Edge-Enhanced QoS Aware Compression Learning for Sustainable Data Stream Analytics
Existing Cloud systems involve large volumes of data streams being sent to a centralised data centre for monitoring, storage and analytics. However, migrating all the data to the cloud is often not feasible due to cost, privacy, and performance concerns. However, Machine Learning (ML) algorithms typ...
Saved in:
| Published in: | IEEE transactions on sustainable computing Vol. 8; no. 3; pp. 1 - 17 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Piscataway
IEEE
01.07.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects: | |
| ISSN: | 2377-3782, 2377-3790 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Existing Cloud systems involve large volumes of data streams being sent to a centralised data centre for monitoring, storage and analytics. However, migrating all the data to the cloud is often not feasible due to cost, privacy, and performance concerns. However, Machine Learning (ML) algorithms typically require significant computational resources, hence cannot be directly deployed on resource-constrained edge devices for learning and analytics. Edge-enhanced compressive offloading becomes a sustainable solution that allows data to be compressed at the edge and offloaded to the cloud for further analysis, reducing bandwidth consumption and communication latency. The design and implementation of a learning method for discovering compression techniques that offer the best QoS for an application is described. The approach uses a novel modularisation approach that maps features to models and classifies them for a range of Quality of Service (QoS) features. An automated QoS-aware orchestrator has been designed to select the best autoencoder model in real-time for compressive offloading in edge-enhanced clouds based on changing QoS requirements. The orchestrator has been designed to have diagnostic capabilities to search appropriate parameters that give the best compression. A key novelty of this work is harnessing the capabilities of autoencoders for edge-enhanced compressive offloading based on portable encodings, latent space splitting and fine-tuning network weights. Considering how the combination of features lead to different QoS models, the system is capable of processing a large number of user requests in a given time. The proposed hyperparameter search strategy (over the neural architectural space) reduces the computational cost of search through the entire space by up to 89%. When deployed on an edge-enhanced cloud using an Azure IoT testbed, the approach saves up to 70% data transfer costs and takes 32% less time for job completion. It eliminates the additional computational cost of decompression, thereby reducing the processing cost by up to 30%. |
|---|---|
| AbstractList | Existing Cloud systems involve large volumes of data streams being sent to a centralised data centre for monitoring, storage and analytics. However, migrating all the data to the cloud is often not feasible due to cost, privacy, and performance concerns. However, Machine Learning (ML) algorithms typically require significant computational resources, hence cannot be directly deployed on resource-constrained edge devices for learning and analytics. Edge-enhanced compressive offloading becomes a sustainable solution that allows data to be compressed at the edge and offloaded to the cloud for further analysis, reducing bandwidth consumption and communication latency. The design and implementation of a learning method for discovering compression techniques that offer the best QoS for an application is described. The approach uses a novel modularisation approach that maps features to models and classifies them for a range of Quality of Service (QoS) features. An automated QoS-aware orchestrator has been designed to select the best autoencoder model in real-time for compressive offloading in edge-enhanced clouds based on changing QoS requirements. The orchestrator has been designed to have diagnostic capabilities to search appropriate parameters that give the best compression. A key novelty of this work is harnessing the capabilities of autoencoders for edge-enhanced compressive offloading based on portable encodings, latent space splitting and fine-tuning network weights. Considering how the combination of features lead to different QoS models, the system is capable of processing a large number of user requests in a given time. The proposed hyperparameter search strategy (over the neural architectural space) reduces the computational cost of search through the entire space by up to 89%. When deployed on an edge-enhanced cloud using an Azure IoT testbed, the approach saves up to 70% data transfer costs and takes 32% less time for job completion. It eliminates the additional computational cost of decompression, thereby reducing the processing cost by up to 30%. |
| Author | Ali, Muhammad Amaizu, Maryleen Uluaku Liotta, Antonio Anjum, Ashiq Liu, Lu Rana, Omer |
| Author_xml | – sequence: 1 givenname: Maryleen Uluaku orcidid: 0000-0002-4280-1450 surname: Amaizu fullname: Amaizu, Maryleen Uluaku organization: School of Computing and Mathematical Sciences, University of Leicester, U.K – sequence: 2 givenname: Muhammad surname: Ali fullname: Ali, Muhammad organization: School of Computing and Mathematical Sciences, University of Leicester, U.K – sequence: 3 givenname: Ashiq orcidid: 0000-0002-3378-1152 surname: Anjum fullname: Anjum, Ashiq organization: School of Computing and Mathematical Sciences, University of Leicester, U.K – sequence: 4 givenname: Lu orcidid: 0000-0003-1013-4507 surname: Liu fullname: Liu, Lu organization: School of Computing and Mathematical Sciences, University of Leicester, U.K – sequence: 5 givenname: Antonio orcidid: 0000-0002-2773-4421 surname: Liotta fullname: Liotta, Antonio organization: Faculty of Computer Science, Free University of Bozen-Bolzano, Italy – sequence: 6 givenname: Omer orcidid: 0000-0003-3597-2646 surname: Rana fullname: Rana, Omer organization: School of Computer Science and Informatics, Cardiff University, U.K |
| BookMark | eNpNkF1PwjAUhhuDiYj8AeNFE6-Hp-22bpdk4kdCYnRwvXTtGY5Ai-2I4d87hBivzrl4n_ecPNdkYJ1FQm4ZTBiD_GFRLstiwoGLieAJB5FfkCEXUkZC5jD42zN-RcYhrAGASZnknA3Jx8ysMJrZT2U1GvruSjr9Vh5p4bY7jyG0ztI5Km9bu6KN87Tch061VtUbpI-qU7TsPKotnVq1OXStDjfkslGbgOPzHJHl02xRvETzt-fXYjqPNM9ZF5laZLXJQeqaJzFglrBMGqVj3igjZGxSFCZNGkSs0xwhTXQttKw1gKi5AjEi96fenXdfewxdtXZ7338RKp6lPI1zyVmf4qeU9i4Ej0218-1W-UPFoDrqq371VUd91VlfD92doLa__g-ANOYiFT_S0W2s |
| CODEN | ITSCBE |
| Cites_doi | 10.1016/j.bspc.2020.102225 10.1145/3384419.3430898 10.1109/OPNARC.1998.662039 10.1109/TCBB.2022.3185395 10.1145/3274783.3274840 10.1007/978-981-15-6044-6_4 10.1109/ICCIS49240.2020.9257645 10.1109/PCS.2018.8456308 10.1109/CFEC.2018.8358733 10.1109/AVSS.2018.8639121 10.1016/j.future.2019.08.012 10.1109/HICSS.2005.32 10.1109/TMM.2022.3168146 10.1109/CANDAR.2017.13 10.1109/ICCWorkshops49005.2020.9145068 10.1109/JIOT.2016.2579198 10.1109/INFOCOM.2018.8485905 10.1109/BDCAT50828.2020.00018 10.1002/spe.761 10.1109/SECON52354.2021.9491600 10.1109/SiPS50750.2020.9195249 10.1109/MCOM.2018.1700332 10.1109/IWCMC.2018.8450511 10.1016/j.micpro.2021.104032 10.1109/TCC.2020.2991748 10.1016/j.jnca.2020.102696 10.1109/HPCC/SmartCity/DSS.2019.00180 10.1007/3-540-44892-6_19 10.1109/MNET.2018.1700202 10.1109/TII.2017.2679740 10.1109/CCECE.2019.8861806 10.1109/CogMI48466.2019.00035 10.1109/TBC.2011.2104671 10.1109/JSAC.2021.3118346 10.1109/JIOT.2018.2876695 10.1109/JIOT.2020.3027102 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TSUSC.2023.3252039 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Computer and Information Systems Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2377-3790 |
| EndPage | 17 |
| ExternalDocumentID | 10_1109_TSUSC_2023_3252039 10064236 |
| Genre | orig-research |
| GroupedDBID | 0R~ 6IK 97E AAJGR AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AGQYO AHBIQ AKJIK ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IEDLZ IFIPE IPLJI JAVBF OCL RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c291t-db38bd907cb2540e85187dac42fad374d6e3d65feeeb69e065cb3c7bc003b2a03 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001064522500011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2377-3782 |
| IngestDate | Sun Jun 29 12:30:39 EDT 2025 Sat Nov 29 04:09:20 EST 2025 Wed Aug 27 02:56:23 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c291t-db38bd907cb2540e85187dac42fad374d6e3d65feeeb69e065cb3c7bc003b2a03 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-1013-4507 0000-0003-3597-2646 0000-0002-4280-1450 0000-0002-3378-1152 0000-0002-2773-4421 |
| OpenAccessLink | https://figshare.com/articles/journal_contribution/Edge-Enhanced_QoS_Aware_Compression_Learning_for_Sustainable_Data_Stream_Analytics/22236502 |
| PQID | 2862649721 |
| PQPubID | 4437206 |
| PageCount | 17 |
| ParticipantIDs | crossref_primary_10_1109_TSUSC_2023_3252039 proquest_journals_2862649721 ieee_primary_10064236 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-07-01 |
| PublicationDateYYYYMMDD | 2023-07-01 |
| PublicationDate_xml | – month: 07 year: 2023 text: 2023-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Piscataway |
| PublicationPlace_xml | – name: Piscataway |
| PublicationTitle | IEEE transactions on sustainable computing |
| PublicationTitleAbbrev | TSUSC |
| PublicationYear | 2023 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref35 ref12 ref15 ref14 ref36 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref39 ref16 ref19 valtchev (ref40) 2020 liashchynskyi (ref37) 2019 said (ref45) 2017 xiao (ref41) 2017 theis (ref34) 2017 ref24 ref23 anguita (ref42) 2013 ref26 ref25 benmeziane (ref38) 2021 ref20 ref22 ref44 ref21 ref43 ref28 ref27 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 baldi (ref18) 2012 bank (ref31) 2020 |
| References_xml | – ident: ref30 doi: 10.1016/j.bspc.2020.102225 – ident: ref25 doi: 10.1145/3384419.3430898 – ident: ref12 doi: 10.1109/OPNARC.1998.662039 – ident: ref24 doi: 10.1109/TCBB.2022.3185395 – year: 2020 ident: ref40 article-title: Convolutional autoencoders for lossy light field compression – ident: ref19 doi: 10.1145/3274783.3274840 – ident: ref26 doi: 10.1007/978-981-15-6044-6_4 – ident: ref28 doi: 10.1109/ICCIS49240.2020.9257645 – ident: ref35 doi: 10.1109/PCS.2018.8456308 – year: 2021 ident: ref38 article-title: A comprehensive survey on hardware-aware neural architecture search – year: 2013 ident: ref42 article-title: A public domain dataset for human activity recognition using smartphones publication-title: Proc 21st Eur Symp Artif Neural Netw – year: 2017 ident: ref34 article-title: Lossy image compression with compressive autoencoders – ident: ref1 doi: 10.1109/CFEC.2018.8358733 – ident: ref22 doi: 10.1109/AVSS.2018.8639121 – ident: ref9 doi: 10.1016/j.future.2019.08.012 – ident: ref11 doi: 10.1109/HICSS.2005.32 – ident: ref6 doi: 10.1109/TMM.2022.3168146 – ident: ref27 doi: 10.1109/CANDAR.2017.13 – ident: ref20 doi: 10.1109/ICCWorkshops49005.2020.9145068 – ident: ref2 doi: 10.1109/JIOT.2016.2579198 – ident: ref16 doi: 10.1109/INFOCOM.2018.8485905 – ident: ref7 doi: 10.1109/BDCAT50828.2020.00018 – start-page: 1 year: 2017 ident: ref45 article-title: Multimodal deep learning approach for joint EEG-EMG data compression and classification publication-title: Proc IEEE Wireless Commun Netw Conf – year: 2017 ident: ref41 article-title: Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms – ident: ref10 doi: 10.1002/spe.761 – ident: ref23 doi: 10.1109/SECON52354.2021.9491600 – ident: ref36 doi: 10.1109/SiPS50750.2020.9195249 – ident: ref3 doi: 10.1109/MCOM.2018.1700332 – ident: ref14 doi: 10.1109/IWCMC.2018.8450511 – ident: ref44 doi: 10.1016/j.micpro.2021.104032 – ident: ref17 doi: 10.1109/TCC.2020.2991748 – year: 2020 ident: ref31 article-title: Autoencoders – ident: ref29 doi: 10.1016/j.jnca.2020.102696 – ident: ref32 doi: 10.1109/HPCC/SmartCity/DSS.2019.00180 – ident: ref8 doi: 10.1007/3-540-44892-6_19 – ident: ref4 doi: 10.1109/MNET.2018.1700202 – ident: ref5 doi: 10.1109/TII.2017.2679740 – ident: ref13 doi: 10.1109/CCECE.2019.8861806 – ident: ref15 doi: 10.1109/CogMI48466.2019.00035 – ident: ref39 doi: 10.1109/TBC.2011.2104671 – ident: ref21 doi: 10.1109/JSAC.2021.3118346 – ident: ref33 doi: 10.1109/JIOT.2018.2876695 – year: 2019 ident: ref37 article-title: Grid search, random search, genetic algorithm: A big comparison for NAS – start-page: 37 year: 2012 ident: ref18 article-title: Autoencoders, unsupervised learning, and deep architectures publication-title: Proc ICML Workshop Unsupervised Transfer Learn – ident: ref43 doi: 10.1109/JIOT.2020.3027102 |
| SSID | ssj0001775921 |
| Score | 2.2313116 |
| Snippet | Existing Cloud systems involve large volumes of data streams being sent to a centralised data centre for monitoring, storage and analytics. However, migrating... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Adaptation models Algorithms Biological system modeling Cloud Computing Computational efficiency Computational modeling Computing costs Data centers Data compression Data models Data transfer (computers) Data transmission Deep Autoencoders Edge Computing Machine learning Network latency Quality of service Quality of service architectures Real-time analytics Search methods Task analysis Transmission Optimisation |
| Title | Edge-Enhanced QoS Aware Compression Learning for Sustainable Data Stream Analytics |
| URI | https://ieeexplore.ieee.org/document/10064236 https://www.proquest.com/docview/2862649721 |
| Volume | 8 |
| WOSCitedRecordID | wos001064522500011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 2377-3790 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001775921 issn: 2377-3782 databaseCode: RIE dateStart: 20160101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6EePDiI2JE0fTgzRSXtrTbI0GIJ6IuJNyavhY9uBhY9O_bdpdAYjx420N3037t7Mx05psB4A5z5pUc5Sg3TCNKlEXa8hxZZnlihE0TomOzCT6ZpPO5eK7J6pEL45yLyWeuGx5jLN8uzSZclXkJD-YyYQ3Q4JxVZK3dhQrnfYF7W2JMIh6m2SwbdkN_8C7BfZyEhuB7yid2U_n1C456ZXzyzxmdguPagISDasfPwIErzsHryC4cGhVvMZ4PX5YZHHyrlYNB3KtM1wLWpVQX0NupMNsRp-CjKhUM4Wn1AWORklC6uQVm49F0-ITqbgnIYNErkdUk1db7ukZ7py9x3pRKuVWG4lxZwqlljljWz_0aNBPOmx5GE8O18XKtsUrIBWgWy8JdAuhSG3JlUqOd89vnR_eUUoJRoyhVXLTB_RZG-VkVxZDRmUiEjKDLALqsQW-DVgBub2SFWRt0ttDLWnDWEgcPi4aSQld_vHYNjsLXq5TZDmiWq427AYfmq3xfr27jmfgB1zm27Q |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFG8UTfTiR8SIovbgzRRH263rkSAEIxIVSLgt_Rp6cBgY-u_bdiOQGA_eduiy9te-vff63u89AG4wi6ySowylKpKIEqGR1CxFOtIsUFzHAZG-2QQbDOLJhD-XZHXPhTHG-OQz03CPPpavZ2rprsqshDtzmUTbYCekFAcFXWt9pcJYyHFzRY0J-N1oOB62G65DeIPgEAeuJfiG-vH9VH79hL1m6R7-c05H4KA0IWGr2PNjsGWyE_Da0VODOtmbj-jDl9kQtr7F3EAn8EWuawbLYqpTaC1VOFxTp-C9yAV0AWrxAX2ZEle8uQrG3c6o3UNlvwSkMG_mSEsSS229XSWt2xcYa0zFTAtFcSo0YVRHhugoTO0aZMSNNT6UJIpJZSVbYhGQU1DJZpk5A9DE2mXLxEoaYzfQjm4KIXhElaBUMF4DtysYk8-iLEbi3YmAJx70xIGelKDXQNUBtzGywKwG6ivok1J0Fgl2PhZ1RYXO_3jtGuz1Rk_9pP8weLwA--5LRQJtHVTy-dJcgl31lb8v5lf-fPwAhye6NA |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Edge-Enhanced+QoS+Aware+Compression+Learning+for+Sustainable+Data+Stream+Analytics&rft.jtitle=IEEE+transactions+on+sustainable+computing&rft.au=Amaizu%2C+Maryleen+Uluaku&rft.au=Ali%2C+Muhammad&rft.au=Anjum%2C+Ashiq&rft.au=Liu%2C+Lu&rft.date=2023-07-01&rft.pub=IEEE&rft.eissn=2377-3790&rft.spage=1&rft.epage=17&rft_id=info:doi/10.1109%2FTSUSC.2023.3252039&rft.externalDocID=10064236 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2377-3782&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2377-3782&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2377-3782&client=summon |