Autonomous Resource Management in Construction Companies Using Deep Reinforcement Learning Based on IoT

Resource allocation is one of the most critical issues in planning construction projects, due to its di- rect impact on cost, time, and quality. There are usually specific allocation methods for autonomous resource management according to the project’s objectives. However, integrated planning and opti- mization of utilizing resources in an entire construction organization are scarce. The purpose of this study is to present an automatic resource allocation structure for construction companies based on Deep Reinforcement Learning (DRL), which can be used in various situations. In this structure, Data Harvesting (DH) gathers resource information from the distributed Internet of Things (IoT) sensor devices all over the company’s projects to be employed in the autonomous resource management approach. Then, Coverage Resources Allocation (CRA) is compared to the information obtained from DH in which the Autonomous Resource Management (ARM) determines the project of interest. Like-wise, Double Deep Q-Networks (DDQNs) with similar models are trained on two distinct assignment situationsbasedonstructuredresourceinformationofthecompanytobalanceobjectiveswithresourceconstraints.Thesuggestedtechniqueinthispapercanefficientlyadjusttolargeresourcemanagementsystemsbycombiningportfolioinformationwithadoptedindividualprojectinformation.Also,theeffectsofimportantinformationprocessingparametersonresourceallocationperformanceareana-lyzedindetail.Moreover,theresultsofthegeneralizabilityofmanagementapproachesarepresented,indicatingnoneedforadditionaltrainingwhenthevariablesofsituationschange.