Flexible Deep Learning in Edge Computing for Internet of Things

Rashmi, K and Sneha, S and Archana, N and Gayathri, R Flexible Deep Learning in Edge Computing for Internet of Things. International Journal of Pure and Applied Mathematics, 2018, vol. 119, n. 10, pp. 531-543. [Journal article (Paginated)]

This is the latest version of this item.

[img]
Preview
 Text
Flexible Deep Learning in Edge Computing for Internet of Things.pdf
Download (623kB) | Preview

English abstract

Deep learning is a promising approach for extracting accurate information from raw sensor data from IoT devices deployed in complex environments. Because of its multilayer structure, deep learning is also appropriate for the edge computing environment. Traditional edge computing models have rigid characteristics. Flexible edge computing architecture solves rigidity in IoT edge computing. Proposed model combines deep learning into edge computing and flexible edge computing architecture using multiple agents. Since existing edge nodes have limited processing capability, we also design a novel offloading strategy to optimize the performance of IoT deep learning applications with edge computing. FEC architecture is a flexible and advanced IoT system model characterized by environment adaptation ability and user orientation ability. In the performance evaluation, we test the performance of executing deep learning tasks in FEC architecture for edge computing environment. The evaluation results show that our method outperforms other optimization solutions on deep learning for IoT.

Spanish abstract

El aprendizaje profundo es un enfoque prometedor para extraer información precisa de datos sin procesar del sensor de dispositivos IoT implementados en entornos complejos. Debido a su estructura multicapa, el aprendizaje profundo también es apropiado para el entorno informático de borde. Los modelos informáticos de borde tradicionales tienen características rígidas. La arquitectura flexible de informática de borde resuelve la rigidez en la informática de borde de IoT. El modelo propuesto combina el aprendizaje profundo en la computación de borde y la arquitectura de computación de borde flexible utilizando múltiples agentes. Dado que los nodos perimetrales existentes tienen una capacidad de procesamiento limitada, también diseñamos una nueva estrategia de descarga para optimizar el rendimiento de las aplicaciones de aprendizaje profundo de IoT con la computación perimetral. La arquitectura FEC es un modelo de sistema IoT flexible y avanzado que se caracteriza por la capacidad de adaptación del entorno y la capacidad de orientación del usuario. En la evaluación del rendimiento, probamos el rendimiento de la ejecución de tareas de aprendizaje profundo en la arquitectura FEC para el entorno informático de borde. Los resultados de la evaluación muestran que nuestro método supera a otras soluciones de optimización en aprendizaje profundo para IoT.

Item type: Journal article (Paginated)
Keywords: IoT, deep learning, FEC, edge computing.
Subjects: L. Information technology and library technology
L. Information technology and library technology > LC. Internet, including WWW.
L. Information technology and library technology > LK. Software methodologies and engineering.
Depositing user: Dr. R Gayathri
Date deposited: 04 Aug 2020 06:43
Last modified: 04 Aug 2020 06:43
URI: http://hdl.handle.net/10760/40242

Available Versions of this Item

References

Lane N.D., Georgiev P ., Qendro L., Deepear: Robust Smartphone Audio Sensing in Unconstrained Acoustic Environments Using Deep Learning, Proc. ACM Int’l. Joint Conf. Pervasive and Ubiquitous Computing (2015), 283–94.

Li L., Eyes in the Dark: Distributed Scene Understanding for Disaster Management, IEEE Trans. Parallel Distrib. Systems (2017).

Bhattacharya S., Lane N.D., Sparsification and Separation of Deep Learning Layers for Constrained Resource Inference on Wearables, Proc. 14th ACM Conf. Embedded Network Sensor Systems CD-ROM, ser. SenSys 16 (2016), 176–89.

Seufert M., Kwam B.K., Wamser F., Tran-Gia P., Edge network cloud sim: Placement of service chains in edge clouds using network cloud sim, In NetSoft (2017), 1–6.

Calheiros R.N., Ranjan R., Beloglazov A., De Rose C.A., Buyya R., Cloud sim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms, Software: Practice and experience 41(1) (2011), 23– 50.

Gupta H., Vahid Dastjerdi A., Ghosh S.K., Buyya R., iFogSim: A toolkit for modeling and simulation of resource management techniques in the internet of things, edge and fog computing environments, Software: Practice and Experience 47(9) (2017), 1275–1296.

Alsmirat M.A., Jararweh Y., Obaidat I., Gupta B.B., Internet of surveillance: a cloud supported large-scale wireless surveillance system, The Journal of Supercomputing 73(3) (2017), 973–992.

Stanciu A., Blockchain based distributed control system for edge computing, IEEE International Conference on Control Systems and Computer Science (CSCS) (2017), 667–671.

Sapienza M., Guardo E., Cavallo M., La Torre G., Leombruno G., Tomarchio O., Solving critical events through mobile edge computing: An approach for smart cities, IEEE International Conference on Smart Computing (SMARTCOMP) (2016), 1–5.

Cicirelli F., Guerrieri A., Spezzano G., Vinci A., An edge based platform for dynamic smart city applications, Future Generation Computer Systems (2017), 106–118.

Varghese B., Wang N., Barbhuiya S., Kilpatrick P., Nikolopoulos D.S., Challenges and opportunities in edge computing, IEEE International Conference on Smart Cloud (Smart Cloud) (2016), 20–26.

Ghose D., Robertazzi T., Foreword (special issue of cluster computing on divisible load scheduling), Cluster Computing 6(1) (2003), 5–5.

Kyong Y., Robertazzi T., Greedy signature processing with arbitrary location distributions: a divisible load framework, IEEE Transactions on Aerospace and Electronic Systems 48(4) (2012), 3027–3041.

Bharadwaj V., Ghose D., Robertazzi T., Divisible load theory: a new paradigm for load scheduling in distributed systems, Cluster Computing 6(1) (2003), 7–17.

Lin X., Lu Y., Deogun J., Goddard S., Real-time divisible load scheduling for cluster computing, In IEEE Real Time and Embedded Technology and Applications Symposium (2007), 303–314.

Mamat A., Lu Y., Deogun J., Goddard S., An efficient algorithm for real-time divisible load scheduling, In IEEE Real-Time and Embedded Technology and Applications Symposium (2010), 323–332.

Eriksson E., Dn G., Fodor V., Predictive distributed visual analysis for video in wireless sensor networks, IEEE Transactions on Mobile Computing 15(7) (2016), 1743–1756.

Al-Fuqaha A., Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications, IEEE Commun. Surveys & Tutorials 17(4) (2015), 2347–76.

Alsheikh M.A., Mobile Big Data Analytics Using Deep Learning and Apache Spark, IEEE Network 30(3) (2016), 22–29.

Tran T.X., Collaborative Mobile Edge Computing in 5G Networks: New Paradigms, Scenarios, and Challenges, IEEE Commun. Mag., 55(4) (2017), 54–61.

Liu C., A New Deep Learning-Based Food Recognition System for Dietary Assessment on an Edge Computing Service Infrastructure, IEEE Trans. Services Computing (2008).

Takuo Suganuma, Takuma Oide, Shinji Kitagami, Kenji Sugawara, Norio Shiratori, Multi agent-Based Flexible Edge Computing Architecture for IoT, Edge Computing for the Internet of Things (2018).

Tadapaneni, N. R. (2016). Overview and Opportunities of Edge Computing. Social Science Research Network.

He Li, Kaoru Ota, Mianxiong Dong, Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing, Edge computing for the internet of things (2018).

Khanna, D. (2019). Internet of Things Challenges and Opportunities. International Journal For Technological Research In Engineering


Downloads

Downloads per month over past year

Actions (login required)

View Item View Item
Contact us
Send email Sponsors
Sponsor: AIMS Sponsor: D&P Sponsor: UniNa CAB Get connected
Facebook Facebook Twitter Twitter Linkedin LinkedIn RSS RSS