Intelligent Decision Support System Based on Multi-Agent Interaction Models by The Example of The Oil and Gas Industry

This study develops an intelligent decision support tool for managing complex production systems using the example of a field development system. The problem solved in the study lies in the limitations of existing tools for generating optimal and realistic scenarios for managing production systems due to the lack of consideration of local knowledge and target functions of individual production sites. The relevance of the work lies in the need to improve the quality of management decisions in complex production systems through decision support systems that consider the multi-agent nature of the interaction of system elements, considering the multiplicity of target functions and incomplete awareness of individual agents. The result of the work is the developed multi-agent field development system, consisting of an environment presented as a set of computational models and intelligent agents that control production elements at different levels of the hierarchy. A hierarchical MAS with region–field–bush–crew agents was built using BDI and integrated with a Python-based simulation model. The effectiveness of the developed solution is verified by comparing the predicted oil flow rates for alternative optimization algorithms. Optimization of the distribution of teams across the region’s fields and the schedules of GTO and drilling using the MAS has increased the region’s production rate by 4.5%, ensured the feasibility of field plans, and reduced the costs of well logging and drilling. The testing results demonstrate the effectiveness of using multi-agent systems to generate field development scenarios.

Complex technical and socio-economic systems; Intelligent decision support system; Multi-agent interaction; Oil and gas industry; Simulation modeling

Ahmadi, S. E., Sadeghi, D., Marzband, M., Abusorrah, A., & Sedraoui, K. (2022). Decentralized bi-level stochastic optimization approach for multiagent multi-energy networked micro-grids with multi-energy storage technologies. Energy, 245, 123223. https://doi.org/10.1016/j.energy.2022.123223

Boissier, O., Bordini, R., Hübner, J., Ricci, A., & Santi, A. (2013). Multi-agent oriented programming with JaCaMo. Science of Computer Programming, 78. https://doi.org/10.1016/j.scico.2011.10.004

Boissier, O., Bordini, R. H., Hübner, J., & Ricci, A. (2020). Multi-agent oriented programming: Programming multi-agent systems using JaCaMo. MIT Press.

Bolsunovskaya, M. V., Gintciak, A. M., Fedyaevskaya, D., Petryaeva, A., & Burlutskaya, Z. V. (2023). Complex modeling of the oil production processes: Analytical review. Automation and Informatization of the Fuel and Energy Complex, 51–62. https://doi.org/10.33285/2782-604X-2023-2(595)-51-62

Caillou, P., Gaudou, B., Grignard, A., Truong, C. Q., & Taillandier, P. (2017). A simple-to-use BDI architecture for agent-based modeling and simulation. In Advances in Social Simulation 2015 (pp. 15–28). Springer. https://doi.org/10.1007/978-3-319-47253-9_2

Chen, H.-Q., Tan, A.-H., & Ng, G.-W. (2007). Integrated cognitive architectures: A survey. Artificial Intelligence Review, 28, 103–130. https://doi.org/10.1007/s10462-009-9094-9

Chernyshev, S. A. (2023). Problems of multi-agent systems and possible ways to solve them. Vestnik of Russian New University. Series: Complex Systems: Models, Analysis, Management, (3), 231–241. https://doi.org/10.18137/RNU.V9187.23.03.P.231

Fedyaevskaya, D. E., Burlutskaya, Z. V., Gintciak, A. M., & Dixit, S. (2023). Hierarchical cybernetic model of oil production enterprise with distributed decision-making centers. In Digital Transformation: What Is the Company of Today? (pp. 21–34). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-46594-9_2

Ferrigno, E., Rodriguez, M., & Davidsson, E. (2024). Revolutionizing drilling operations: Next-gen LLM-AI for real-time support in well construction control rooms. SPE Annual Technical Conference and Exhibition. https://doi.org/10.2118/220798-MS

Gorodetsky, V. I., Kozhevnikov, S. S., Novichkov, D., & Skobelev, P. O. (2019). The framework for designing autonomous cyber-physical multi-agent systems for adaptive resource management. In International Conference on Industrial Applications of Holonic and Multi-Agent Systems (pp. 52–64). https://doi.org/10.1007/978-3-030-27878-6_5

Kuo, C., Kuruoglu, E. E., & Chan, W. K. V. (2022). Neural network structure optimization by simulated annealing. Entropy, 24(3), 348. https://doi.org/10.3390/e24030348

Lakemond, N., Holmberg, G., & Pettersson, A. (2021). Digital transformation in complex systems. IEEE Transactions on Engineering Management, 71, 192–204. https://doi.org/10.1109/TEM.2021.3118203

Lang, J., & Zhao, J. (2016). Modeling and optimization for oil well production scheduling. Chinese Journal of Chemical Engineering, 24(10), 1423–1430. https://doi.org/10.1016/j.cjche.2016.04.050

Li, W., Wang, S., & Koo, C. (2021). A real-time optimal control strategy for multi-zone VAV air-conditioning systems adopting a multi-agent based distributed optimization method. Applied Energy, 287, 116605. https://doi.org/10.1016/j.apenergy.2021.116605

Liu, H., Ren, Y., Li, X., Deng, Y., Wang, Y., Cao, Q., Du, J., Lin, Z., & Wang, W. (2024). Research status and application of artificial intelligence large models in the oil and gas industry. Petroleum Exploration and Development, 51, 1049–1065. https://doi.org/10.1016/S1876-3804(24)60524-0

Novikov, D. (2013). Theory of control in organizations. Nova Science Publishers.

Oroojlooy, A., & Hajinezhad, D. (2019). A review of cooperative multi-agent deep reinforcement learning. arXiv preprint. https://doi.org/10.48550/arXiv.1908.03963

Perko, I., Espejo, R., Lepskiy, V., & Novikov, D. A. (2022). World Organization of Systems and Cybernetics 18th Congress (WOSC2021) (Vol. 495). Springer. https://doi.org/10.1007/978-3-031-08195-8

Pospelov, K. N., Burlutskaya, Z. V., Gintciak, A. M., & Troshchenko, K. D. (2023). Multi-parametric optimization of complex system management scenarios based on simulation models. International Journal of Technology, 14(8), 1748–1758. https://doi.org/10.14716/ijtech.v14i8.6832

Pospelov, K. N., Vatamaniuk, I. V., Lundaeva, K. A., & Gintciak, A. M. (2023). Heuristic approach to planning complex multi-stage production systems. International Journal of Technology, 14(8), 1790–1799. https://doi.org/10.14716/ijtech.v14i8.6833

Reddicharla, N., & Mayada, S. A. (2024). Innovating oil and gas field operations: Harnessing the power of generative AI for supporting workforce towards achieving autonomous operations. ADIPEC Conference. https://doi.org/10.2118/222046-MS

Saboo, S., & Shekhawat, D. (2024). Enhancing predictive maintenance in an oil and gas refinery using IoT, AI and ML: A generative AI solution. International Petroleum Technology Conference. https://doi.org/10.2523/IPTC-23466-MS

Seidita, V., Lanza, F., Sabella, A. M. P., & Chella, A. (2022). Can agents talk about what they are doing? A proposal with Jason and speech acts. Workshop on Agents and Objects (WOA), 17–29.

Sharko, P. A., Burlutskaya, Z. V., Gintciak, A. M., Beketov, S. M., & Lundaeva, K. A. (2025). The influence of communication strategies of intelligent agents in production systems on the shift of sustainable solutions. Sustainability, 17(24), 11130. https://doi.org/10.3390/su172411130

Sharko, P. A., Burlutskaya, Z. V., Zubkova, D. A., Gintciak, A. M., & Pospelov, K. N. (2025). AI-supported decision making in multi-agent production systems using the example of the oil and gas industry. Applied Sciences, 15(10), 5366. https://doi.org/10.3390/app15105366

Shen, R., Zhang, S., Wen, X., An, Q., Zheng, R., Li, Y., & Zhao, J. (2022). Multi-agent deep reinforcement learning optimization framework for building energy system with renewable energy. Applied Energy, 312, 118724. https://doi.org/10.1016/j.apenergy.2022.118724

Shvetcov, A. N., Dianov, S. V., & Dianov, D. S. (2022). Designing a multi-agent system for resolving interfunctional conflicts in an enterprise. Cherepovets State University Bulletin, 1(106), 74–89. https://doi.org/10.23859/1994-0637-2022-1-106-6

White, B. (2015). Managing complexity by George Rzevski and Petr Skobelev. Informatics, 49–50. https://doi.org/10.1002/inst.12050

Wooldridge, M. J. (2009). An introduction to multiagent systems. John Wiley & Sons.

Yu, V., Susanto, H., Jodiawan, P., Ho, T., Lin, S., & Huang, Y. (2022). A simulated annealing algorithm for the vehicle routing problem with parcel lockers. IEEE Access, 10, 20764–20782. https://doi.org/10.1109/ACCESS.2022.3152062

Yu, Z., Yu, S., Jiang, H., & Mei, X. (2021). Distributed fixed-time optimization for multi-agent systems over a directed network. Nonlinear Dynamics, 103, 775–789. https://doi.org/10.1007/s11071-020-06116-1