{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:16:44Z","timestamp":1759331804576,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,2,8]],"date-time":"2019-02-08T00:00:00Z","timestamp":1549584000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","award":["RG121\/15"],"award-info":[{"award-number":["RG121\/15"]}],"id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s10586-019-02912-6","type":"journal-article","created":{"date-parts":[[2019,2,8]],"date-time":"2019-02-08T23:07:48Z","timestamp":1549667268000},"page":"1299-1315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["$$FC^{2}$$ F C 2 : cloud-based cluster provisioning for distributed machine learning"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2882-2837","authenticated-orcid":false,"given":"Nguyen Binh Duong","family":"Ta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,8]]},"reference":[{"key":"2912_CR1","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4960\u20134964. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"2912_CR2","first-page":"583","volume":"14","author":"M Li","year":"2014","unstructured":"Li, M., Andersen, D.G., Park, J.W., Smola, A.J., Ahmed, A., Josifovski, V., Long, J., Shekita, E.J., Su, B.Y.: Scaling distributed machine learning with the parameter server. OSDI 14, 583\u2013598 (2014)","journal-title":"OSDI"},{"key":"2912_CR3","doi-asserted-by":"crossref","unstructured":"Ulanov, A., Simanovsky, A., Marwah, M.: Modeling scalability of distributed machine learning. In: 2017 IEEE 33rd International Conference on Data Engineering (ICDE), pp. 1249\u20131254. IEEE (2017)","DOI":"10.1109\/ICDE.2017.160"},{"key":"2912_CR4","doi-asserted-by":"crossref","unstructured":"Yan, F., Ruwase, O., He, Y., Chilimbi, T.: Performance modeling and scalability optimization of distributed deep learning systems. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1355\u20131364. ACM (2015)","DOI":"10.1145\/2783258.2783270"},{"key":"2912_CR5","unstructured":"Amazon Machine Learning. https:\/\/aws.amazon.com\/machine-learning . August 2018"},{"key":"2912_CR6","unstructured":"Microsoft Azure Machine Learning Studio. https:\/\/studio.azureml.net . August 2018"},{"key":"2912_CR7","unstructured":"Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M., Xiao, T., Xu, B., Zhang, C., Zhang, Z.: Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 (2015)"},{"key":"2912_CR8","first-page":"265","volume":"16","author":"M Abadi","year":"2016","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M.: Tensorflow: a system for large-scale machine learning. OSDI 16, 265\u2013283 (2016)","journal-title":"OSDI"},{"key":"2912_CR9","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on Multimedia, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"2912_CR10","first-page":"571","volume":"14","author":"TM Chilimbi","year":"2014","unstructured":"Chilimbi, T.M., Suzue, Y., Apacible, J., Kalyanaraman, K.: Project adam: building an efficient and scalable deep learning training system. OSDI 14, 571\u2013582 (2014)","journal-title":"OSDI"},{"key":"2912_CR11","unstructured":"Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., Mao, M., Senior, A., Tucker, P., Yang, K., Le, Q.V., et\u00a0al.: Large scale distributed deep networks. In: Advances in Neural Information Processing Systems, pp. 1223\u20131231 (2012)"},{"issue":"6","key":"2912_CR12","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2018","unstructured":"Varol, G., Laptev, I., Schmid, C.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510\u20131517 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"2912_CR13","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2912_CR14","doi-asserted-by":"crossref","unstructured":"Klein, G., Kim, Y., Deng, Y., Senellart, J., Rush, A.M.: Opennmt: Open-source toolkit for neural machine translation. arXiv preprint arXiv:1701.02810 (2017)","DOI":"10.18653\/v1\/P17-4012"},{"issue":"7587","key":"2912_CR15","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"2912_CR16","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"2912_CR17","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, Vol. 1, p. 3 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"2912_CR18","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733. IEEE (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2912_CR19","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"issue":"4s","key":"2912_CR20","first-page":"69","volume":"12","author":"W Wang","year":"2016","unstructured":"Wang, W., Chen, G., Chen, H., Dinh, T.T.A., Gao, J., Ooi, B.C., Tan, K.L., Wang, S., Zhang, M.: Deep learning at scale and at ease. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 12(4s), 69 (2016)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"issue":"2","key":"2912_CR21","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/TBDATA.2015.2472014","volume":"1","author":"EP Xing","year":"2015","unstructured":"Xing, E.P., Ho, Q., Dai, W., Kim, J.K., Wei, J., Lee, S., Zheng, X., Xie, P., Kumar, A., Yu, Y.: Petuum: a new platform for distributed machine learning on big data. IEEE Trans. Big Data 1(2), 49\u201367 (2015)","journal-title":"IEEE Trans. Big Data"},{"key":"2912_CR22","doi-asserted-by":"crossref","unstructured":"Watcharapichat, P., Morales, V.L., Fernandez, R.C., Pietzuch, P.: Ako: Decentralised deep learning with partial gradient exchange. In: Proceedings of the Seventh ACM Symposium on Cloud Computing, pp. 84\u201397. ACM (2016)","DOI":"10.1145\/2987550.2987586"},{"key":"2912_CR23","doi-asserted-by":"crossref","unstructured":"Jonas, E., Pu, Q., Venkataraman, S., Stoica, I., Recht, B.: Occupy the cloud: distributed computing for the 99%. In: Proceedings of the 2017 Symposium on Cloud Computing, pp. 445\u2013451. ACM (2017)","DOI":"10.1145\/3127479.3128601"},{"key":"2912_CR24","doi-asserted-by":"crossref","unstructured":"Duong, T.N.B., Zhong, J., Cai, W., Li, Z., Zhou, S.: Ra2: Predicting simulation execution time for cloud-based design space explorations. In: Proceedings of the 20th International Symposium on Distributed Simulation and Real-Time Applications, pp. 120\u2013127. IEEE Press (2016)","DOI":"10.1109\/DS-RT.2016.9"},{"key":"2912_CR25","doi-asserted-by":"crossref","unstructured":"Yan, F., Ruwase, O., He, Y., Smirni, E.: Serf: efficient scheduling for fast deep neural network serving via judicious parallelism. In: SC16: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 300\u2013311. IEEE (2016)","DOI":"10.1109\/SC.2016.25"},{"key":"2912_CR26","unstructured":"Sergeev, A., Del\u00a0Balso, M.: Horovod: fast and easy distributed deep learning in tensorflow. arXiv preprint arXiv:1802.05799 (2018)"},{"key":"2912_CR27","doi-asserted-by":"crossref","unstructured":"Oyama, Y., Nomura, A., Sato, I., Nishimura, H., Tamatsu, Y., Matsuoka, S.: Predicting statistics of asynchronous SGD parameters for a large-scale distributed deep learning system on GPU supercomputers. In: 2016 IEEE International Conference on Big Data (Big Data), pp. 66\u201375. IEEE (2016)","DOI":"10.1109\/BigData.2016.7840590"},{"key":"2912_CR28","doi-asserted-by":"crossref","unstructured":"Li, A., Zong, X., Kandula, S., Yang, X., Zhang, M.: Cloudprophet: towards application performance prediction in cloud. In: ACM SIGCOMM Computer Communication Review, vol.\u00a041, pp. 426\u2013427. ACM (2011)","DOI":"10.1145\/2043164.2018502"},{"issue":"1","key":"2912_CR29","doi-asserted-by":"publisher","first-page":"e3825","DOI":"10.1002\/cpe.3825","volume":"29","author":"M Cunha","year":"2017","unstructured":"Cunha, M., Mendon\u00e7a, N., Sampaio, A.: Cloud crawler: a declarative performance evaluation environment for infrastructure-as-a-service clouds. Concurr. Comput. Pract. Exp. 29(1), e3825 (2017)","journal-title":"Concurr. Comput. Pract. Exp."},{"issue":"11","key":"2912_CR30","doi-asserted-by":"publisher","first-page":"3074","DOI":"10.1109\/TPDS.2017.2707543","volume":"28","author":"HW Li","year":"2017","unstructured":"Li, H.W., Wu, Y.S., Chen, Y.Y., Wang, C.M., Huang, Y.N.: Application execution time prediction for effective cpu provisioning in virtualization environment. IEEE Trans. Parallel Distrib. Syst. 28(11), 3074\u20133088 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2912_CR31","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.future.2016.11.002","volume":"78","author":"A Evangelinou","year":"2018","unstructured":"Evangelinou, A., Ciavotta, M., Ardagna, D., Kopaneli, A., Kousiouris, G., Varvarigou, T.: Enterprise applications cloud rightsizing through a joint benchmarking and optimization approach. Future Gener. Comput. Syst. 78, 102\u2013114 (2018)","journal-title":"Future Gener. Comput. Syst."},{"key":"2912_CR32","unstructured":"Cui, H., Cipar, J., Ho, Q., Kim, J.K., Lee, S., Kumar, A., Wei, J., Dai, W., Ganger, G.R., Gibbons, P.B., et\u00a0al.: Exploiting bounded staleness to speed up big data analytics. In: USENIX Annual Technical Conference, pp. 37\u201348 (2014)"},{"key":"2912_CR33","doi-asserted-by":"crossref","unstructured":"Sun, P., Wen, Y., Duong, T.N.B., Yan, S.: Timed dataflow: Reducing communication overhead for distributed machine learning systems. In: 2016 IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS), pp. 1110\u20131117. IEEE (2016)","DOI":"10.1109\/ICPADS.2016.0146"},{"key":"2912_CR34","doi-asserted-by":"crossref","unstructured":"Sun, P., Wen, Y., Ta, N.B.D., Yan, S.: Towards distributed machine learning in shared clusters: a dynamically-partitioned approach. In: 2017 IEEE International Conference on Smart Computing (SMARTCOMP), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/SMARTCOMP.2017.7947053"},{"key":"2912_CR35","unstructured":"Wen, W., Xu, C., Yan, F., Wu, C., Wang, Y., Chen, Y., Li, H.: Terngrad: Ternary gradients to reduce communication in distributed deep learning. In: Advances in Neural Information Processing Systems, pp. 1509\u20131519 (2017)"},{"key":"2912_CR36","doi-asserted-by":"crossref","unstructured":"Seide, F., Fu, H., Droppo, J., Li, G., Yu, D.: 1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-274"},{"key":"2912_CR37","unstructured":"Lin, Y., Han, S., Mao, H., Wang, Y., Dally, W.J.: Deep gradient compression: reducing the communication bandwidth for distributed training. arXiv preprint arXiv:1712.01887 (2017)"},{"key":"2912_CR38","doi-asserted-by":"crossref","unstructured":"Peng, Y., Bao, Y., Chen, Y., Wu, C., Guo, C.: Optimus: an efficient dynamic resource scheduler for deep learning clusters. In: Proceedings of the Thirteenth EuroSys Conference. ACM (2018)","DOI":"10.1145\/3190508.3190517"},{"key":"2912_CR39","unstructured":"Google Cloud AI. https:\/\/cloud.google.com\/products\/ai . August 2018"},{"key":"2912_CR40","unstructured":"BigML. https:\/\/bigml.com . August 2018"},{"key":"2912_CR41","unstructured":"Amazon Deep Learning AMIs. https:\/\/aws.amazon.com\/machine-learning\/amis . August 2018"},{"key":"2912_CR42","unstructured":"AWS CloudFormation. https:\/\/aws.amazon.com\/cloudformation . August 2018"},{"issue":"8","key":"2912_CR43","doi-asserted-by":"publisher","first-page":"716","DOI":"10.14778\/2212351.2212354","volume":"5","author":"Y Low","year":"2012","unstructured":"Low, Y., Bickson, D., Gonzalez, J., Guestrin, C., Kyrola, A., Hellerstein, J.M.: Distributed graphlab: a framework for machine learning and data mining in the cloud. Proc. VLDB Endow. 5(8), 716\u2013727 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"2912_CR44","doi-asserted-by":"crossref","unstructured":"Li, M., Andersen, D.G., Smola, A.J., Yu, K.: Communication efficient distributed machine learning with the parameter server. In: Advances in Neural Information Processing Systems, pp. 19\u201327 (2014)","DOI":"10.1145\/2640087.2644155"},{"key":"2912_CR45","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical Report, University of Toronto (2009)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-02912-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02912-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02912-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T14:07:50Z","timestamp":1694614070000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-02912-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,8]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["2912"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-02912-6","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2019,2,8]]},"assertion":[{"value":"25 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}