Feature-Based Deep Neural Networks for Short-Term Prediction of WiFi Channel Occupancy Rate



Al-Tahmeesschi, Ahmed, Umebayashi, Kenta, Iwata, Hiroki, Lehtomaki, Janne and Lopez-Benitez, Miguel ORCID: 0000-0003-0526-6687
(2021) Feature-Based Deep Neural Networks for Short-Term Prediction of WiFi Channel Occupancy Rate. IEEE ACCESS, 9. pp. 85645-85660.

[img] Text
IEEE_Access_2021_2.pdf - Author Accepted Manuscript

Download (4MB) | Preview

Abstract

Spectrum occupancy prediction is a key enabling technology to facilitate a proactive resource allocation for dynamic spectrum management systems. This work focuses on the prediction of duty cycle (DC) metric that reflects spectrum usage (in the time domain). The spectrum usage is typically measured on a shorter time scale than needed for prediction. Hence, data thinning is required and we apply block averaging. However, averaging operation results in flattening the DC data and losing essential features to assist deep neural network (DNN) to predict the spectrum usage. To improve DC prediction after block averaging, a feature-based deep learning framework is proposed. Namely, long short-term memory (LSTM) and gated recurrent unit (GRU) are selected and enhanced by using features of the data, such as the variance of DC data in addition to DC data themself. The proposed model is capable of proactively predicting the spectrum usage by capturing complex relationships among various input features for the measured spectrum, thus providing higher prediction accuracy with an average improvement of 5% in RMSE compared with traditional models. Moreover, to have a better understanding of the proposed model, we quantify the effect of input features on the predicted spectrum usage values. Based on the most significant input features, a simpler and more efficient model is proposed to estimate DC with similar accuracy to when using all features.

Item Type: Article
Uncontrolled Keywords: Predictive models, Neural networks, Deep learning, Autoregressive processes, Resource management, Wireless fidelity, Time series analysis, 5G, deep neural networks, explainable AI, GRU, LSTM, occupancy rate, SHAP, short-term prediction, spectrum awareness, WiFi
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 01 Jun 2021 14:46
Last Modified: 15 Mar 2024 06:08
DOI: 10.1109/ACCESS.2021.3088423
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3124744