Show simple item record

dc.contributor.authorLuo, Qiwu
dc.contributor.authorFang, Xiaoxin
dc.contributor.authorSun, Yichuang
dc.contributor.authorAi, Jiaqiu
dc.contributor.authorYang, Chunhua
dc.date.accessioned2020-01-07T01:07:38Z
dc.date.available2020-01-07T01:07:38Z
dc.date.issued2020-01-03
dc.identifier.citationLuo , Q , Fang , X , Sun , Y , Ai , J & Yang , C 2020 , ' Self-Learning Hot Data Prediction: Where Echo State Network Meets NAND Flash Memories ' , IEEE Transactions on Circuits and Systems I: Regular Papers , vol. 67 , no. 3 , 8949460 , pp. 939-950 . https://doi.org/10.1109/TCSI.2019.2960015
dc.identifier.issn1549-8328
dc.identifier.otherPURE: 18310572
dc.identifier.otherPURE UUID: b0e424ac-9e07-4293-afce-1e907d746fce
dc.identifier.otherScopus: 85080900583
dc.identifier.urihttp://hdl.handle.net/2299/22039
dc.description© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.description.abstractWell understanding the access behavior of hot data is significant for NAND flash memory due to its crucial impact on the efficiency of garbage collection (GC) and wear leveling (WL), which respectively dominate the performance and life span of SSD. Generally, both GC and WL rely greatly on the recognition accuracy of hot data identification (HDI). However, in this paper, the first time we propose a novel concept of hot data prediction (HDP), where the conventional HDI becomes unnecessary. First, we develop a hybrid optimized echo state network (HOESN), where sufficiently unbiased and continuously shrunk output weights are learnt by a sparse regression based on L2 and L1/2 regularization. Second, quantum-behaved particle swarm optimization (QPSO) is employed to compute reservoir parameters (i.e., global scaling factor, reservoir size, scaling coefficient and sparsity degree) for further improving prediction accuracy and reliability. Third, in the test on a chaotic benchmark (Rossler), the HOESN performs better than those of six recent state-of-the-art methods. Finally, simulation results about six typical metrics tested on five real disk workloads and on-chip experiment outcomes verified from an actual SSD prototype indicate that our HOESN-based HDP can reliably promote the access performance and endurance of NAND flash memories.en
dc.format.extent12
dc.language.isoeng
dc.relation.ispartofIEEE Transactions on Circuits and Systems I: Regular Papers
dc.subjectNAND flash memory
dc.subjectecho state network (ESN)
dc.subjecthot data prediction
dc.subjectregularization
dc.subjectsolid state disk (SSD)
dc.subjectElectrical and Electronic Engineering
dc.titleSelf-Learning Hot Data Prediction: Where Echo State Network Meets NAND Flash Memoriesen
dc.contributor.institutionCentre for Engineering Research
dc.contributor.institutionCommunications and Intelligent Systems
dc.contributor.institutionSchool of Physics, Engineering & Computer Science
dc.contributor.institutionDepartment of Engineering and Technology
dc.description.statusPeer reviewed
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85080900583&partnerID=8YFLogxK
rioxxterms.versionAM
rioxxterms.versionofrecordhttps://doi.org/10.1109/TCSI.2019.2960015
rioxxterms.typeJournal Article/Review
herts.preservation.rarelyaccessedtrue


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record