DEFT: Dynamic Edge Fabric environmenT       



DEFT: Dynamic Edge Fabric environmenT - overview

Research team:
Fatemeh Jalali, Ram Kolluri, Frank suits

IBM Research Australia


Project summary:

With the proliferation of IoT devices and sensors on the Internet into the billions, the assumption that all computation can simply be pushed into the Cloud is not practical. Edge/Fog computing is needed to help Cloud computing serve more IoT applications efficiently. Currently, some applications are assigned to be served by Edge/Fog, some by Cloud and the rest by hybrid Fog-Cloud. The platform for each application is predefined and unchangeable at run-time, regardless of the real-time conditions and the performance of the system part. The current IoT gateways are merely bridges between IoT devices and the Cloud and are not smart enough to decide when to run an application on the Fog/Edge platform and when to run it on the Cloud based on the system real-time conditions for achieving a better performance.

IBM scientists are working on a new research agenda to build dynamic switching between Fog/Edge and Cloud for IoT applications for improved performance and better utilization of Fog/Edge-Cloud capabilities. We propose a new platform, DEFT (Dynamic Edge-Fabric environmenT), that can automatically learn where best to execute each task based on real-time system status and task requirements, along with learned behavior from past performance of the available resources. Such an intelligent environment is an essential part of the exploding IoT ecosystem.



[1] F. Jalali, T. Lynar,O. Smith, R. Kolluri,C. Hardgrove, N. Waywood,F. Suits, “DEFT: Dynamic Edge Fabric environmenT”, IEEE EDGE 2019, Milan, Italy, July 2019.

[2] F. Jalali, O. Smith, T. Lynar, F. Suits, “Cognitive IoT Gateways: Automatic Task Sharing and Switching between Cloud and Edge/Fog Computing”, Proceedings of the ACM SIGCOMM 2017, Los Angles, USA, August 2017.

[3] T. Lynar, F. Jalali, O. Smith,R. Kolluri,F. Suits, “Machine Learning Assisted Heuristic Approach for Optimal Task Deployment in Hybrid Cloud-Edge Environments”, AI4IoT workshop in conjunction with IJCAI2018, July 2018.

[4] A. Yousefpour, C. Fung, T Nguyen, K. Kadiyala, F. Jalali, A. Niakanlahiji, All one needs to know about fog computing and related edge computing paradigms: A complete survey, Journal of Systems Architecture, 2019.

[5] F Jalali, A Vishwanath, J De Hoog, F Suits, Interconnecting Fog computing and microgrids for greening IoT, IEEE Innovative Smart Grid Technologies-Asia (ISGT-Asia) 2016, 693-698.
[6] F Jalali, K Hinton, R Ayre, T Alpcan, RS Tucker, Fog computing may help to save energy in cloud computing, IEEE Journal on Selected Areas in Communications 34 (5), 1728-1739, 2016.


Awards & recognitions:

[1] Fatemeh Jalali was selected as one of the Australia's Most Innovative Engineers 2018 by Engineers Australia for proposing the DEFT architecture:

[2] IBM Science Accomplishment 2018

[3] IBM Outstanding Technical Achievement Award (OTAA) 2019