A Spectrum Status Duration Prediction Method Based on Homotopy Theory for UAV Communication

With the development of wireless communication technology, a large number of spectrum resources are occupied and become increasingly scarce. If drones want to communicate, they need to share spectrum with others. The method of spectrum prediction in cognitive radio can efficiently achieve this. The traditional spectrum status duration prediction method based on the non-stationary hidden Markov model only predict the duration of one fixed geographic location and cannot meet the requirement of UAV's communications. We intend to apply the homotopy theory to the non-stationary hidden Markov model to obtain the spectrum status duration of different locations so that it can apply to UAV's communications. We also conducted experiments to predict the duration of the spectrum status at different locations. The experimental results show that our model can work well.