AI-Based Dynamic Resource Allocation in Construction Projects: A Reinforcement Learning Approach to Time–Cost–Resource Optimization

Mohammad Elahi

Authors

Mohammad Elahi M.Sc., Department of Civil Engineering, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran https://orcid.org/0009-0008-4954-1445

Keywords:

artificial intelligence, reinforcement learning, Proximal Policy Optimization, construction project management, resource allocation, time–cost optimization, project scheduling

Abstract

This study aimed to develop and evaluate an artificial intelligence–based dynamic resource-allocation framework using reinforcement learning to simultaneously optimize project duration, cost performance, and resource utilization in construction projects. A quantitative computational study was conducted using data from 84 medium- and large-scale construction projects in Tehran, Iran, together with validation input from 168 construction professionals. Project-level data included activity schedules, labor and equipment allocation, progress, costs, resource conflicts, idle time, and operational constraints. A Proximal Policy Optimization reinforcement learning model was developed to dynamically allocate resources at weekly decision intervals. The model state incorporated schedule, cost, activity, and resource indicators, while the reward function jointly represented time, cost, and resource-efficiency objectives. Projects were divided at the project level into training, validation, and independent test subsets. Model performance was compared with historical managerial allocation and a conventional rule-based scheduling strategy. Robustness, sensitivity, and expert-validation analyses were also conducted. PPO-based allocation significantly reduced project completion time compared with historical allocation (mean difference = -2.68 months, 95% CI [-3.26, -2.10], p < .001, d = 1.02) and rule-based allocation (-1.13 months, 95% CI [-1.48, -0.78], p < .001, d = 0.71). Schedule deviation was significantly reduced by 7.69 percentage points relative to historical allocation (p < .001, d = 1.56) and by 3.25 percentage points relative to rule-based allocation (p < .001, d = 0.98). Cost deviation decreased by 5.83 and 2.42 percentage points, respectively (both p < .001). Labor utilization significantly increased by 12.94 percentage points versus historical allocation (p < .001, d = 1.91) and 6.22 percentage points versus rule-based allocation (p < .001, d = 1.28), while equipment utilization also improved significantly. Resource conflicts were significantly lower under PPO than both comparison strategies (both p < .001). Reinforcement learning provided a feasible, robust, and statistically superior approach to dynamic construction resource allocation, enabling simultaneous improvements in schedule performance, cost control, and resource utilization.

References

Bahroun, Z., Tanash, M., As’ad, R., & Alnajar, M. (2023). Artificial Intelligence Applications in Project Scheduling: A Systematic Review, Bibliometric Analysis, and Prospects for Future Research. Management Systems in Production Engineering, 31(2), 144-161. https://doi.org/10.2478/mspe-2023-0017

Chen, X., & Chen, L. (2024). Exploration of Adaptive Environment Design Strategy Based on Reinforcement Learning in CAD Environment. Computer-Aided Design and Applications, 175-190. https://doi.org/10.14733/cadaps.2024.s23.175-190

Dai, W., Zan, J., Zhang, P., Hu, D., Fang, R., & Dong, Y. (2026). Cell-Free UAV Real-Time Sensing for Enhanced Substation Operation: Network Construction and Resource Management. Journal of Physics Conference Series, 3212(1), 012006. https://doi.org/10.1088/1742-6596/3212/1/012006

Fawzy, M., Elshaer, R., Chuddher, B. A., & Algohary, G. (2026). Solving the Multi-Skill Resource-Constrained Project Scheduling Problem Considering Skill Depth and Breadth Using ACO Algorithm and LINGO. Algorithms, 19(9), 738. https://doi.org/10.3390/a19090738

Gao, Z., Liu, S., Shi, G., Sun, Y., Ge, X., & Wang, Y. (2026). A Collaborative Scheduling Approach for Sheet Metal Workshops in Printing Equipment Ovens Based on Graph Attention Reinforcement Learning. Symmetry, 18(8), 1298. https://doi.org/10.3390/sym18081298

Guo, R. (2024). Research and Application of Deep Learning Technology in Prefabricated Buildings. Journal of World Architecture, 8(2), 134-139. https://doi.org/10.26689/jwa.v8i2.6920

Huang, Q., & Bai, Y. (2023). Application of Improved Artificial Immune System Algorithm Based on Applied Mathematics for Optimization of Manpower Allocation in Construction Engineering. Processes, 11(7), 1870. https://doi.org/10.3390/pr11071870

Khan, I. U., Saleem, M. A., & Hussain, F. (2024). A Comparative Analysis of Different Vehicular Fog Computing Scheduling Algorithms. Journal of Independent Studies and Research - Computing, 22(1). https://doi.org/10.31645/jisrc.24.22.1.9

Li, B., Yang, C., & Yang, Z. (2023). Multiple Container Terminal Berth Allocation and Joint Operation Based on Dueling Double Deep Q-Network. Journal of Marine Science and Engineering, 11(12), 2240. https://doi.org/10.3390/jmse11122240

Li, B., & Zhang, Z. (2026). A Multiagent Reinforcement Learning–based Approach for Construction Resource Scheduling and Cost Control in Intelligent Construction Sites. 39. https://doi.org/10.1117/12.3118711

Li, Y., Niu, X., Li, P., H, L., Dong, R., Li, N., & Tan, Z. (2026). Multi-Agent Deep Reinforcement Learning for Dynamic Cost Overrun Mitigation in Smart Grid Construction Projects. Energies, 19(13), 3147. https://doi.org/10.3390/en19133147

Liang, H., Yang, Z., Zhang, G., & Hou, H. (2024). Resource Allocation for Space-Air-Ground Integrated Networks: A Comprehensive Review. Journal of Communications and Information Networks, 9(1), 1-23. https://doi.org/10.23919/jcin.2024.10494938

Liu, H., Zhou, H., Chen, H., Yan, Y., Huang, J., Xiong, A., Yang, S., Chen, J., & Guo, S. (2023). A Federated Learning Multi-Task Scheduling Mechanism Based on Trusted Computing Sandbox. Sensors, 23(4), 2093. https://doi.org/10.3390/s23042093

Lou, H. P., Shen, X., & Xu, J. (2025). Multi-Team Agile Software Project Scheduling Using Dual-Indicator Group Learning Particle Swarm Optimization. Symmetry, 17(8), 1267. https://doi.org/10.3390/sym17081267

Luo, J. (2025). MADRL-Based Intelligent Resource Allocation for Green Sports Events. International Journal of Decision Support System Technology, 17(1), 1-23. https://doi.org/10.4018/ijdsst.393787

Mirjalili, R. (2025). Resource-Based Time and Cost Prediction in Project Networks: From Statistical Modeling to Graph Neural Networks. https://doi.org/10.48550/arxiv.2511.15003

Olaya, S., Tibaná, C., Sánchez, O., Castañeda, K., & Torres, K. (2026). Human Resource Planning for Building Construction Processes Through the Integration of BIM and Line of Balance. Buildings, 16(10), 1919. https://doi.org/10.3390/buildings16101919

Sun, Y. (2025). A Complex Project Management Method Optimized by Ant Colony Algorithm. Engineering Research Express, 7(4), 045293. https://doi.org/10.1088/2631-8695/ae1ddd

Verma, P., Maurya, A. K., & Yadav, R. S. (2023). A Survey on Energy‐efficient Workflow Scheduling Algorithms in Cloud Computing. Software Practice and Experience, 54(5), 637-682. https://doi.org/10.1002/spe.3292

Wang, L., Liu, H., Xia, M., Wang, Y., & Li, M. (2023). Research on a Multilevel Scheduling Model for Multi Variety and Variable Batch Production Environments Based on Machine Learning. Frontiers in Energy Research, 11. https://doi.org/10.3389/fenrg.2023.1251335

Wang, L., Zhao, Y., & Yin, X. (2023). Precast Production Scheduling in Off-Site Construction: Mainstream Contents and Optimization Perspective. Journal of Cleaner Production, 405, 137054. https://doi.org/10.1016/j.jclepro.2023.137054

Wang, M., Guo, H., Liu, C., Shabaz, M., Aldawsari, H., & Qiao, S. (2026). A Hierarchical and Entropy‐Adaptive Reinforcement Learning Framework for Multi‐Task Offloading in Vehicular Ad Hoc Networks. Transactions on Emerging Telecommunications Technologies, 37(6). https://doi.org/10.1002/ett.70454

Xu, G., & Guo, T. (2025). Advances in AI-powered Civil Engineering Throughout the Entire Lifecycle. Advances in Structural Engineering, 28(9), 1515-1541. https://doi.org/10.1177/13694332241307721

Yang, J., & Wu, Y. (2023). Dynamic Resource Allocation Strategy of Multi-Objective Fuzzy Optimization Based on Markov Decision Process. IEEE Access, 11, 99607-99613. https://doi.org/10.1109/access.2023.3314657

Yang, T. (2026). Intelligent Scheduling and Optimization Decision Model of Elderly Service Resources Based on Reinforcement Learning. 25. https://doi.org/10.1117/12.3108077

Yao, Y. (2026). Deep Learning‐Based Intelligent Resource Management for Renewable Energy Engineering Projects. Annals of the New York Academy of Sciences, 1563(1). https://doi.org/10.1111/nyas.70353

Zeng, J., Cheng, Y., Lu, C., Wang, Z., Liu, X., Wang, X., & Song, D. (2026). A Hybrid Reverse Learning Particle Swarm Optimization Method for Aircraft Maintenance Scheduling Based on the Resource-Constrained Project Scheduling Problem Model. Machines, 14(6), 622. https://doi.org/10.3390/machines14060622

Zhang, J., Wang, T., & Cheng, L. (2023). Time-Sensitive and Resource-Aware Concurrent Workflow Scheduling for Edge Computing Platforms Based on Deep Reinforcement Learning. Applied Sciences, 13(19), 10689. https://doi.org/10.3390/app131910689

Zhang, L., Fang, M., Yuan, K., Cheng, S., & Bai, L. (2025). Bridging Project Management and Supply Chain Management via Optimization Method: Scenarios, Technologies, and Future Opportunities. Mathematics, 13(21), 3490. https://doi.org/10.3390/math13213490

Zhang, N., Yang, G., Su, B., & Song, W. (2024). Transfer Learning Method From Parameter Scene to Physical Scene Based on Self-Game Theory. Electronics, 13(7), 1327. https://doi.org/10.3390/electronics13071327

Zhang, Y. (2025). Development of an Integrated Intelligent BIM-based Model for Multi-Objective Optimization in Engineering Assembly Processes. PLoS One, 20(11), e0333354. https://doi.org/10.1371/journal.pone.0333354

Zhasmukhambetova, A., Evdorides, H., & Davies, R. J. (2025). Integrating Risk Assessment and Scheduling in Highway Construction: A Systematic Review of Techniques, Challenges, and Hybrid Methodologies. Future Transportation, 5(3), 85. https://doi.org/10.3390/futuretransp5030085

Zhou, X., Liang, W., Yan, K., Li, W., Wang, K. I., Ma, J., & Jin, Q. (2023). Edge-Enabled Two-Stage Scheduling Based on Deep Reinforcement Learning for Internet of Everything. Ieee Internet of Things Journal, 10(4), 3295-3304. https://doi.org/10.1109/jiot.2022.3179231