Joint Forecasting-Scheduling for the Internet of Things

Basit Öğe Kaydı
dc.authorscopusid57212473263
dc.authorscopusid6602651842
dc.authorscopusid55937768800
dc.authorscopusid14521079300
dc.contributor.authorNakip, Mert
dc.contributor.authorRodoplu, Volkan
dc.contributor.authorGüzeliş, C.
dc.contributor.authorEliiyi, Deniz Türsel
dc.date.accessioned2022-02-15T16:58:11Z
dc.date.available2022-02-15T16:58:11Z
dc.date.issued2019
dc.departmentBakırçay Üniversitesien_US
dc.description2019 IEEE Global Conference on Internet of Things, GCIoT 2019 -- 4 December 2019 through 7 December 2019 -- -- 159114en_US
dc.description.abstractWe present a joint forecasting-scheduling (JFS) system, to be implemented at an IoT Gateway, in order to alleviate the Massive Access Problem of the Internet of Things. The existing proposals to solve the Massive Access Problem model the traffic generation pattern of each IoT device via random arrivals. In contrast, our JFS system forecasts the traffic generation pattern of each IoT device and schedules the transmissions of these devices in advance. The comparison of the network throughput of Autoregressive Integrated Moving Average (ARIMA), Multi-Layer Perceptron (MLP) and Long-Short Term Memory (LSTM) forecasting models reveals that the optimal choice of the forecasting model for JFS depends heavily on the proportions of distinct IoT device classes that are present in the network. Simulations show that our JFS system scales up to 1000 devices while achieving a total execution time under 1 second. This work opens the way to the design of scalable joint forecasting-scheduling solutions at IoT Gateways. © 2019 IEEE.en_US
dc.description.sponsorshipTürkiye Bilimsel ve Teknolojik Araştirma Kurumu, TÜBITAK: 118E277en_US
dc.description.sponsorshipACKNOWLEDGMENT This work was supported by TÜBITAK (Scientific and Technological Research Council of Turkey) under the 1001 Program Grant # 118E277.en_US
dc.description.sponsorshipThis work was supported by TUBITAK (Scientific and Technological Research Council of Turkey) under the 1001 Program Grant # 118E277.en_US
dc.identifier.doi10.1109/GCIoT47977.2019.9058408
dc.identifier.isbn9781728148731
dc.identifier.scopus2-s2.0-85084119422en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://doi.org/10.1109/GCIoT47977.2019.9058408
dc.identifier.urihttps://hdl.handle.net/20.500.14034/361
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.journal2019 IEEE Global Conference on Internet of Things, GCIoT 2019en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAnomaly Detectionen_US
dc.subjectConcept Driften_US
dc.subjectInternet of Thingsen_US
dc.subjectIntrusion Detectionen_US
dc.subjectOnline Machine Learningen_US
dc.subjectAutoregressive moving average modelen_US
dc.subjectForecastingen_US
dc.subjectGateways (computer networks)en_US
dc.subjectLong short-term memoryen_US
dc.subjectSchedulingen_US
dc.subjectAuto-regressive integrated moving averageen_US
dc.subjectForecasting modelingen_US
dc.subjectForecasting modelsen_US
dc.subjectMulti layer perceptronen_US
dc.subjectNetwork throughputen_US
dc.subjectOptimal choiceen_US
dc.subjectProblem modelingen_US
dc.subjectTraffic generationen_US
dc.subjectInternet of thingsen_US
dc.titleJoint Forecasting-Scheduling for the Internet of Thingsen_US
dc.typeConference Objecten_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Joint_Forecasting-Scheduling_for_the_Internet_of_Things.pdf
Boyut:
1.21 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Endüstri Mühendisliği Bölümü Koleksiyonu