A. Al-Tahmeesschi, K. Umebayashi, H. Iwata, J. Lehtomäki and M. López-Benítez, "Feature-Based Deep Neural Networks for Short-Term Prediction of WiFi Channel Occupancy Rate," in IEEE Access, vol. 9, pp. 85645-85660, 2021, doi: 10.1109/ACCESS.2021.3088423
Feature-based deep neural networks for short-term prediction of WiFi channel occupancy rate
|Author:||Al-Tahmeesschi, Ahmed1; Umebayashi, Kenta1; Iwata, Hiroki1;|
1Department of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology, Tokyo 183-8538, Japan
2Centre for Wireless Communications (CWC), University of Oulu, 90570 Oulu, Finland
3Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool L69 3GJ, U.K.
4ARIES Research Centre, Antonio de Nebrija University, 28040 Madrid, Spain
|Online Access:||PDF Full Text (PDF, 2 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2021101250681
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2021-10-12
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.
|Pages:||85645 - 85660|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
213 Electronic, automation and communications engineering, electronics
This work was supported by the European Commission in the framework of the H2020-EUJ-02-2018 project 5G-Enhance (Grant agreement no. 815056), by "Strategic Information and Communications R&D Promotion Programme (SCOPE)" of Ministry of Internal Affairs and Communications (MIC) of Japan (Grant no. JPJ000595). The work of J. Lehtomäki was supported by the Academy of Finland 6Genesis Flagship (grant no. 318927). The work of M. López-Benítez was supported by British Council under UKIERI DST Thematic Partnerships 2016-17 (ref. DST-198/2017).
|EU Grant Number:||
(815056) 5G-Enhance - 5G Enhanced Mobile Broadband Access Networks in Crowded Environments
|Academy of Finland Grant Number:||
318927 (Academy of Finland Funding decision)
© The Authors 2021. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.