Edge Computing and Networking for Ubiquitous AI

Submission Deadline: 15 May 2020

IEEE Access invites manuscript submissions in the area of Edge Computing and Networking for Ubiquitous AI.

Edge computing has become an important solution to break through the bottleneck of emerging technology development by virtue of its advantages of reducing data transmission, decreasing service latency and easing cloud computing pressure. It can also be applied to extensive application scenarios, such as smart city, manufacturing, logistics and transportation, healthcare, and smart grid. In these scenarios, transmitting massive data and requests generated by edge devices to the cloud data center is no longer the only option, and the edge computing architecture can be complementary to the cloud. Among several application scenarios, such as network optimization, intelligent manufacturing, and real-time video analytics, the combination of Deep Learning (DL) and edge computing shows its advantages.

For example, the DL model trained for face recognition can be deployed on the edge architecture to achieve real-time identity verification. In addition, from predictive maintenance to network and resource management, many researchers are paying attention to “artificial intelligence” plus “edge computing,” aiming to enhance the computing, storage and communication capabilities of edge computing networks through artificial intelligence techniques, especially Deep Reinforcement Learning (DRL). With the increment of smart devices and the diversification needs, the network environment is becoming more complex. Traditional network technologies rely on fixed mathematical models, which are not applicable in a rapidly changing network environment. The emergence of artificial intelligence can effectively solve this problem. When network devices face some complex and fuzzy network information, artificial intelligence technology relies on its powerful learning and reasoning ability to extract valuable information from massive data, and can realize intelligent management.

However, such ubiquitous intelligence potentially enabled by both edge computing and learning still faces a major challenge, i.e., the effective deployment fashion of the learning model on the collaborated “edge-cloud” architecture is still not determined. The deployment of deep learning models should concern the training and inference of them, and the edge computing architecture shall be well devised.

The topics of interest include, but are not limited to:

  • Deep learning applications enabled by edge computing
  • Deep learning and deep reinforcement learning for optimizing edge computing networks
  • Deep learning-based traffic offloading prediction and optimization
  • Distributed and collaborative AI with edge computing and networking
  • Hardware platforms and software stacks for deploying deep learning on the edge
  • Data processing and business intelligence on the edge
  • Offloading scheme for intensive deep learning tasks
  • Architecture and orchestration of deep learning services in edge computing
  • Deep learning for the management of edge computing networks
  • Transfer learning for the preliminary deployment of deep learning models on the edge
  • Training scheme of deep learning model at the edge
  • Federated learning for massive edge devices, edge nodes and the cloud data center
  • Federated learning devised for deep reinforcement learning, i.e., federated reinforcement learning
  • Compression of deep learning models for deploying them on edge devices or edge nodes
  • Segmentation of deep learning models for collaborative intelligence between cloud and the edge
  • “Early exit of inference” of deep learning models for accelerating the edge intelligence
  • Incentive-based training and inference schemes for heterogeneous devices in the edge
  • The fusion of training and inference in the edge computing network
  • New AI-based edge computing and networking testbed and trials

We also highly recommend the submission of multimedia with each article as it significantly increases the visibility, downloads, and citations of articles.

Associate Editor:  Victor Leung, The University of British Columbia, China

Guest Editors:

    1. Xiaofei Wang, Tianjin University, China
    2. Abbas Jamalipour, The University of Sydney, Australia
    3. Xu Chen, Sun Yat-sen University, China
    4. Samia Bouzefrane, Conservatoire National des Arts et Métiers, France


Relevant IEEE Access Special Sections:


  1. Communication and Fog/Edge Computing Towards Intelligent Connected Vehicles (ICVs)
  2. 5G and Beyond Mobile Wireless Communications Enabling Intelligent Mobility
  3. Artificial Intelligence and Cognitive Computing for Communications and Networks

IEEE Access Editor-in-Chief:
  Prof. Derek Abbott, University of Adelaide

Article submission: Contact Associate Editor and submit manuscript to:

For inquiries regarding this Special Section, please contact:  xiaofeiwang@tju.edu.cn.