Expectation-Maximization for Scheduling Problems in Satellite Communication

In this paper we address unsupervised machine learning for two use cases in satellite communication, which are scheduling problems: (i) Kaband frequency plan optimization and (ii) dynamic configuration of an active antenna array satellite. We apply approaches based on the ExpectationMaximization (EM) framework to both of them. We compare against baselines of currently deployed solutions, and show that they can be significantly outperformed by the EMbased approach. In addition, the approaches can be applied incrementally, thus supporting fast adaptation to small changes in the input configuration.