Machine Learning Frameworks and Algorithms for Fog and Edge Computing

Fog, edge and pervasive computing are technologies developed to overcome the limitations of cloud computing. In this chapter we will cover the role of various machine learning, deep learning frameworks, techniques and algorithms in fog, edge and pervasive computing. Latency, privacy, and bandwidth are some of the limitations or problems with the cloud computing and in this chapter, we will discuss how machine learning combined with these computing technologies can help to overcome the limitations of cloud computing. Inferencing is the main challenge in using machine learning or deep learning models, this chapter covers the various frameworks that help to provide inference and quantize the models. Even machine learning has some advantages and disadvantages, in this chapter we will cover the advantages and disadvantages of using machine learning in edge/fog/pervasive computing. We will also cover the various studies done by the researchers. Every field has numerous applications, in this chapter we will discuss the few possible applications in this fog era using machine learning techniques. By the end of the chapter you will know about the ML frameworks and the various machine learning algorithms used for fog/edge computing.

Bibliography

Aakash, R. S., Nishanth, M., Rajageethan, R., Rao, R., & Ezhilarasie, R. (2019). Data Mining Approach to Predict Forest Fire Using Fog Computing. Proceedings of the 2nd International Conference on Intelligent Computing and Control Systems, ICICCS 2018, (Iciccs), 1582–1587. https://doi.org/10.1109/ICCONS.2018.8663160
Google Scholar
Al-Rakhami, M., Alsahli, M., Hassan, M. M., Alamri, A., Guerrieri, A., & Fortino, G. (2018). Cost efficient edge intelligence framework using docker containers. Proceedings - IEEE 16th International Conference on Dependable, Autonomic and Secure Computing, IEEE 16th International Conference on Pervasive Intelligence and Computing, IEEE 4th International Conference on Big Data Intelligence and Computing and IEEE 3, 792–799. https://doi.org/10.1109/DASC/PiCom/DataCom/CyberSciTec.2018.00138
10.1109/DASC/PiCom/DataCom/CyberSciTec.2018.00138
Google Scholar
Cui, Q., Zhou, Z., Fu, Z., Meng, R., Sun, X., & Jonathan Wu, Q. M. (2019). Image Steganography Based on Foreground Object Generation by Generative Adversarial Networks in Mobile Edge Computing with Internet of Things. IEEE Access, 7, 90815–90824. https://doi.org/10.1109/ACCESS.2019.2913895
10.1109/ACCESS.2019.2913895
Web of Science® Google Scholar
Han, S., Mao, H., & Dally, W. J. (2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings, 1–14.
Google Scholar
Hou, S., & Huang, X. (2019). Use of Machine Learning in Detecting Network Security of Edge Computing System. 2019 4th IEEE International Conference on Big Data Analytics, ICBDA 2019, 252–256. https://doi.org/10.1109/ICBDA.2019.8713237
10.1109/ICBDA.2019.8713237
Google Scholar
Kim, D., Yang, H., Chung, M., Cho, S., Kim, H., Kim, M., … Kim, E. (2018). Squeezed Convolutional Variational AutoEncoder for unsupervised anomaly detection in edge device industrial Internet of Things. 2018 International Conference on Information and Computer Technologies, ICICT 2018, 67–71. https://doi.org/10.1109/INFOCT.2018.8356842
10.1109/INFOCT.2018.8356842
Google Scholar
Kulkarni, S., Saha, S., & Hockenbury, R. (2014). Preserving privacy in sensor-fog networks. 2014 9th International Conference for Internet Technology and Secured Transactions, ICITST 2014, (1), 96–99. https://doi.org/10.1109/ICITST.2014.7038785
10.1109/ICITST.2014.7038785
Google Scholar
Lai, L., & Suda, N. (2018). Enabling deep learning at the IoT edge. IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD. https://doi.org/10.1145/3240765.3243473
Google Scholar
LeCun, Y., Denker, J. S., & Solla, S. A. (1990). Optimal Brain Damage (Pruning). Advances in Neural Information Processing Systems, 598–605. Retrieved from http://papers.nips.cc/paper/250-optimal-brain-damage.pdf%0Ahttps://papers.nips.cc/paper/250-optimal-brain-damage
Google Scholar
Li, B., Wang, K., Xue, D., & Pei, Y. (2018). K-Means based edge server deployment algorithm for edge computing environments. Proceedings - 2018 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People and Smart City Innovations, SmartWorld/UIC/ATC/ScalCom/CBDCo, 1169–1174. https://doi.org/10.1109/SmartWorld.2018.00203
10.1109/SmartWorld.2018.00203
Google Scholar
Li, G., Liu, Y., Wu, J., Lin, D., & Zhao, S. (2019). Methods of resource scheduling based on optimized fuzzy clustering in fog computing. Sensors (Switzerland), 19(9). https://doi.org/10.3390/s19092122
10.3390/s19092122
Google Scholar
Manukumar, S. T., & Muthuswamy, V. (2020). A Novel Resource Management Framework for Fog Computing by Using Machine Learning Algorithm. https://doi.org/10.4018/978-1-7998-0194-8.ch002
10.4018/978-1-7998-0194-8.ch002
Google Scholar
Na, T., Lee, M., Mudassar, B. A., Saha, P., Ko, J. H., & Mukhopadhyay, S. (2019). Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms. Proceedings of the International Joint Conference on Neural Networks, 2019-July, 1–10. https://doi.org/10.1109/IJCNN.2019.8851932
10.1109/IJCNN.2019.8851932
Google Scholar
Nikouei, S. Y., Chen, Y., Song, S., Xu, R., Choi, B. Y., & Faughnan, T. R. (2018). Real-time human detection as an edge service enabled by a lightweight CNN. Proceedings - 2018 IEEE International Conference on Edge Computing, EDGE 2018 - Part of the 2018 IEEE World Congress on Services, 125–129. https://doi.org/10.1109/EDGE.2018.00025
10.1109/EDGE.2018.00025
Google Scholar
Pena Queralta, J., Gia, T. N., Tenhunen, H., & Westerlund, T. (2019). Edge-AI in LoRa-based health monitoring: Fall detection system with fog computing and LSTM recurrent neural networks. 2019 42nd International Conference on Telecommunications and Signal Processing, TSP 2019, 601–604. https://doi.org/10.1109/TSP.2019.8768883
10.1109/TSP.2019.8768883
Google Scholar
Qiu, J., Wang, J., Yao, S., Guo, K., & Li, B. (2016). Going Deeper with Embedded FPGA Platform for Convolutional Neural Network • Deep Learning and Convolutional Neural Network – V2 : Brief introduction. 26–35.
Google Scholar
Rodrigues, T. K., Suto, K., & Kato, N. (2019). Hyperparameter Study of Machine Learning Solutions for the Edge Server Deployment Problem. 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall), ( 18), 1–5.
Google Scholar
Srinivas, S., & Babu, R. V. (2015). Data-free Parameter Pruning for Deep Neural Networks. 31.1-31.12. https://doi.org/10.5244/c.29.31
Google Scholar
Vijayakumar, V., Malathi, D., Subramaniyaswamy, V., Saravanan, P., & Logesh, R. (2019). Fog computing-based intelligent healthcare system for the detection and prevention of mosquito-borne diseases. Computers in Human Behavior, 100, 275–285. https://doi.org/10.1016/j.chb.2018.12.009
10.1016/j.chb.2018.12.009
Web of Science® Google Scholar
Yang, Z., Chen, N., Chen, Y., & Zhou, N. (2018). A Novel PMU Fog Based Early Anomaly Detection for an Efficient Wide Area PMU Network. 2018 IEEE 2nd International Conference on Fog and Edge Computing, ICFEC 2018 - In Conjunction with 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, IEEE/ACM CCGrid 2018, 1–10. https://doi.org/10.1109/CFEC.2018.8358730
10.1109/CFEC.2018.8358730
Google Scholar
Zhu, C., Mao, H., Han, S., & Dally, W. J. (2019). Trained ternary quantization. 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings, 1–10.
Google Scholar

Citing Literature

Fog, Edge, and Pervasive Computing in Intelligent IoT Driven Applications