Genetic Algorithm–Simulation Framework for Decision Making in Construction Site Layout Planning

Seyedreza RazaviAlavi, Simaan AbouRizk

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)
425 Downloads (Pure)

Abstract

Site layout planning is a complicated task in many construction projects because of the diversity of decision variables, conflicting objectives, and the variety of possible solutions. This paper describes a framework that facilitates decision making on site-layout planning problems. The framework consists of three phases: (1) functionality evaluation phase (FEP), which qualitatively evaluates using a new method; (2) cost evaluation phase (CEP), which quantitatively evaluates the goodness of the layouts using simulation; and (3) value evaluation phase (VEP), which selects the most desirable layout from both qualitative and quantitative aspects. This framework also takes advantage of heuristic optimization through genetic algorithm (GA) to search for the most qualified layouts within FEP. The primary contribution of this research is to introduce a novel method for evaluating quality of layouts, which more realistically model the closeness constraints, and consider size and location desirability in the evaluating function. Also, using simulation for estimating project cost improves the effectiveness of the framework in practice because simulation can model construction processes, uncertainties, resources, and dynamic interactions between various parameters. Applicability of the framework is demonstrated through a case study of the layout planning of a tunneling project.
Original languageEnglish
Article number04016084
JournalJournal of Construction Engineering and Management - ASCE
Volume143
Issue number1
Early online date21 Jul 2016
DOIs
Publication statusPublished - 1 Jan 2017
Externally publishedYes

Fingerprint Dive into the research topics of 'Genetic Algorithm–Simulation Framework for Decision Making in Construction Site Layout Planning'. Together they form a unique fingerprint.

Cite this