Recurrent Neural Networks for Transmission Opportunity Forecasting

One of the major challenges in opportunistic networks is the correct identification of a transmission opportunity and its corresponding duration. In this work, recurrent neural network structures are investigated for transmission opportunity forecast. The proposed method is based on in-channel spectrum sensing and the use of Elman recurrent neural network to model the occupation of the channel. The results, based on real experiment measurements, using a Software Defined Radio for monitoring of a Wi-Fi channel shows that, in the evaluated scenarios even a small neural network is able to achieves 99.9% of correct transmission opportunity identification rate.