Study of Spectrum Prediction Techniques in Cognitive Radio Networks

Suriya, M; G, Sumithra M.

doi:10.1109/icaccs54159.2022.9785289

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, deep learning has shown its promising capability in spectrum prediction, with high precision, strong robustness, and adaptability. Recurrent neural network (RNN)-based methods (Long Short-Term Memory (LSTM) and gated recurrent unit network (GRU)) [ 17 ] are capable of mining underlying temporal correlations among spectrum data. In [ 18 ], LSTM was employed to simultaneously predict the Radio Spectrum State (RSS) for two time slots, which requested a large amount of computing resources and suffers from very long training time.…”

Section: Introductionmentioning

confidence: 99%

A Deep Long-Term Joint Temporal–Spectral Network for Spectrum Prediction

Wang,

Hu,

Jiang

et al. 2024

Sensors

View full text Add to dashboard Cite

Spectrum prediction is a promising technique to release spectrum resources and plays an essential role in cognitive radio networks and spectrum situation generating. Traditional algorithms normally focus on one-dimensional or predict spectrum values in a slot-by-slot manner and thus cannot fully perceive the spectrum states in complex environments and lack timeliness. In this paper, a deep learning-based prediction method with a simple structure is developed for temporal–spectral and multi-slot spectrum prediction simultaneously. Specifically, we first analyze and construct spectrum data suitable for the model to simultaneously achieve long-term and multi-dimensional spectrum prediction. Then, a hierarchical spectrum prediction system is developed that takes advantage of the advanced Bi-ConvLSTM and the seq2seq framework. The Bi-ConvLSTM captures time–frequency characteristics of spectrum data, and the seq2seq framework is used for long-term spectrum prediction. Furthermore, the attention mechanism is used to address the limitations of the seq2seq framework that compresses all inputs into fixed-length vectors, resulting in information loss. Finally, the experimental results have shown that the proposed model has a significant advantage over the benchmark schemes. Especially, the proposed spectrum prediction model achieves 6.15%, 0.7749, 1.0978, and 0.9628 in MAPE, MAE, RMSE, and R2, respectively, which is better than all the baseline deep learning models.

show abstract

Section: Introductionmentioning

confidence: 99%