Home // BUSTECH 2016, The Sixth International Conference on Business Intelligence and Technology // View article
Authors:
Christian Schwarz
Christopher Schmidt
Michael Hopstock
Werner Sinzig
Hasso Plattner
Keywords: in-memory database; enterprise coprocessing; busi- ness data processing; product cost calculation.
Abstract:
Determination of product cost and resource consump- tion during manufacturing, is a crucial scenario for manufac- turing companies. While enterprises have the required data for these calculations already, the computational complexity makes it still hard to build interactive applications that can be used for end-to-end simulation, from procurement to sales. Nevertheless, these applications are required for collaborative product cost simulations that support business experts to make fact-based and data-driven decisions. Within this paper, we present the generic calculation engine that can calculate product cost and other resource based features of thousands of products within the time-frame requirements for interactive applications efficiently. The engine leverages the potential of today’s high-end in-memory databases in combination with the computational power of coprocessors. To solve the problem, we transfer the input drivers and their interdependencies into a system of equations that can be solved by either the coprocessor or a large scale multi- processor system. For our evaluation, we use actual enterprise data of a Fortune 200 company also providing the scenario. We evaluate the approach based on this data, comparing our enterprise application specific problem solution with standard solution techniques of the same domain.
Pages: 12 to 18
Copyright: Copyright (c) IARIA, 2016
Publication date: March 20, 2016
Published in: conference
ISSN: 2308-4391
ISBN: 978-1-61208-467-1
Location: Rome, Italy
Dates: from March 20, 2016 to March 24, 2016