Postgraduate research student, School of Electronics
Recently, Multi-access Edge Computing (MEC) has been proposed to offer cloud-computing capabilities and an IT service environment at the edge of the network. Benefits of MEC include the reduction of transmission costs and latency, the improvement of Quality-of-Service (QoS), through the decreased volumes of data that must be moved, the consequent traffic, and the distance the data must travel.
It is challenging to build an MEC system. Sometimes Edge computing nodes are resource-constrained devices such as wireless routers or small cells. How to take advantage of Edge computing nodes with limited hardware resources is an important problem to solve.
We have designed a framework to manage the life cycle of Edge applications through sharing hardware resources among multiple applications in Edge computing nodes. The framework enables partial computation offloading from the Cloud to the Edge, through a context-aware decision making mechanism to select the optimal deployment plan. Once applications are offloaded into Edge computing nodes, the framework prioritises the applications and dynamically allocates hardware resource to them based on their QoSs.
Our resource management framework is lightweight and can effectively improve the QoS of applications by utilising Edge computing. This was verified through deploying a location-based mobile application and a real-time face detection application in a Device-Edge-Cloud test-bed. Our research will contribute to the design of MEC systems and facilitating techniques for managing Edge computing services applicable to increasingly data-intensive mobile networks.
If you would like to learn more about how your University can participate in a future Mobile World Scholar Challenge, send us a message at [email protected]. Please include your name, title and university in the email.