A learning agent for a multi-agent system for project scheduling in construction

Florian Wenzler, Willibald A. Günthner

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

The quality of the project plan created is essential for realizing a construction project. This is a big challenge for planners, because there are many constraints to be considered. The problem to be solved is known as the multi-mode resource-constrained project scheduling problem (MRCPSP). This paper presents a multi-agent approach in which resources and processes are represented as collaborative agents. Autonomous process and resource agents register themselves on a central blackboard where resource allocation to activities is negotiated. As expansion to prior works, a learning agent is integrated to improve the solutions created. A discrete-event simulation implements the model and it is evaluated with standardized project plans from the field of operations research.

Original languageEnglish
Title of host publicationProceedings - 30th European Conference on Modelling and Simulation, ECMS 2016
EditorsThorsten Claus, Frank Herrmann, Michael Manitz, Oliver Rose
PublisherEuropean Council for Modelling and Simulation
Pages11-17
Number of pages7
ISBN (Electronic)9780993244025
DOIs
StatePublished - 2016
Event30th European Conference on Modelling and Simulation, ECMS 2016 - Regensburg, Germany
Duration: 31 May 20163 Jun 2016

Publication series

NameProceedings - 30th European Conference on Modelling and Simulation, ECMS 2016

Conference

Conference30th European Conference on Modelling and Simulation, ECMS 2016
Country/TerritoryGermany
CityRegensburg
Period31/05/163/06/16

Keywords

  • Discrete event simulation
  • MRCPSP
  • Multi-agent system
  • Project scheduling

Fingerprint

Dive into the research topics of 'A learning agent for a multi-agent system for project scheduling in construction'. Together they form a unique fingerprint.

Cite this