Large-Scale Spectrum Occupancy Learning via Tensor Decomposition and LSTM Networks
This work addresses spectrum management for wireless communication systems, offering an incremental improvement by integrating existing techniques for enhanced correlation modeling.
The paper tackles the problem of predicting large-scale spectrum occupancy by capturing complex correlations in time and frequency, proposing a method that combines tensor decomposition and LSTM networks, which achieves high prediction accuracy and computational efficiency on a synthetic dataset.
A new paradigm for large-scale spectrum occupancy learning based on long short-term memory (LSTM) recurrent neural networks is proposed. Studies have shown that spectrum usage is a highly correlated time series. Moreover, there is a correlation for occupancy of spectrum between different frequency channels. Therefore, revealing all these correlations using learning and prediction of one-dimensional time series is not a trivial task. In this paper, we introduce a new framework for representing the spectrum measurements in a tensor format. Next, a time-series prediction method based on CANDECOMP/PARFAC (CP) tensor decomposition and LSTM recurrent neural networks is proposed. The proposed method is computationally efficient and is able to capture different types of correlation within the measured spectrum. Moreover, it is robust against noise and missing entries of sensed spectrum. The superiority of the proposed method is evaluated over a large-scale synthetic dataset in terms of prediction accuracy and computational efficiency.