Hierarchical Meta-Learning Models with Deep Neural Networks for Spectrum Assignment

In this paper, we consider a data-driven approach and apply machine learning methods to facilitate frequency assignment. Specifically, an hierarchical meta-learning architecture, which harness the predictive capability of both statistical and deep learning approaches, is proposed to predict a diverse range of spectrum usage patterns. Using spectrum measurement, network simulations are conducted to evaluate the effectiveness of the proposed architecture. It is shown that the hierarchical meta-learning models with deep recurrent neural networks have great potential for predicting spectrum usage patterns to facilitate multi-tier spectrum assignment.