Designing Parallel Computing Using Raspberry Pi Clusters for IoT Servers on Apache Hadoop
Setiya Nugroho, Andi Widiyanto
Universitas Muhammadiyah Magelang
setiya[at]ummgl.ac.id
Abstract
The community has widely used the IoT tool because it makes it easy for users in various sectors. The implementation of IoT does not only require connectivity and devices but also requires a server. Servers that are accessed by many devices will have more and more computing processes on the server. The computing process on the server requires a high-performance but small-sized server device that is easy to connect with other devices. There is a computer with a small size, cheap, and very energy efficient that can be used as an IoT server known as Raspberry Pi. To have high performance, a parallel machine was built based on Raspberry Pi using parallel computing technology. One of the parallel computing tools that are often used today is Apache Hadoop. This research using clusters method with four pieces of Raspberry Pi which is built with parallel computing technology using Apache Hadoop tools. Testing is done using Siege tools. Siege test results with a condition of 100 connections for 5 minutes are Transactions: 10,2072 hits; Elapsed Time: 299.96 secs; Data Transferred: 63.57MB; Response Time: 0.29 secs; Transaction Rate: 340.29 trans / sec; Throughput: 0.21MB / sec; Successful Transactions: 100%.
Keywords: IoT; Parallel Computing; Apache Hadoop;
Topic: Information Engineering