Chapter Seven - Resource allocation for distributed production networks

C. K.M. Lee, Shuzhu Zhang, Y. P. Tsang, Jiage Huo

Research output: Chapter in book / Conference proceedingChapter in an edited book (as author)Academic researchpeer-review

Abstract

Efficient resource allocation is important in distributed production networks such that the appropriate resources can be allocated to achieve the target output with the desired quality and value. This chapter explores the machine learning approach for dynamic production resource allocation. With the enormous data collected by the Internet of Things (IoT), the hidden knowledge in resource allocation can be discovered by means of the machine learning algorithm. This is considered to be one of the pioneering research studies in IoT-based smart production systems. Given that the Markovian properties of the production network are defined, the artificial neural network, among computational intelligence techniques, is firstly applied for the production configuration determination. Moreover, a reinforcement learning approach is adopted to further exploit the possible self-aware and self-organized production network. This chapter contributes in modeling the next paradigm shift of the production network by investigating advanced production systems with the IoT and artificial intelligence.

Original languageEnglish
Title of host publicationDigital Manufacturing
Subtitle of host publicationKey Elements of a Digital Factory
PublisherElsevier
Pages247-277
Number of pages31
ISBN (Electronic)9780443138126
ISBN (Print)9780443138133
DOIs
Publication statusE-pub ahead of print - 19 Jan 2024

Keywords

  • Artificial neural network
  • Cyber-physical system
  • Distributed production network
  • Internet of things
  • Reinforcement learning
  • Resource allocation
  • Smart production system

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Chapter Seven - Resource allocation for distributed production networks'. Together they form a unique fingerprint.

Cite this