Visible to the public Hosting distributed databases on internet of things-scale devices

TitleHosting distributed databases on internet of things-scale devices
Publication TypeConference Paper
Year of Publication2017
AuthorsRichardson, D. P., Lin, A. C., Pecarina, J. M.
Conference Name2017 IEEE Conference on Dependable and Secure Computing
Keywordsbenchmarks, Cassandra distributed database, computation power, decentralized architecture, Distributed databases, distributed device deployment, Hardware, human factors, interconnected devices, Internet of Things, Internet of Things-scale devices, IoT nodes, IoT representative devices, IoT-representative device specifications, Metrics, mobile computing, network compression, node configuration, performance evaluation, Pervasive computing, Pervasive Computing Security, physical devices, processing workload, pubcrawl, racked servers, Random access memory, Raspberry Pi, Resiliency, Scalability, security, sensor nets, storage, system resiliency, Testing, virtual machines, Virtual machining
Abstract

The Internet of Things (IoT) era envisions billions of interconnected devices capable of providing new interactions between the physical and digital worlds, offering new range of content and services. At the fundamental level, IoT nodes are physical devices that exist in the real world, consisting of networking, sensor, and processing components. Some application examples include mobile and pervasive computing or sensor nets, and require distributed device deployment that feed information into databases for exploitation. While the data can be centralized, there are advantages, such as system resiliency and security to adopting a decentralized architecture that pushes the computation and storage to the network edge and onto IoT devices. However, these devices tend to be much more limited in computation power than traditional racked servers. This research explores using the Cassandra distributed database on IoT-representative device specifications. Experiments conducted on both virtual machines and Raspberry Pi's to simulate IoT devices, examined latency issues with network compression, processing workloads, and various memory and node configurations in laboratory settings. We demonstrate that distributed databases are feasible on Raspberry Pi's as IoT representative devices and show findings that may help in application design.

DOI10.1109/DESEC.2017.8073855
Citation Keyrichardson_hosting_2017