Big Data Analytics from the Rich Cloud to the Frugal Edge

Abstract

Modern systems and applications generate and consume an enormous amount of data from different sources, including mobile edge computing and IoT systems. Our ability to locate and analyze these massive amounts of data will shape the future, building next-generation Big Data Analytics (BDA) and artificial intelligence systems in critical domains. Traditionally, big data materialize in a centralized repository (e.g., the cloud) for running sophisticated analytics using decent computation. Nevertheless, many modern applications and critical domains require low-latency data analysis with the right decision at the right time standard for building trust. With the advent of edge computing, that traditional deployment model shifted closer to the data sources at the network’s edge. Such a shift was motivated by minimized latency, increased uptime, and enhanced efficiencies. This paper studies the BDA building blocks, analyzes the deployment requirements for edge-based BDA QoS, and drafts future trends. It also discusses critical open issues and further research directions for the next step of edge-based BDA.