Deep RL-based spectrum occupancy prediction exploiting time and frequency correlations

Basit Öğe Kaydı
dc.authorid0000-0003-3375-0310
dc.authorid0000-0001-9474-7372
dc.contributor.authorAygül, Mehmet Ali
dc.contributor.authorNazzal, Mahmoud
dc.contributor.authorArslan, Hüseyin
dc.date.accessioned2022-06-03T11:56:38Z
dc.date.available2022-06-03T11:56:38Z
dc.date.issued2022
dc.departmentİstanbul Medipol Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü
dc.description.abstractIn cognitive radio systems, predicting spectrum occupancies is a convenient alternative way to continuous spectrum sensing. It can provide information on spectrum usage and so empty spectrum bands can be used by secondary users. The usage of the spectrum bands is highly correlated over both time and frequency. Recently, machine learning algorithms are used to predict spectrum occupancy by exploiting such correlations. However, this approach primarily assumes a supervised learning setting. Despite its outstanding performance, this setting requires the availability of sufficiently large datasets (of labeled data) and is not adaptive to environment changes. In this paper, different from the existing literature, a deep reinforcement learning (RL) algorithm is used to alleviate those shortcomings. In this algorithm, we define the reward functions of the deep RL setting and its state and action spaces such that it is applicable to work dynamically, in an online fashion, in real world settings. Extensive experiments validate the capability of the proposed algorithm in predicting spectrum occupancies as examined over real world spectrum measurements. These are carried out in the 832-862 megahertz frequency bands, which are used by the leading Turkish telecom providers as private uplink bands. This is a significant step towards realizing a standalone spectrum occupancy prediction operation without any control from the operator and minimizing memory requirements while alleviating the need for the labeled dataset.
dc.identifier.citationAygül, M. A., Nazzal, M. ve Arslan, H. (2022). Deep RL-based spectrum occupancy prediction exploiting time and frequency correlations. IEEE Wireless Communications and Networking Conference (IEEE WCNC), Austin, 10-13 April 2022. https://dx.doi.org/10.1109/WCNC51071.2022.9771702
dc.identifier.doi10.1109/WCNC51071.2022.9771702
dc.identifier.endpage2404
dc.identifier.isbn9781665442664
dc.identifier.issn1525-3511
dc.identifier.scopus2-s2.0-85130722136
dc.identifier.scopusqualityN/A
dc.identifier.startpage2399
dc.identifier.urihttps://dx.doi.org/10.1109/WCNC51071.2022.9771702
dc.identifier.urihttps://hdl.handle.net/20.500.12511/9497
dc.identifier.wos000819473100403en_US
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorNazzal, Mahmoud
dc.institutionauthorArslan, Hüseyin
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofIEEE Wireless Communications and Networking Conference (IEEE WCNC)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.relation.tubitakinfo:eu-repo/grantAgreement/TUBITAK/SOBAG/5200030
dc.rightsinfo:eu-repo/semantics/embargoedAccess
dc.subjectCognitive Radio
dc.subjectDeep Reinforcement Learning
dc.subjectReal World Spectrum Measurements
dc.subjectSpectrum Occupancy Prediction
dc.subjectTime and Frequency Correlations
dc.titleDeep RL-based spectrum occupancy prediction exploiting time and frequency correlations
dc.typeConference Object

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Nazzal-Mahmoud-2022.pdf
Boyut:
1.09 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bildiri Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu