Machine learning-based spectrum occupancy prediction: a comprehensive survey
In cognitive radio (CR) systems, efficient spectrum utilization depends on the ability to predict spectrum opportunities. Traditional statistical methods for spectrum occupancy prediction (SOP) are insufficient for addressing the non-stationary nature of spectrum occupancy, especially with UEs’ incr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Communications and Networks |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frcmn.2025.1482698/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591725166592000 |
|---|---|
| author | Mehmet Ali Aygül Mehmet Ali Aygül Hakan Ali Çırpan Hüseyin Arslan |
| author_facet | Mehmet Ali Aygül Mehmet Ali Aygül Hakan Ali Çırpan Hüseyin Arslan |
| author_sort | Mehmet Ali Aygül |
| collection | DOAJ |
| description | In cognitive radio (CR) systems, efficient spectrum utilization depends on the ability to predict spectrum opportunities. Traditional statistical methods for spectrum occupancy prediction (SOP) are insufficient for addressing the non-stationary nature of spectrum occupancy, especially with UEs’ increased mobility and diversity in the sixth-generation and beyond wireless networks. This survey provides a comprehensive overview of machine learning (ML)-based SOP methods that address these challenges. The paper begins with a brief discussion of problem definition and traditional statistical methods before delving into a detailed survey of ML-based methods. Various aspects of SOP are analyzed from a CR perspective, highlighting the multidimensional correlations in spectrum usage across time, frequency, space, etc. Key challenges and enabling methods for effective prediction are reviewed, focusing on deep learning methods that exploit these multidimensional correlations. The survey also covers dataset generation techniques for SOP. Additionally, the paper discusses CR threats that impair spectrum utilization and reviews ML methods for detecting these threats. The future directions for ML-based SOP are also given. |
| format | Article |
| id | doaj-art-b2fac415888646e68071a2c999f738f6 |
| institution | Kabale University |
| issn | 2673-530X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Communications and Networks |
| spelling | doaj-art-b2fac415888646e68071a2c999f738f62025-01-22T07:11:23ZengFrontiers Media S.A.Frontiers in Communications and Networks2673-530X2025-01-01610.3389/frcmn.2025.14826981482698Machine learning-based spectrum occupancy prediction: a comprehensive surveyMehmet Ali Aygül0Mehmet Ali Aygül1Hakan Ali Çırpan2Hüseyin Arslan3Department of Electronics and Communications Engineering, Istanbul Technical University, Istanbul, TürkiyeDepartment of Research and Development, Vestel, Manisa, TürkiyeDepartment of Electronics and Communications Engineering, Istanbul Technical University, Istanbul, TürkiyeDepartment of Electrical and Electronics Engineering, Istanbul Medipol University, Istanbul, TürkiyeIn cognitive radio (CR) systems, efficient spectrum utilization depends on the ability to predict spectrum opportunities. Traditional statistical methods for spectrum occupancy prediction (SOP) are insufficient for addressing the non-stationary nature of spectrum occupancy, especially with UEs’ increased mobility and diversity in the sixth-generation and beyond wireless networks. This survey provides a comprehensive overview of machine learning (ML)-based SOP methods that address these challenges. The paper begins with a brief discussion of problem definition and traditional statistical methods before delving into a detailed survey of ML-based methods. Various aspects of SOP are analyzed from a CR perspective, highlighting the multidimensional correlations in spectrum usage across time, frequency, space, etc. Key challenges and enabling methods for effective prediction are reviewed, focusing on deep learning methods that exploit these multidimensional correlations. The survey also covers dataset generation techniques for SOP. Additionally, the paper discusses CR threats that impair spectrum utilization and reviews ML methods for detecting these threats. The future directions for ML-based SOP are also given.https://www.frontiersin.org/articles/10.3389/frcmn.2025.1482698/full6Gcognitive radiodeep learningmachine learningmulti-dimensionsspectrum occupancy prediction |
| spellingShingle | Mehmet Ali Aygül Mehmet Ali Aygül Hakan Ali Çırpan Hüseyin Arslan Machine learning-based spectrum occupancy prediction: a comprehensive survey Frontiers in Communications and Networks 6G cognitive radio deep learning machine learning multi-dimensions spectrum occupancy prediction |
| title | Machine learning-based spectrum occupancy prediction: a comprehensive survey |
| title_full | Machine learning-based spectrum occupancy prediction: a comprehensive survey |
| title_fullStr | Machine learning-based spectrum occupancy prediction: a comprehensive survey |
| title_full_unstemmed | Machine learning-based spectrum occupancy prediction: a comprehensive survey |
| title_short | Machine learning-based spectrum occupancy prediction: a comprehensive survey |
| title_sort | machine learning based spectrum occupancy prediction a comprehensive survey |
| topic | 6G cognitive radio deep learning machine learning multi-dimensions spectrum occupancy prediction |
| url | https://www.frontiersin.org/articles/10.3389/frcmn.2025.1482698/full |
| work_keys_str_mv | AT mehmetaliaygul machinelearningbasedspectrumoccupancypredictionacomprehensivesurvey AT mehmetaliaygul machinelearningbasedspectrumoccupancypredictionacomprehensivesurvey AT hakanalicırpan machinelearningbasedspectrumoccupancypredictionacomprehensivesurvey AT huseyinarslan machinelearningbasedspectrumoccupancypredictionacomprehensivesurvey |