{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:54:34Z","timestamp":1753887274615,"version":"3.41.2"},"reference-count":33,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In distributed computing environments, the collaboration of nodes for predictive analytics at the network edge plays a crucial role in supporting real-time services. When a node\u2019s service becomes unavailable for various reasons (e.g., service updates, node maintenance, or even node failure), the rest of the available nodes connot efficiently replace its service due to different data and predictive models (e.g., machine learning [ML] models). To address this, we propose decision-making strategies rooted in the statistical signatures of nodes\u2019 data. Specifically, these signatures refer to the unique patterns and behaviors within each node\u2019s data that can be leveraged to predict the suitability of potential surrogate nodes. Recognizing and acting on these statistical nuances ensures a more targeted and efficient response to node failures. Such strategies aim to identify <jats:italic>surrogate nodes<\/jats:italic> capable of substituting for failing nodes\u2019 services by building <jats:italic>enhanced<\/jats:italic> predictive models. Our resilient framework helps to guide the task requests from failing nodes to the most appropriate surrogate nodes. In this case, the surrogate nodes can use their enhanced models, which can produce equivalent and satisfactory results for the requested tasks. We provide experimental evaluations and comparative assessments with baseline approaches over real datasets. Our results showcase the capability of our framework to maintain the overall performance of predictive analytics under nodes\u2019 failures in edge computing environments.<\/jats:p>","DOI":"10.1515\/comp-2023-0116","type":"journal-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T13:12:40Z","timestamp":1715605960000},"source":"Crossref","is-referenced-by-count":0,"title":["Resilient edge predictive analytics by enhancing local models"],"prefix":"10.1515","volume":"14","author":[{"given":"Qiyuan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computing Science, University of Glasgow , Glasgow , United Kingdom"}]},{"given":"Saleh","family":"ALFahad","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow , Glasgow , United Kingdom"}]},{"given":"Jordi Mateo","family":"Fornes","sequence":"additional","affiliation":[{"name":"Department Computer Science, University of Lleida , Lleida , Spain"}]},{"given":"Christos","family":"Anagnostopoulos","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow , Glasgow , United Kingdom"}]},{"given":"Kostas","family":"Kolomvatsos","sequence":"additional","affiliation":[{"name":"Department Informatics & Telecommunications, University of Thessaly , Lamia , Greece"}]}],"member":"374","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"2024051313123466882_j_comp-2023-0116_ref_001","doi-asserted-by":"crossref","unstructured":"J. Ren, Y. Pan, A. Goscinski, and R. A. Beyah, \u201cEdge computing for the internet of things,\u201d IEEE Netw., vol. 32, no. 1. pp. 6\u20137, 2018.","DOI":"10.1109\/MNET.2018.8270624"},{"key":"2024051313123466882_j_comp-2023-0116_ref_002","doi-asserted-by":"crossref","unstructured":"S. Deng, H. Zhao, W. Fang, J. Yin, S. Dustdar, and A. Y. Zomaya, \u201cEdge intelligence: The confluence of edge computing and artificial intelligence,\u201d IEEE Internet Things J., vol. 7, no. 8. pp. 7457\u20137469, 2020.","DOI":"10.1109\/JIOT.2020.2984887"},{"key":"2024051313123466882_j_comp-2023-0116_ref_003","doi-asserted-by":"crossref","unstructured":"W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, \u201cEdge computing: Vision and challenges,\u201d. IEEE Internet Things J., vol. 3, no. 5. pp. 637\u2013646, 2016.","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"2024051313123466882_j_comp-2023-0116_ref_004","doi-asserted-by":"crossref","unstructured":"M. A. Jan, et al. \u201cAn AI-enabled lightweight data fusion and load optimization approach for internet of things,\u201d Future Gener. Comput. Syst., vol. 122, pp. 40\u201351, 2021.","DOI":"10.1016\/j.future.2021.03.020"},{"key":"2024051313123466882_j_comp-2023-0116_ref_005","doi-asserted-by":"crossref","unstructured":"J. Wang, S. Pambudi, W. Wang, and M. Song, \u201cResilience of iot systems against edge-induced cascade-of-failures: A networking perspective,\u201d IEEE Internet Things J., vol. 6, no. 4. pp. 6952\u20136963, 2019b.","DOI":"10.1109\/JIOT.2019.2913140"},{"key":"2024051313123466882_j_comp-2023-0116_ref_006","doi-asserted-by":"crossref","unstructured":"A. Borg, J. Baumbach, and S. Glazer, \u201cA message system supporting fault tolerance,\u201d ACM SIGOPS Operating Systems Review, vol. 17, no. 5. pp. 90\u201399, 1983.","DOI":"10.1145\/773379.806617"},{"key":"2024051313123466882_j_comp-2023-0116_ref_007","unstructured":"B. Cully, G. Lefebvre, D. Meyer, M. Feeley, N. Hutchinson, and A. Warfield, \u201cRemus: High availability via asynchronous virtual machine replication,\u201d In Proceedings of the 5th USENIX symposium on networked systems design and implementation, pp. 161\u2013174. San Francisco, 2008."},{"key":"2024051313123466882_j_comp-2023-0116_ref_008","doi-asserted-by":"crossref","unstructured":"J. Sherry, P. X. Gao, S. Basu, A. Panda, A. Krishnamurthy, C. Maciocco, et al. \u201cRollback-recovery for middleboxes,\u201d In Proceedings of the 2015 ACM Conference on Special Interest Group on Data Communication, pp. 227\u2013240, 2015.","DOI":"10.1145\/2785956.2787501"},{"key":"2024051313123466882_j_comp-2023-0116_ref_009","doi-asserted-by":"crossref","unstructured":"M. Mudassar, Y. Zhai, and L. Lejian, \u201cAdaptive fault-tolerant strategy for latency-aware IoT application executing in edge computing environment,\u201d IEEE Internet Things J., vol. 9, no. 15. pp. 13250\u201313262, 2022.","DOI":"10.1109\/JIOT.2022.3144026"},{"key":"2024051313123466882_j_comp-2023-0116_ref_010","doi-asserted-by":"crossref","unstructured":"M. Siavvas, and E. Gelenbe, \u201cOptimum interval for application-level checkpoints,\u201d In 2019 6th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)\/2019 5th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom), pp. 145\u2013150, 2019.","DOI":"10.1109\/CSCloud\/EdgeCom.2019.000-4"},{"key":"2024051313123466882_j_comp-2023-0116_ref_011","doi-asserted-by":"crossref","unstructured":"Y. Harchol, A. Mushtaq, V. Fang, J. McCauley, A. Panda, and S. Shenker, \u201cMaking edge-computing resilient,\u201d In Proceedings of the 11th ACM Symposium on Cloud Computing, SoCC \u201920, pp. 253\u2013266, New York, NY, USA. Association for Computing Machinery, 2020.","DOI":"10.1145\/3419111.3421278"},{"key":"2024051313123466882_j_comp-2023-0116_ref_012","doi-asserted-by":"crossref","unstructured":"J. P. Sterbenz, D. Hutchison, E. K. \u00c7etinkaya, A. Jabber, J. P. Rohrer, M. Schller, et al., \u201cResilience and survivability in communication networks: Strategies, principles, and survey of disciplines,\u201d Comput. Netw., vol. 54, no. 8. pp. 1245\u20131265, 2010. Resilient and Survivable networks.","DOI":"10.1016\/j.comnet.2010.03.005"},{"key":"2024051313123466882_j_comp-2023-0116_ref_013","doi-asserted-by":"crossref","unstructured":"K. A. Delic, \u201cOn resilience of IoT systems: The internet of things (ubiquity symposium),\u201d Ubiquity, 2016 February:1\u20137.","DOI":"10.1145\/2822885"},{"key":"2024051313123466882_j_comp-2023-0116_ref_014","doi-asserted-by":"crossref","unstructured":"J. Beutel, K. R\u00f6mer, M. Ringwald, and M. Woehrle, \u201cDeployment Techniques for Sensor Networks,\u201d pp. 219\u2013248, 2009.","DOI":"10.1007\/978-3-642-01341-6_9"},{"key":"2024051313123466882_j_comp-2023-0116_ref_015","doi-asserted-by":"crossref","unstructured":"M. M. H. Khan, H. K. Le, M. LeMay, P. Moinzadeh, L. Wang, Y. Yang, et al., \u201cDiagnostic power tracing for sensor node failure analysis,\u201d In Proceedings of the 9th ACM\/IEEE international conference on information processing in sensor networks, pp. 117\u2013128, 2010.","DOI":"10.1145\/1791212.1791227"},{"key":"2024051313123466882_j_comp-2023-0116_ref_016","doi-asserted-by":"crossref","unstructured":"S. Shao, X. Huang, H. E. Stanley, and S. Havlin, \u201cPercolation of localized attack on complex networks,\u201d New J. Phys., vol. 17, no. 2. p. 023049, 2015.","DOI":"10.1088\/1367-2630\/17\/2\/023049"},{"key":"2024051313123466882_j_comp-2023-0116_ref_017","doi-asserted-by":"crossref","unstructured":"S. N. Shirazi, A. Gouglidis, A. Farshad, and D. Hutchison, \u201cThe extended cloud: Review and analysis of mobile edge computing and fog from a security and resilience perspective,\u201d IEEE J. Sel. Areas Commun., vol. 35, no. 11. pp. 2586\u20132595, 2017.","DOI":"10.1109\/JSAC.2017.2760478"},{"key":"2024051313123466882_j_comp-2023-0116_ref_018","doi-asserted-by":"crossref","unstructured":"S. Kounev, P. Reinecke, F. Brosig, J. T. Bradley, K. Joshi, V. Babka, et al., \u201cProviding Dependability and Resilience in the Cloud: Challenges and Opportunities,\u201d pp. 65\u201381. Springer Berlin Heidelberg, Berlin, Heidelberg, 2012.","DOI":"10.1007\/978-3-642-29032-9_4"},{"key":"2024051313123466882_j_comp-2023-0116_ref_019","doi-asserted-by":"crossref","unstructured":"A. Shafahi, M. Najibi, Z. Xu, J. Dickerson, L. S. Davis, and T. Goldstein, \u201cUniversal adversarial training,\u201d AAAI Conference on Artificial Intelligence, vol. 34, no. 04. pp. 5636\u20135643, 2020.","DOI":"10.1609\/aaai.v34i04.6017"},{"key":"2024051313123466882_j_comp-2023-0116_ref_020","unstructured":"E. Wong, L. Rice, and J. Z. Kolter, \u201cFast is better than free: Revisiting adversarial training,\u201d CoRR, abs\/2001. vol. 03994, 2020."},{"key":"2024051313123466882_j_comp-2023-0116_ref_021","doi-asserted-by":"crossref","unstructured":"T. Bai, J. Luo, J. Zhao, B. Wen, and Q. Wang, \u201cRecent advances in adversarial training for adversarial robustness,\u201d CoRR, vol. abs\/2102.01356, 2021.","DOI":"10.24963\/ijcai.2021\/591"},{"key":"2024051313123466882_j_comp-2023-0116_ref_022","unstructured":"H. Daum\u00e9 III, \u201cFrustratingly easy domain adaptation,\u201d arXiv:http:\/\/arXiv.org\/abs\/arXiv:0907.1815, 2009."},{"key":"2024051313123466882_j_comp-2023-0116_ref_023","doi-asserted-by":"crossref","unstructured":"A. Farahani, S. Voghoei, K. Rasheed, and A. R. Arabnia, \u201cA brief review of domain adaptation,\u201d Advances in Data Science and Information Engineering, pp. 877\u2013894, 2021.","DOI":"10.1007\/978-3-030-71704-9_65"},{"key":"2024051313123466882_j_comp-2023-0116_ref_024","doi-asserted-by":"crossref","unstructured":"A. Samanta, F. Esposito, and T. G. Nguyen, \u201cFault-tolerant mechanism for edge-based iot networks with demand uncertainty,\u201d IEEE Internet Things J., vol. 8, no. 23. pp. 16963\u201316971, 2021.","DOI":"10.1109\/JIOT.2021.3075681"},{"key":"2024051313123466882_j_comp-2023-0116_ref_025","doi-asserted-by":"crossref","unstructured":"D. Takao, K. Sugiura, and Y. Ishikawa, Approximate fault-tolerant data stream aggregation for edge computing,\u201d In Big-Data-Analytics in Astronomy, Science, and Engineering: 9th International Conference on Big Data Analytics, BDA 2021, Virtual Event, December 7\u20139, 2021, Proceedings, Berlin, Heidelberg, Springer-Verlag, pp. 233\u2013244, 2021.","DOI":"10.1007\/978-3-030-96600-3_17"},{"key":"2024051313123466882_j_comp-2023-0116_ref_026","doi-asserted-by":"crossref","unstructured":"C. Wang, C. Gill, and C. Lu, \u201cFrame: Fault tolerant and real-time messaging for edge computing,\u201d In 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), pp. 976\u2013 985. IEEE, 2019a.","DOI":"10.1109\/ICDCS.2019.00101"},{"key":"2024051313123466882_j_comp-2023-0116_ref_027","doi-asserted-by":"crossref","unstructured":"Q. Wang, J. M. Fornes, C. Anagnostopoulos, and K. Kolomvatsos, \u201cPredictive model resilience in edge computing,\u201d Accepted on IEEE 8th World Forum on Internet of Things 2022.","DOI":"10.1109\/WF-IoT54382.2022.10152282"},{"key":"2024051313123466882_j_comp-2023-0116_ref_028","doi-asserted-by":"crossref","unstructured":"C. Chatfield, \u201cModel uncertainty, data mining and statistical inference,\u201d Journal of the Royal Statistical Society. Series A (Statistics in Society), vol. 158, no. 3. pp. 419\u2013466, 1995.","DOI":"10.2307\/2983440"},{"key":"2024051313123466882_j_comp-2023-0116_ref_029","doi-asserted-by":"crossref","unstructured":"A. E. Raftery, D. Madigan, and J. A. Hoeting, \u201cBayesian model averaging for linear regression models,\u201d J. Am. Stat. Assoc., vol. 92, no. 437. pp. 179\u2013191, 1997.","DOI":"10.1080\/01621459.1997.10473615"},{"key":"2024051313123466882_j_comp-2023-0116_ref_030","doi-asserted-by":"crossref","unstructured":"N. Harth, and C. Anagnostopoulos, \u201cEdge-centric efficient regression analytics,\u201d In 2018 IEEE EDGE, pp. 93\u2013100. IEEE, 2018.","DOI":"10.1109\/EDGE.2018.00020"},{"key":"2024051313123466882_j_comp-2023-0116_ref_031","doi-asserted-by":"crossref","unstructured":"G. S. Sampaio, A. R. de Aguiar Vallim Filho, L. S. da Silva, and L. A. da Silva, \u201cPrediction of motor failure time using an artificial neural network,\u201d Sensors, vol. 19, no. 19. p. 4342, 2019.","DOI":"10.3390\/s19194342"},{"key":"2024051313123466882_j_comp-2023-0116_ref_032","doi-asserted-by":"crossref","unstructured":"P. T\u00fcfekci, \u201cPrediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods,\u201d Int J. Electr. Power Energy Syst., vol. 60, pp. 126\u2013140, 2014.","DOI":"10.1016\/j.ijepes.2014.02.027"},{"key":"2024051313123466882_j_comp-2023-0116_ref_033","doi-asserted-by":"crossref","unstructured":"L. McInnes, J. Healy, and J. Melville, \u201cUMAP: Uniform manifold approximation and projection for dimension reduction,\u201d 2018.","DOI":"10.21105\/joss.00861"}],"container-title":["Open Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/comp-2023-0116\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/comp-2023-0116\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T13:12:58Z","timestamp":1715605978000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/comp-2023-0116\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,1]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,5,13]]},"published-print":{"date-parts":[[2024,5,13]]}},"alternative-id":["10.1515\/comp-2023-0116"],"URL":"https:\/\/doi.org\/10.1515\/comp-2023-0116","relation":{},"ISSN":["2299-1093"],"issn-type":[{"type":"electronic","value":"2299-1093"}],"subject":[],"published":{"date-parts":[[2024,1,1]]},"article-number":"20230116"}}