You are here

Edge Computing for the Internet-of-Things

Moving data, computation and control into the cloud has been a significant trend in the past decade. However, as the explosion of connected lightweight devices starts the era of the Internet-of-Things (IoT), cloud computing is facing increasing difficulty to meet the data computing and intelligent service demands of IoT devices and applications. Moving the data computation and service supply from the cloud to the edge enables the possibility of meeting application delay requirements, improves the scalability and energy efficiency of lightweight IoT devices, provides contextual information processing, and mitigates the traffic burdens of the backbone network.

Instead of performing data storage and computing in a cluster of clouds, edge computing emphasizes leveraging the power of local computing and using different types of edge devices, such as smartphones, routers and PCs, as edge servers to provide intelligent services. Data storage, computing and control can be separated and intelligently distributed among the connected edge servers and IoT devices. Thus, edge computing can bring many beneficial advantages, such as, highly-improved scalability by remote and intelligent service supply, local computing that makes full use of client computing capabilities and meets the requirements of contextual computing Furthermore, by interacting with the cloud, edge computing can provide more scalable services for delay-tolerant IoT applications. With these common advantages, different edge computing paradigms, such as transparent computing and fog computing, still have different focuses. For example, compared to fog computing focusing on resource allocation in the service level, transparent computing concentrates on logically splitting the software stack (including OS) from the underlying hardware platform to provide cross-platform and streamed services for a variety of devices. The differences enable edge computing to support broader IoT applications with various requirements.

However, to truly realize edge computing in IoT applications, many challenges must be addressed. For example, most IoT devices communicate via wireless and mobile links, leading to the inherent disadvantage of unstable and intermittent data transmission. Moreover, how to efficiently distribute and manage data storage and computing, how to make edge computing collaborate with cloud computing for more scalable services, as well as how to secure the whole system, are significant challenges impeding the development and implementation of edge computing for IoT.

This special issue seeks to address the key challenges such as those mentioned above, and help industry and academia better understand recent advances and potential research directions in leveraging edge computing for IoT. We solicit original and unpublished papers that are not under review by a conference or a journal, in any of, but are not limited to the following topics of interest:

  • New edge computing architectures and implementations for IoT
  • Modeling and performance analysis for edge computing in IoT
  • Wireless communication and networking in edge computing for IoT
  • Resource allocation and energy efficiency in edge computing for IoT
  • QoS and QoE provisioning in edge computing for IoT
  • Trust, security and privacy issues in edge computing for IoT
  • Cross-platform service supply in transparent computing for IoT
  • Streaming execution and cache management in transparent computing for IoT


Dr. Yi Pan
Regents’ Professor
Department of Computer Science
Georgia State University, USA

Dr. Andrzej Goscinski
School of Information Technology
Deakin University, Australia

Dr. Raheem A. Beyah
Motorola Foundation Professor
School of Electrical & Computer Engineering
Georgia Institute of Technology, USA

Dr. Ju Ren (corresponding guest editor)
School of Information Science and Engineering
Central South University, Changsha, China