A Systematic Mapping Study on Edge Computing and Analytics

Abstract

The vast amount of data provided by the Internet of Things and sensors, have given rise to edge computing and analytics. In edge computing and analytics, data processing and analysis on sensor input is performed in edge devices prior to sending the results to the cloud. This reduces required processing in the cloud while minimizing communication network utilization and allows cloud resources to be used for other tasks such as decision making. In this paper, we present a comprehensive, unbiased overview of state-of-the-art research on edge computing and analytics. Of the 47 identified papers, several have targeted task scheduling and power optimisation, while data management and engineering, image and facial recognition as well as anomaly detection were not well studied. Simulation remains the most used approach for validation, and research results based on implementations of edge systems in real life environments are still sparse.