dc.contributor.author | Merayo Álvarez, Noemí | |
dc.contributor.author | Juárez Estévez, David | |
dc.contributor.author | Aguado Manzano, Juan Carlos | |
dc.contributor.author | Miguel Jiménez, Ignacio de | |
dc.contributor.author | Durán Barroso, Ramón José | |
dc.contributor.author | Fernández Reguero, Patricia | |
dc.contributor.author | Lorenzo Toledo, Rubén Mateo | |
dc.contributor.author | Abril Domingo, Evaristo José | |
dc.date.accessioned | 2018-12-17T12:29:02Z | |
dc.date.available | 2018-12-17T12:29:02Z | |
dc.date.issued | 2017 | |
dc.identifier.citation | IEEE/OSA Journal of Optical Communications and Networking, 2017, Volume 9, Issue 5, pp. 433 - 445 | es |
dc.identifier.issn | 1943-0639 | es |
dc.identifier.uri | http://uvadoc.uva.es/handle/10324/33487 | |
dc.description | Producción Científica | es |
dc.description.abstract | In this paper, a proportional-integral-derivative (PID) controller integrated with a neural network (NN) is proposed to ensure quality of service (QoS) bandwidth requirements in passive optical networks (PONs). To the best of our knowledge, this is the first time an approach that implements a NN to tune a PID to deal with QoS in PONs is used. In contrast to other tuning techniques such as Ziegler-Nichols or genetic algorithms (GA), our proposal allows a real-time adjustment of the tuning parameters according to the network conditions. Thus, the new algorithm provides an online control of the tuning process unlike the ZN and GA techniques, whose tuning parameters are calculated offline. The algorithm, called neural network service level PID (NNSPID), guarantees minimum bandwidth levels to users depending on their service level agreement, and it is compared with a tuning technique based on genetic algorithms (GASPID). The simulation study demonstrates that NN-SPID continuously adapts the tuning parameters, achieving lower fluctuations than GA-SPID in the allocation process. As a consequence, it provides a more stable response than GA-SPID since it needs to launch the GA to obtain new tuning values. Furthermore, NN-SPID guarantees the minimum bandwidth levels faster than GA-SPID. Finally, NN-SPID is more robust than GA-SPID under real-time changes of the guaranteed bandwidth levels, as GA-SPID shows high fluctuations in the allocated bandwidth, especially just after any change is made. | es |
dc.format.mimetype | application/pdf | es |
dc.language.iso | eng | es |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.subject.classification | Red neuronal (NN) | es |
dc.subject.classification | Red óptica pasiva (PON) | es |
dc.subject.classification | Neural network (NN) | es |
dc.subject.classification | Passive optical network (PON) | es |
dc.title | PID controller based on a self-adaptive neural network to ensure qos bandwidth requirements in passive optical networks | es |
dc.type | info:eu-repo/semantics/article | es |
dc.rights.holder | © 2017 Optical Society of America | es |
dc.identifier.doi | https://doi.org/10.1364/JOCN.9.000433 | es |
dc.relation.publisherversion | https://ieeexplore.ieee.org/document/7926828 | es |
dc.peerreviewed | SI | es |
dc.description.project | Ministerio de Ciencia e Innovación (Projects TEC2014-53071-C3-2-P and TEC2015-71932-REDT) | es |
Aviso: Si va a participar en la campaña de sexenios 2024, le recomendamos que deposite en UVaDoc de forma preferente las aportaciones que vaya a presentar a dicha convocatoria (opción Autoarchivo). El resto de sus publicaciones podrá subirlas al repositorio en cualquier otro momento. Gracias.