Transfer Learning for Channel Quality Prediction

The ability to predict the quality of a wireless channel is essential for enabling anticipatory networking tasks. Traditional channel quality prediction problems encompass predicting future conditions based on past measurements of the same channel. In this paper we study the channel quality prediction problem across different wireless channels. To this extent, we consider a reference scenario including multiple 4G cells, each of which operates on multiple concurrent frequency carriers. We propose a framework based on transfer learning to predict the channel quality of a given frequency carrier when no or minimal information is available on the very same frequency carrier for model training. For the transfer learning task we use convolutional neural networks and long short-term memory networks. We compare their performance against statistical methods on a dataset collected from a commercial 4G mobile radio network. The performance evaluation carried out on the reference dataset demonstrates the validity of the proposed transfer learning approach, achieving a root mean squared error of 0.3 on average.