A Temporal-Spatial Spectrum Prediction Based on Homotopy Theory for UAVs with Arbitrary Flight Paths
Wenjun Zhou, Shan Luo, Yuwei Zhao, Rongping Lin · 2021 IEEE 21st International Conference on Communication Technology (ICCT) · 2021
The higher demand for wireless communication services has promoted the widespread use of unmanned aerial vehicles (UAVs), but the spectrum resources for UAVs communication are becoming scarce. UAVs can use spectrum prediction to find available frequency bands and share spectrum with other users to solve the problem of spectrum resources shortage. However, due to the rapid speed of UAVs and constantly changing spectral environment, it is difficult to obtain the historical data of the next location in advance. Therefore, the existing methods cannot be well applied to the actual scenario of UVA flying randomly in a certain area. Based on the concept of homotopy theory (HT) and Hidden Markov model (HMM), we propose a new method that first estimates the historical information of the next location, then performs the spectrum prediction at the next moment. We conduct experiments with simulated data, and the results show that the proposed method can effectively predict the spectrum state of UAV flying in a specific area on the premise of obtaining the prior information of limited locations.