Invited Paper: Edge and Fog Computing: Vision and Research Challenges

Abstract

Recently, the wide adoption of Internet of Things (IoT) devices has introduced new challenges that the current cloud-centric approach must overcome. The high-latency obtained from sending daily massive volumes of generated data to the cloud, for further processing, is insufficient to meet the stringent requirements of emerging IoT applications. As a consequence, researchers have introduced new paradigms, like edge and fog computing, with the purpose of extending cloud capabilities closer to the edge of the network. This extension of the cloud enables IoT applications to be deployed in the proximity of sensors, adding new benefits like fast response time and better security and privacy. In this paper, we discuss in detail both paradigms based on their individual characteristics and use cases. Furthermore, we explain what future challenges, i.e., resource management, security and privacy, and network management, researches must solve to enable the adoption in society. Finally, we present our vision regarding a smart city scenario in which users have the possibility of customizing their environment as they desire, by seamlessly downloading applications on a personal edge network.