarios.