Primary User Channel State Prediction Based on Time Series and Hidden Markov Model

Predicting the licensed or primary user (PU) channel state future has been widely investigated in the recent literature, this study introduce a new approach for predicting PU channel state based on time series and hidden Markov model (HMM). In this new approach we model the primary user channel state detection sequence, which can be represented by; PU channel "idle" or "occupied" as a time series switching over the time between two hidden states can be represented by two different random distributions according to the detection sequence. Then, we fed this time series as an observation sequence into the hidden Markov model to predict these switches before they happen so that the secondary user (SU) can adjust its transmission strategies accordingly. The experimental results show that new approach performs very well for predicting the primary users channel state in time domain with low computational complexity.