Jianxin Zhao
Liang Wang
ABSTRACT
Data analytics on edge devices has gained rapid growth in research, industry, and different aspects of our daily life. This topic still faces many challenges such as limited computation resource on edge devices. In this paper, we further identify two main challenges: the composition and deployment of data analytics services on edge devices. We present the Zoo system to address these two challenge: on one hand, it provides simple and concise domain-specific language to enable easy and and type-safe composition of different data analytics services; on the other, it utilises multiple deployment backends, including Docker container, JavaScript, and MirageOS, to accommodate the heterogeneous edge deployment environment. We show the expressiveness of Zoo with a use case, and thoroughly compare the performance of different deployment backends in evaluation.
- Deepak Agarwal, Bo Long, Jonathan Traupman, Doris Xin, and Liang Zhang. 2014. Laser: A scalable response prediction platform for online advertising. In Proc. ACM WSDM'14. ACM, 173--182. Google Scholar
Digital Library
- Amazon. 2017. AWS Lambda. https://aws.amazon.com/cn/lambda/. (2017). {Online; accessed 14-Mar-2018}.Google Scholar
- Mariusz Bojarski, Del Testa, et al. 2016. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016).Google Scholar
- Wenlin Chen, James Wilson, Stephen Tyree, Kilian Weinberger, and Yixin Chen. 2015. Compressing neural networks with the hashing trick. In International Conference on Machine Learning. 2285--2294. Google ScholarDigital Library
- Byung-Gon Chun and Petros Maniatis. 2009. Augmented smartphone applications through clone cloud execution.. In HotOS, Vol. 9. 8--11. Google ScholarDigital Library
- Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J Franklin, Joseph E Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System.. In NSDI. 613--627. Google ScholarDigital Library
- Google. 2017. Google Cloud Vision API. https://cloud.google.com/vision. (2017). Accessed Nov. 11, 2017.Google Scholar
- Andrew G. Howard, Menglong Zhu, Bo Chen, et al. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. CoRR abs/1704.04861 (2017). arXiv:1704.04861Google Scholar
- Huawei-News. 2017. HUAWEI Reveals the Future of Mobile AI at IFA 2017. http://consumer.huawei.com/en/press/news/2017/ifa2017-kirin970/. (2017). {Online; accessed 10-Nov-2017}.Google Scholar
- Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016).Google Scholar
- Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, and Matei Zaharia. 2017. NoScope: optimizing neural network queries over video at scale. Proceedings of the VLDB Endowment 10, 11 (2017), 1586--1597. Google ScholarDigital Library
- Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278--2324.Google ScholarCross Ref
- Xin Lei, Andrew W Senior, Alexander Gruenstein, and Jeffrey Sorensen. 2013. Accurate and compact large vocabulary speech recognition on mobile devices.. In Interspeech, Vol. 1.Google Scholar
- Fujun Luan, Sylvain Paris, Eli Shechtman, and Kavita Bala. 2017. Deep Photo Style Transfer. CoRR abs/1703.07511 (2017). arXiv:1703.07511 http://arxiv.org/abs/1703.07511Google Scholar
- Anil Madhavapeddy and David J Scott. 2013. Unikernels: Rise of the virtual library operating system. Queue 11, 11 (2013), 30. Google ScholarDigital Library
- Richard Mortier, Jianxin Zhao, Jon Crowcroft, Liang Wang, Qi Li, Hamed Haddadi, Yousef Amar, et al. 2016. Personal Data Management with the Databox: What's Inside the Box?. In Proceedings of the 2016 ACM Workshop on Cloud-Assisted Networking. ACM, 49--54. Google ScholarDigital Library
- Movidius. 2017. Movidius Neural Compute Stick. https://developer.movidius.com/. (2017). Accessed Nov. 11, 2017.Google Scholar
- MxNet. 2017. MxNet Model Zoo. https://mxnet.incubator.apache.org/model_zoo/index.html. (2017). {Online; accessed 14-Mar-2018}.Google Scholar
- Sandra Servia Rodríguez, Liang Wang, Jianxin R. Zhao, Richard Mortier, and Hamed Haddadi. 2018. Privacy-preserving Personal Model Training. Internet-of-Things Design and Implementation (IoTDI), The 3rd ACM/IEEE International Conference on (2018).Google Scholar
- TensorFlow Serving. 2017. TensorFlow Serving. https://www.tensorflow.org/serving/. (2017). {Online; accessed 14-Mar-2018}.Google Scholar
- Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. 2016. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2818--2826.Google ScholarCross Ref
- Berkeley Vision and Learning Center. 2017. Caffe Model Zoo. https://github.com/BVLC/caffe/wiki/Model-Zoo. (2017). {Online; accessed 14-Mar-2018}.Google Scholar
- Liang Wang. 2017. Owl: A General-Purpose Numerical Library in OCaml. CoRR abs/1707.09616 (2017). http://arxiv.org/abs/1707.09616Google Scholar
- Liang Wang, Sotiris Tasoulis, Teemu Roos, and Jussi Kangasharju. 2016. Kvasir: Scalable provision of semantically relevant web content on big data framework. IEEE Transactions on Big Data 2, 3 (2016), 219--233.Google ScholarCross Ref
- Kok-Kiong Yap, Murtaza Motiwala, Jeremy Rahe, Steve Padgett, Matthew Holliman, Gary Baldus, Marcus Hines, Taeeun Kim, Ashok Narayanan, Ankur Jain, et al. 2017. Taking the edge off with espresso: Scale, reliability and programmability for global internet peering. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication. ACM, 432--445. Google ScholarDigital Library
Index Terms
- Data Analytics Service Composition and Deployment on Edge Devices
Recommendations
Privacy-Preserving Machine Learning Based Data Analytics on Edge Devices
AIES '18: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and SocietyEmerging Machine Learning (ML) techniques, such as Deep Neural Network, are widely used in today's applications and services. However, with social awareness of privacy and personal data rapidly rising, it becomes a pressing and challenging societal ...
The Implications of Big Data Analytics Orientation upon Deployment
ICIT '18: Proceedings of the 6th International Conference on Information Technology: IoT and Smart CityBig data analytics (BDA) is becoming a key way for leading companies to outperform their peers by utilizing big data and better understanding its business environment. However, there is evidence that many firms are facing difficulties in deploying BDA ...
Comments