Multi-Channel Multi-Step Spectrum Prediction Using Transformer and Stacked Bi-LSTM

TL;DR

This paper introduces a novel spectrum prediction method combining Transformer and stacked Bi-LSTM to improve accuracy in multichannel, multi-step spectrum forecasting, leveraging attention mechanisms and deep learning architectures.

Contribution

The paper proposes a new multichannel, multi-step spectrum prediction approach using Transformer and stacked Bi-LSTM, enhancing long-term dependence learning.

Findings

Outperforms baseline methods in accuracy

Effective in capturing long-term dependencies

Validated on real simulation data

Abstract

Spectrum prediction is considered as a key technology to assist spectrum decision. Despite the great efforts that have been put on the construction of spectrum prediction, achieving accurate spectrum prediction emphasizes the need for more advanced solutions. In this paper, we propose a new multichannel multi-step spectrum prediction method using Transformer and stacked bidirectional LSTM (Bi- LSTM), named TSB. Specifically, we use multi-head attention and stacked Bi-LSTM to build a new Transformer based on encoder-decoder architecture. The self-attention mechanism composed of multiple layers of multi-head attention can continuously attend to all positions of the multichannel spectrum sequences. The stacked Bi-LSTM can learn these focused coding features by multi-head attention layer by layer. The advantage of this fusion mode is that it can deeply capture the long-term dependence of multichannel spectrum data. We have conducted extensive experiments on a dataset generated by a real simulation platform. The results show that the proposed algorithm performs better than the baselines.