{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T20:33:03Z","timestamp":1782937983798,"version":"3.54.5"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,12,17]],"date-time":"2019-12-17T00:00:00Z","timestamp":1576540800000},"content-version":"vor","delay-in-days":16,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2017YFD0400101"],"award-info":[{"award-number":["2017YFD0400101"]}]},{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"crossref","award":["61902236"],"award-info":[{"award-number":["61902236"]}],"id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Wireless Com Network"],"published-print":{"date-parts":[[2019,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Server workload in the form of cloud-end clusters is a key factor in server maintenance and task scheduling. How to balance and optimize hardware resources and computation resources should thus receive more attention. However, we have observed that the disordered execution of running application and batching seriously cuts down the efficiency of the server. To improve the workload prediction accuracy, this paper proposes an approach using the long short-term memory (LSTM) encoder-decoder network with attention mechanism. First, the approach extracts the sequential and contextual features of the historical workload data through the encoder network. Second, the model integrates the attention mechanism into the decoder network, through which the prediction for batch workloads can be carried out. Third, experiments carried out on Alibaba and Dinda workload traces dataset demonstrate that our method achieves state-of-the-art performance in mixed workload prediction in cloud computing environment. Furthermore, we also propose a scroll prediction method, which splits a long prediction sequence into several small sequences to monitor and control prediction accuracy. This work helps to dynamically guide the configuration for workload balancing.<\/jats:p>","DOI":"10.1186\/s13638-019-1605-z","type":"journal-article","created":{"date-parts":[[2019,12,17]],"date-time":"2019-12-17T19:03:02Z","timestamp":1576609382000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":124,"title":["A novel approach to workload prediction using attention-based LSTM encoder-decoder network in cloud environment"],"prefix":"10.1186","volume":"2019","author":[{"given":"Yonghua","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weilin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghao","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,12,17]]},"reference":[{"key":"1605_CR1","doi-asserted-by":"crossref","unstructured":"Josep AD, Katz RA, Konwinski A, Lee G, Patterson D, Rabkin A. A view of cloud computing. Commun ACM. 2010;53.","DOI":"10.1145\/1721654.1721672"},{"key":"1605_CR2","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s13174-010-0007-6","volume":"1","author":"Q Zhang","year":"2010","unstructured":"Q. Zhang, L. Cheng, R. Boutaba, Cloud computing: state-of-the-art and research challenges. J Internet Serv Appl. 1, 7\u201318 (2010)","journal-title":"J Internet Serv Appl."},{"key":"1605_CR3","doi-asserted-by":"crossref","unstructured":"Rajan K, Kakadia D, Curino C, Krishnan S. PerfOrator: eloquent performance models for resource optimization. In: Proceedings of the Seventh ACM Symposium on Cloud Computing. ACM; 2016. p. 415\u201327.","DOI":"10.1145\/2987550.2987566"},{"key":"1605_CR4","doi-asserted-by":"crossref","unstructured":"Lianyong Qi, Jiguo Yu, Zhili Zhou. An invocation cost optimization method for web services in cloud environment. Scientific Programming, Volume 2017, Article ID 4358536, 9 pages, 2017.","DOI":"10.1155\/2017\/4358536"},{"key":"1605_CR5","first-page":"42","volume-title":"international parallel and distributed processing symposium","author":"L Yang","year":"2003","unstructured":"L. Yang, I.T. Foster, J.M. Schopf, in international parallel and distributed processing symposium. Homeostatic and tendency-based CPU load predictions (2003), p. 42"},{"key":"1605_CR6","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1109\/TPDS.2006.24","volume":"17","author":"PA Dinda","year":"2006","unstructured":"P.A. Dinda, Design, implementation, and performance of an extensible toolkit for resource prediction in distributed systems. IEEE Trans Parallel Distrib Syst 17, 160\u2013173 (2006)","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1605_CR7","doi-asserted-by":"crossref","unstructured":"Lianyong Qi, Xiaolong Xu, Wanchun Dou, Jiguo Yu, Zhili Zhou, Xuyun Zhang. Time-aware IoE service recommendation on sparse data, Mobile Information Systems, Volume 2016, Article ID 4397061, 12 pages, 2016.","DOI":"10.1155\/2016\/4397061"},{"key":"1605_CR8","doi-asserted-by":"crossref","unstructured":"Di S, Kondo D, Cirne W. Host load prediction in a Google compute cloud with a Bayesian model. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society Press; 2012. p. 21.","DOI":"10.1109\/SC.2012.68"},{"key":"1605_CR9","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.1016\/j.neucom.2011.01.009","volume":"74","author":"F Benhammadi","year":"2011","unstructured":"F. Benhammadi, Z. Gessoum, A. Mokhtari, CPU load prediction using neuro-fuzzy and Bayesian inferences. Neurocomputing 74, 1606\u20131616 (2011)","journal-title":"Neurocomputing"},{"key":"1605_CR10","doi-asserted-by":"crossref","unstructured":"Liang J, Cao J, Wang J, Xu Y. Long-term CPU load prediction. In: 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing. IEEE; 2011. p. 23\u20136.","DOI":"10.1109\/DASC.2011.28"},{"key":"1605_CR11","doi-asserted-by":"publisher","first-page":"3037","DOI":"10.1007\/s11227-015-1426-8","volume":"71","author":"Q Yang","year":"2015","unstructured":"Q. Yang, Y. Zhou, Y. Yu, J. Yuan, X. Xing, S. Du, Multi-step-ahead host load prediction using autoencoder and echo state networks in cloud computing. J Supercomput 71, 3037\u20133053 (2015)","journal-title":"J Supercomput"},{"key":"1605_CR12","doi-asserted-by":"publisher","first-page":"6554","DOI":"10.1007\/s11227-017-2044-4","volume":"74","author":"B Song","year":"2018","unstructured":"B. Song, Y. Yu, Y. Zhou, Z. Wang, S. Du, Host load prediction with long short-term memory in cloud computing. J Supercomput 74, 6554\u20136568 (2018)","journal-title":"J Supercomput"},{"key":"1605_CR13","doi-asserted-by":"crossref","unstructured":"Peng C, Li Y, Yu Y, Zhou Y, Du S. Multi-step-ahead host load prediction with GRU based encoder-decoder in cloud computing. In: 2018 10th International Conference on Knowledge and Smart Technology (KST). IEEE. p. 186\u201391.","DOI":"10.1109\/KST.2018.8426104"},{"key":"1605_CR14","doi-asserted-by":"crossref","unstructured":"Di S, Kondo D, Cappello F. Characterizing cloud applications on a Google data center. In: 2013 42nd International Conference on Parallel Processing. IEEE; 2013. p. 468\u201373.","DOI":"10.1109\/ICPP.2013.56"},{"key":"1605_CR15","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1145\/1773394.1773400","volume":"37","author":"AK Mishra","year":"2010","unstructured":"A.K. Mishra, J.L. Hellerstein, W. Cirne, C.R. Das, Towards characterizing cloud backend workloads: insights from Google compute clusters. ACM SIGMETRICS Perform Eval Rev. 37, 34\u201341 (2010)","journal-title":"ACM SIGMETRICS Perform Eval Rev."},{"key":"1605_CR16","unstructured":"Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv Prepr arXiv14123555. 2014."},{"key":"1605_CR17","unstructured":"Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks. In: Advances in neural information processing systems. 2014. p. 3104\u201312."},{"key":"1605_CR18","unstructured":"Akioka S, Muraoka Y. Extended forecast of CPU and network load on computational grid. In: IEEE International Symposium on Cluster Computing and the Grid, 2004. CCGrid 2004. IEEE; 2004. p. 765\u201372."},{"key":"1605_CR19","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.ins.2018.11.030","volume":"480","author":"L Qi","year":"2019","unstructured":"L. Qi, R. Wang, S. Li, Q. He, X. Xu, C. Hu, Time-aware distributed service recommendation with privacy-preservation. Inform Sci 480, 354\u2013364 (2019)","journal-title":"Inform Sci"},{"key":"1605_CR20","doi-asserted-by":"crossref","unstructured":"Yang D, Cao J, Yu C, Xiao J. A multi-step-ahead CPU load prediction approach in distributed system. In: 2012\u2009Second International Conference on Cloud and Green Computing. IEEE; 2012. p. 206\u201313.","DOI":"10.1109\/CGC.2012.32"},{"issue":"1","key":"1605_CR21","first-page":"1","volume":"13","author":"L Qi","year":"2017","unstructured":"L. Qi, P. Dai, J. Yu, Z. Zhou, Y. Xu, \u201cTime-Location-Frequency\u201d-aware Internet of things service selection based on historical records. Int J Distributed Sensor Netw 13(1), 1\u20139 (2017)","journal-title":"Int J Distributed Sensor Netw"},{"key":"1605_CR22","doi-asserted-by":"publisher","first-page":"3409","DOI":"10.1109\/TSP.2004.837418","volume":"52","author":"M Han","year":"2004","unstructured":"M. Han, J. Xi, S. Xu, F.-L. Yin, Prediction of chaotic time series based on the recurrent predictor neural network. IEEE Trans Signal Process 52, 3409\u20133416 (2004)","journal-title":"IEEE Trans Signal Process"},{"key":"1605_CR23","doi-asserted-by":"crossref","unstructured":"Wu Y, Yuan Y, Yang G, Zheng W. Load prediction using hybrid model for computational grid. In: 2007 8th IEEE\/ACM International Conference on Grid Computing. IEEE; 2007. p. 235\u201342.","DOI":"10.1109\/GRID.2007.4354138"},{"key":"1605_CR24","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s10586-018-2868-6","volume":"22","author":"P Singh","year":"2019","unstructured":"P. Singh, P. Gupta, K. Jyoti, Tasm: technocrat arima and svr model for workload prediction of web applications in cloud. Cluster Comput 22, 619\u2013633 (2019)","journal-title":"Cluster Comput"},{"key":"1605_CR25","unstructured":"Dabrowski C, Hunt F. Using Markov chain analysis to study dynamic behaviour in large-scale grid systems. In: Proceedings of the Seventh Australasian Symposium on Grid Computing and e-Research-Volume 99. Australian Computer Society, Inc.; 2009. p. 29\u201340."},{"key":"1605_CR26","doi-asserted-by":"crossref","unstructured":"Huang J, Li C, Yu J. Resource prediction based on double exponential smoothing in cloud computing. In: 2012 2nd International Conference on Consumer Electronics, Communications and Networks (CECNet). IEEE; 2012. p. 2056\u201360.","DOI":"10.1109\/CECNet.2012.6201461"},{"key":"1605_CR27","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/s10723-016-9364-0","volume":"14","author":"NJ Kansal","year":"2016","unstructured":"N.J. Kansal, I. Chana, Energy-aware virtual machine migration for cloud computing-a firefly optimization approach. J Grid Comput. 14, 327\u2013345 (2016)","journal-title":"J Grid Comput."},{"key":"1605_CR28","doi-asserted-by":"crossref","unstructured":"Wang X, Huang S, Fu S, Kavi K. Characterizing workload of web applications on virtualized servers. In: Workshop on Big Data Benchmarks, Performance Optimization, and Emerging Hardware. Springer; 2014. p. 98\u2013108.","DOI":"10.1007\/978-3-319-13021-7_8"},{"key":"1605_CR29","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1002\/spe.2231","volume":"44","author":"J Cao","year":"2014","unstructured":"J. Cao, J. Fu, M. Li, J. Chen, CPU load prediction for cloud environment based on a dynamic ensemble model. Softw Pract Exp. 44, 793\u2013804 (2014)","journal-title":"Softw Pract Exp."},{"key":"1605_CR30","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1109\/TCC.2014.2350475","volume":"3","author":"RN Calheiros","year":"2014","unstructured":"R.N. Calheiros, E. Masoumi, R. Ranjan, R. Buyya, Workload prediction using ARIMA model and its impact on cloud applications\u2019 QoS. IEEE Trans Cloud Comput 3, 449\u2013458 (2014)","journal-title":"IEEE Trans Cloud Comput"},{"key":"1605_CR31","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.future.2017.10.047","volume":"81","author":"J Kumar","year":"2018","unstructured":"J. Kumar, A.K. Singh, Workload prediction in cloud using artificial neural network and adaptive differential evolution. Futur Gener Comput Syst 81, 41\u201352 (2018)","journal-title":"Futur Gener Comput Syst"},{"key":"1605_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1342171.1342172","volume":"3","author":"B Urgaonkar","year":"2008","unstructured":"B. Urgaonkar, P. Shenoy, A. Chandra, P. Goyal, T. Wood, Agile dynamic provisioning of multi-tier internet applications. ACM Trans Auton Adapt Syst 3, 1 (2008)","journal-title":"ACM Trans Auton Adapt Syst"},{"key":"1605_CR33","doi-asserted-by":"crossref","unstructured":"Lu C, Ye K, Xu G, Xu C-Z, Bai T. Imbalance in the cloud: an analysis on alibaba cluster trace. In: 2017 IEEE International Conference on Big Data (Big Data). IEEE; 2017. p. 2884\u201392.","DOI":"10.1109\/BigData.2017.8258257"},{"key":"1605_CR34","doi-asserted-by":"crossref","unstructured":"Abdul-Rahman OA, Aida K. Towards understanding the usage behavior of Google cloud users: the mice and elephants phenomenon. In: 2014 IEEE 6th International Conference on Cloud Computing Technology and Science. IEEE; 2014. p. 272\u20137.","DOI":"10.1109\/CloudCom.2014.75"},{"key":"1605_CR35","doi-asserted-by":"crossref","unstructured":"Verma A, Pedrosa L, Korupolu M, Oppenheimer D, Tune E, Wilkes J. Large-scale cluster management at Google with Borg. In: Proceedings of the Tenth European Conference on Computer Systems. ACM; 2015. p. 18.","DOI":"10.1145\/2741948.2741964"},{"key":"1605_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/8584252","volume":"2017","author":"Zheng Huang","year":"2017","unstructured":"Z. Huang, J. Peng, H. Lian, J. Guo, W. Qiu, Deep recurrent model for server load and performance prediction in data center. Complexity 2017 (2017)","journal-title":"Complexity"},{"key":"1605_CR37","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1016\/j.procs.2017.12.087","volume":"125","author":"J Kumar","year":"2018","unstructured":"J. Kumar, R. Goomer, A.K. Singh, Long short term memory recurrent neural network (lstm-rnn) based workload forecasting model for cloud datacenters. Procedia Comput Sci 125, 676\u2013682 (2018)","journal-title":"Procedia Comput Sci"},{"key":"1605_CR38","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Y. Bengio, P. Simard, P. Frasconi, Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5, 157\u2013166 (1994)","journal-title":"IEEE Trans Neural Netw"},{"key":"1605_CR39","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1605_CR40","unstructured":"Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. arXiv Prepr arXiv14090473. 2014."},{"key":"1605_CR41","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv Prepr arXiv14061078. 2014.","DOI":"10.3115\/v1\/D14-1179"},{"key":"1605_CR42","doi-asserted-by":"crossref","unstructured":"Luong M-T, Pham H, Manning CD. Effective approaches to attention-based neural machine translation. arXiv Prepr arXiv150804025. 2015.","DOI":"10.18653\/v1\/D15-1166"},{"key":"1605_CR43","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision. 2015. p. 1026\u201334.","DOI":"10.1109\/ICCV.2015.123"},{"key":"1605_CR44","doi-asserted-by":"crossref","unstructured":"Huber PJ. Robust estimation of a location parameter. In: Breakthroughs in statistics. Springer; 1992. p. 492\u2013518.","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"1605_CR45","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv Prepr arXiv14126980. 2014."},{"key":"1605_CR46","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"K Cho","year":"2015","unstructured":"K. Cho, A. Courville, Y. Bengio, Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans Multimed 17, 1875\u20131886 (2015)","journal-title":"IEEE Trans Multimed"},{"key":"1605_CR47","doi-asserted-by":"publisher","first-page":"1402","DOI":"10.1007\/s11227-014-1097-x","volume":"68","author":"Q Yang","year":"2014","unstructured":"Q. Yang, C. Peng, H. Zhao, Y. Yu, Y. Zhou, Z. Wang, et al., A new method based on PSR and EA-GMDH for host load prediction in cloud computing system. J Supercomput. 68, 1402\u20131417 (2014)","journal-title":"J Supercomput."}],"container-title":["EURASIP Journal on Wireless Communications and Networking"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13638-019-1605-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13638-019-1605-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13638-019-1605-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,16]],"date-time":"2020-12-16T00:17:13Z","timestamp":1608077833000},"score":1,"resource":{"primary":{"URL":"https:\/\/jwcn-eurasipjournals.springeropen.com\/articles\/10.1186\/s13638-019-1605-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["1605"],"URL":"https:\/\/doi.org\/10.1186\/s13638-019-1605-z","relation":{},"ISSN":["1687-1499"],"issn-type":[{"value":"1687-1499","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]},"assertion":[{"value":"7 August 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}}],"article-number":"274"}}