Treffer: TopADDPi: An Affordable and Sustainable Raspberry Pi Cluster for Parallel-Computing Topology Optimization.

Parallel-Computing Topology Optimization (PCTO) has gained importance, especially with the advancement of additive manufacturing (AM), due to its ability to tackle high-dimensional, high-resolution challenges. PCTO is highly relevant to sustainable manufacturing processes and technologies, enabling resource-efficient designs, reduced emissions, and advancements in Industry 4.0 integration. However, PCTO poses difficulties for newcomers or researchers, mainly because of its reliance on non-traditional computing environments and the limited availability of high-performance computing (HPC) resources. Addressing this, the study introduces TopADDPi, a Raspberry Pi-based cluster system, which has been purpose-built to facilitate learning and research in PCTO. It provides detailed instructions for assembling and configuring a Raspberry Pi cluster, with a focus on cost-effectiveness and ease of use. The study thoroughly investigates how different hardware and software configurations affect computing efficiency. In addition, through extensive numerical testing, the performance, energy consumption, and environmental impact of the Raspberry Pi cluster are benchmarked against conventional computing systems. The findings demonstrate the cluster's advantages in handling parallel computing, its indispensable role in debugging, its remarkable energy efficiency, and its significantly reduced carbon footprint compared to conventional systems. These attributes establish the Raspberry Pi cluster as an invaluable tool for both educational and research applications in structural engineering, offering an affordable, sustainable, and indispensable solution for PCTO. [ABSTRACT FROM AUTHOR]

Copyright of Processes is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)