Performance Prediction of a MongoDB-Based Traceability System in Smart Factory Supply Chains.

Yong-Shin Kang,Sekyoung Youm,Il-Ha Park

doi:10.3390/s16122126

Abstract

In the future, with the advent of the smart factory era, manufacturing and logistics processes will become more complex, and the complexity and criticality of traceability will further increase. This research aims at developing a performance assessment method to verify scalability when implementing traceability systems based on key technologies for smart factories, such as Internet of Things (IoT) and BigData. To this end, based on existing research, we analyzed traceability requirements and an event schema for storing traceability data in MongoDB, a document-based Not Only SQL (NoSQL) database. Next, we analyzed the algorithm of the most representative traceability query and defined a query-level performance model, which is composed of response times for the components of the traceability query algorithm. Next, this performance model was solidified as a linear regression model because the response times increase linearly by a benchmark test. Finally, for a case analysis, we applied the performance model to a virtual automobile parts logistics. As a result of the case study, we verified the scalability of a MongoDB-based traceability system and predicted the point when data node servers should be expanded in this case. The traceability system performance assessment method proposed in this research can be used as a decision-making tool for hardware capacity planning during the initial stage of construction of traceability systems and during their operational phase.

Highlights

In order to maintain competitiveness in the future and respond to intensifying competition in the manufacturing industry, advanced manufacturing countries such as the USA and Germany have formed industry–academic cooperatives such as “Advanced Manufacturing Partnership 2.0” [1] and “Industrie 4.0” [2] in an effort to promote the development and application of smart-factory technology.Smart factories are based on information and communication technologies (ICT) and, the Internet of Things (IoT), BigData, artificial intelligence (AI), cyber-physical systems (CPS), and cloud computing [3,4]
We assumed that each participant in the supply chain has their own and their part
Traceability management and stable in complex-process environments are becoming key factors that will enable smart factories to achieve a competitive edge in diverse areas such as optimization, product quality, and error proofing

Summary

Introduction

Smart factories are based on information and communication technologies (ICT) and, the Internet of Things (IoT), BigData, artificial intelligence (AI), cyber-physical systems (CPS), and cloud computing [3,4]. Smart factories will evolve into self-adaptive factories where all things will be interconnected, exchanging information, recognizing and assessing situations, and organically fusing the physical world with the cyber world [5,6,7]. Kanade et al [21] compared the performance between embedded design and linking design when normalized data and denormalized data are stored in MongoDB. It was shown through inquiry experiments that 2nd normal form and 3rd normal form data models provide better performance than an un-normal form and the 1st normal form, and that embedded design has better performance than linking design

Objectives

Results

Conclusion