
Machine learning enabled Wi-Fi saturation sensing for fair coexistence in unlicensed spectrum
- Author
- Merkebu Girmay (UGent) , Adnan Shahid (UGent) , Vasilis Maglogiannis (UGent) , Dries Naudts (UGent) and Ingrid Moerman (UGent)
- Organization
- Abstract
- In the past few years, machine learning (ML) techniques have been extensively applied to provide efficient solutions to complex wireless network problems. As such, Convolutional Neural Network (CNN) and Q-learning based ML techniques are most popular to achieve harmonized coexistence of Wi-Fi with other co-located technologies such as LTE. In the existing coexistence schemes, a co-located technology selects its transmission time based on the level of Wi-Fi traffic generated in its collision domain which is determined by either sniffing the Wi-Fi packets or using a central coordinator that can communicate with the co-located networks to exchange their status and requirements through a collaboration protocol. However, such approaches for sensing traffic status increase cost, complexity, traffic overhead, and reaction time of the coexistence schemes. As a solution to this problem, this work applies a ML-based approach that is capable to determine the saturation status of a Wi-Fi network based on real-time and over-the-air collection of medium occupation statistics about the Wi-Fi frames without the need for decoding. In particular, inter-frame spacing statistics of Wi-Fi frames are used to develop a CNN model that can determine Wi-Fi network saturation. The results demonstrate that the proposed ML-based approach can accurately classify whether a Wi-Fi network is saturated or not.
- Keywords
- Wireless fidelity, Long Term Evolution, 5G mobile communication, Wireless sensor networks, Wireless networks, Sensors, Analytical models, Wi-Fi saturation, traffic load estimation, coexistence, unlicensed spectrum, machine learning, convolutional neural networks
Downloads
-
7871.pdf
- full text (Published version)
- |
- open access
- |
- |
- 1.91 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8703420
- MLA
- Girmay, Merkebu, et al. “Machine Learning Enabled Wi-Fi Saturation Sensing for Fair Coexistence in Unlicensed Spectrum.” IEEE ACCESS, vol. 9, 2021, pp. 42959–74, doi:10.1109/ACCESS.2021.3066052.
- APA
- Girmay, M., Shahid, A., Maglogiannis, V., Naudts, D., & Moerman, I. (2021). Machine learning enabled Wi-Fi saturation sensing for fair coexistence in unlicensed spectrum. IEEE ACCESS, 9, 42959–42974. https://doi.org/10.1109/ACCESS.2021.3066052
- Chicago author-date
- Girmay, Merkebu, Adnan Shahid, Vasilis Maglogiannis, Dries Naudts, and Ingrid Moerman. 2021. “Machine Learning Enabled Wi-Fi Saturation Sensing for Fair Coexistence in Unlicensed Spectrum.” IEEE ACCESS 9: 42959–74. https://doi.org/10.1109/ACCESS.2021.3066052.
- Chicago author-date (all authors)
- Girmay, Merkebu, Adnan Shahid, Vasilis Maglogiannis, Dries Naudts, and Ingrid Moerman. 2021. “Machine Learning Enabled Wi-Fi Saturation Sensing for Fair Coexistence in Unlicensed Spectrum.” IEEE ACCESS 9: 42959–42974. doi:10.1109/ACCESS.2021.3066052.
- Vancouver
- 1.Girmay M, Shahid A, Maglogiannis V, Naudts D, Moerman I. Machine learning enabled Wi-Fi saturation sensing for fair coexistence in unlicensed spectrum. IEEE ACCESS. 2021;9:42959–74.
- IEEE
- [1]M. Girmay, A. Shahid, V. Maglogiannis, D. Naudts, and I. Moerman, “Machine learning enabled Wi-Fi saturation sensing for fair coexistence in unlicensed spectrum,” IEEE ACCESS, vol. 9, pp. 42959–42974, 2021.
@article{8703420, abstract = {{In the past few years, machine learning (ML) techniques have been extensively applied to provide efficient solutions to complex wireless network problems. As such, Convolutional Neural Network (CNN) and Q-learning based ML techniques are most popular to achieve harmonized coexistence of Wi-Fi with other co-located technologies such as LTE. In the existing coexistence schemes, a co-located technology selects its transmission time based on the level of Wi-Fi traffic generated in its collision domain which is determined by either sniffing the Wi-Fi packets or using a central coordinator that can communicate with the co-located networks to exchange their status and requirements through a collaboration protocol. However, such approaches for sensing traffic status increase cost, complexity, traffic overhead, and reaction time of the coexistence schemes. As a solution to this problem, this work applies a ML-based approach that is capable to determine the saturation status of a Wi-Fi network based on real-time and over-the-air collection of medium occupation statistics about the Wi-Fi frames without the need for decoding. In particular, inter-frame spacing statistics of Wi-Fi frames are used to develop a CNN model that can determine Wi-Fi network saturation. The results demonstrate that the proposed ML-based approach can accurately classify whether a Wi-Fi network is saturated or not.}}, author = {{Girmay, Merkebu and Shahid, Adnan and Maglogiannis, Vasilis and Naudts, Dries and Moerman, Ingrid}}, issn = {{2169-3536}}, journal = {{IEEE ACCESS}}, keywords = {{Wireless fidelity,Long Term Evolution,5G mobile communication,Wireless sensor networks,Wireless networks,Sensors,Analytical models,Wi-Fi saturation,traffic load estimation,coexistence,unlicensed spectrum,machine learning,convolutional neural networks}}, language = {{eng}}, pages = {{42959--42974}}, title = {{Machine learning enabled Wi-Fi saturation sensing for fair coexistence in unlicensed spectrum}}, url = {{http://dx.doi.org/10.1109/ACCESS.2021.3066052}}, volume = {{9}}, year = {{2021}}, }
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: