Computation Offloading
Computation offloading optimizes resource utilization by transferring computationally intensive tasks from resource-constrained devices (e.g., mobile phones, IoT devices, UAVs) to more powerful servers (e.g., edge servers, cloud servers). Current research focuses on developing efficient algorithms, often employing deep reinforcement learning (DRL), graph neural networks (GNNs), and other machine learning techniques, to dynamically allocate resources and make optimal offloading decisions while considering factors like latency, energy consumption, and security. This field is crucial for enabling the deployment of demanding applications like AI inference, augmented reality, and the metaverse on resource-limited devices, impacting various sectors including smart mobility, healthcare, and industrial automation.
Papers
Hybrid Learning for Orchestrating Deep Learning Inference in Multi-user Edge-cloud Networks
Sina Shahhosseini, Tianyi Hu, Dongjoo Seo, Anil Kanduri, Bryan Donyanavard, Amir M. Rahmani, Nikil Dutt
Online Learning for Orchestration of Inference in Multi-User End-Edge-Cloud Networks
Sina Shahhosseini, Dongjoo Seo, Anil Kanduri, Tianyi Hu, Sung-soo Lim, Bryan Donyanavard, Amir M. Rahmani, Nikil Dutt