Resource management from the edge to the cloud and efficient simulation of Internet-of-Things (IoT) scenarios for Artificial Intelligence (AI) applications


The integration of intelligent embedded systems or edge Artificial Intelligence (AI) systems in our daily lives has grown significantly in recent years, and it is expected to continue to affect different aspects of our lives with the full deployment of the Internet of Things (IoT). Thus, ensuring the reliability of the decisions becomes essential in all types of applications, while representing a major challenge considering battery-powered wearable technologies. In particular, transferring the complex and energy-consuming computations to fogs (i.e., networks of distributed edge AI devices that cooperatively operate) or to the cloud can significantly reduce the energy consumption of IoT and result in a longer lifetime of these systems with a single battery charge.

In this research line, we aim to explore efficient methodologies to distribute the complex and energy-consuming machine-learning computations between the edge, fog, and cloud, based on the notion of self-awareness that considers the complexity and reliability of the algorithm. We also model and analyze the trade-offs in terms of energy consumption, latency, and performance of different IoT solutions through new simulation frameworks.

We consider in this research line different real-world case studies and applications, ranging from e-Health to smart home devices and smart cities management, to demonstrate the importance of our newly developed methodologies to efficiently use the concepts of edge AI, fog computing, and cloud computing.

Related Publications

Resource-Aware Distributed Epilepsy Monitoring Using Self-Awareness From Edge to Cloud
Forooghifar, Farnaz ; Aminifar, Amir ; Atienza Alonso, David
2019-11-04IEEE Transactions on Biomedical Circuits and SystemsPublication funded by Hasler MyPreHealth (Predicting Episodic Disorders with Health Companions)Publication funded by Human Brain Project  ()Publication funded by DeepHealth H2020 (Deep-Learning and HPC to Boost Biomedical Applications for Health)