Call for Papers

Edge–cloud collaboration has become a popular framework to enable the solving of resource-intensive tasks with a set of distributed deployed edge devices that collaboratively work with the cloud to achieve low-latency and high efficiency. It envisions a wide range of applications in Internet of Things (IoT), Vehicle-to-Everything (V2X) Networks, Crowd Sourcing, Unmanned Aerial Vehicles (UAV) systems, etc. There is an emerging trend to train and deploy collaborative artificial intelligence (AI) model with the edge–cloud paradigm, which integrates the edges’ cognition to develop far superior intelligence through goal-driven strategic interactions among the collaborating edges and the cloud. It is critical to develop advanced edge–cloud computing mechanisms to enable collaborative AI to confront challenges like device heterogeneity, resource constraints, energy efficiency, communication costs, data privacy, scalability, model accuracy and robustness, etc.

This Special Issue brings together leading research experts from industry and academia to present their novel and original contributions on utilizing edge-cloud computing technology to enable collaborative AI.

The topics of interest for this special issue include, but are not limited to:

• Novel design of machine learning approaches for edge-cloud systems and applications.
• Collaborative AI for optimizing wireless edge-cloud communication systems.
• Collaborative AI for distributed resource management, including cloud resources, edge resources, energy resources, computing resources, and communication infrastructure, etc.
• Collaborative AI and its applications in 5G-and-beyond, Internet of Things (IoT), Vehicle-to-Everything (V2X) Networks, Crowd Sourcing, Unmanned Aerial Vehicles (UAV) systems, etc.
• Cloud AI for training and accelerating large-scale AI models for the areas of Graph, CV, NLP, and web services.
• Edge intelligence in dealing with the bandwidth, privacy or compute-transmission balance.
• Distributed machine learning mechanisms such as federated edge learning for data privacy and device heterogeneity.
• Collaborative AI for smart home, smartphone and mobile applications.
• Deep learning and machine learning for mobile systems and networking.

Submission Guidelines

Prospective authors should submit their manuscripts following the IEEE OJCOMS guidelines. Authors should submit a manuscript trough Manuscript Central.

Important Dates

Manuscript Submission Deadline: 30 June 2023
Publication Date: Third Quarter 2023

Lead Guest Editor

Wenzhong Li, Nanjing University, China

Guest Editors

Luigi Iannone, Huawei Technologies France, France
Yipeng Zhou, Macquarie University, Australia
Xin Wang, Stony Brook University, New York, USA
Xiaoming Fu, Georg-August-University of Goettingen, Germany