OPTIMIZATION OF POWER GENERATION SYSTEMS FOR COST EFFICIENCY AND DECARBONIZATION USING ARTIFICIAL INTELLIGENCE METHODS AT PT PERTAMINA EP BUNYU FIELD

Authors

Brando Sitinjak PT. Pertamina EP Bunyu Field, Bunyu Island
Benny Kawira PT. Pertamina EP Bunyu Field, Bunyu Island
Ahmad Rafi Ramadhan PT. Pertamina EP Bunyu Field, Bunyu Island
Gusti Rinaldi Zulkarnain PT. Pertamina EP Bunyu Field, Bunyu Island

DOI:

Keywords:

Generation Optimization, Gas Engine, Energy Efficiency, Decarbonization, Artificial Intelligence.

Abstract

The oil and gas industry faces challenges in improving energy efficiency and reducing carbon emissions amid the global energy transition. PT Pertamina EP Bunyu Field operates a Gas Engine-based power generation system with potential inefficiencies due to low operational load factors. This research aims to optimize power plant operations by reducing the number of operating units and increasing the load factor by up to 80%, in order to reduce fuel consumption and production costs. The methods used include the optimization of PID control parameters using Genetic Algorithms (GA) and Proximal Policy Optimization (PPO) based on Reinforcement Learning (RL). The simulation results show that this optimization can improve the efficiency of the power generation system and reduce gas consumption by up to 40.15 MMSCFD per year, as well as result in a reduction in carbon emissions of 10,881.87 tons of CO₂eq per year. These findings show that the application of optimal control based on artificial intelligence can provide significant benefits in improving efficiency and supporting decarbonization targets in the oil and gas industry.

References

Ahmmed, T., Akhter, I., Karim, S. R., & Ahamed, F. S. (2020). Genetic algorithm based PID parameter optimization. American Journal of Intelligent Systems, 10(1), 8-13.

Darwito, P. A., Widjiantoro, B. L., Pradana, D. O., Prananda, S. A., & Sudrajat, S. W. (2022, October). Development Of PID Based On Genetic Algorithm As A Control Algorithm On A Three-Phase Mini Plant Separator Level Control System. In 2022 IEEE International Conference of Computer Science and Information Technology (ICOSNIKOM) (pp. 01-06). IEEE.

Gochhayat, R. (2014). Pso Based Pi Controller For Load Frequency Control Of Interconnected Power Systems.

IEA (2023). Global Energy Review: CO₂ Emissions in 2023. International Energy Agency.

Kashki, M., Abdel-Magid, Y. L., & Abido, M. A. (2008). A reinforcement learning automata optimization approach for optimum tuning of PID controller in AVR system. In Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence: 4th International Conference on Intelligent Computing, ICIC 2008 Shanghai, China, September 15-18, 2008 Proceedings 4 (pp. 684-692). Springer Berlin Heidelberg.

M. Zahir, A. A., Alhady, S. S. N., Othman, W. A. F. W., & Ahmad, M. F. (2018). Genetic algorithm optimization of PID controller for brushed DC motor. In Intelligent Manufacturing & Mechatronics: Proceedings of Symposium, 29 January 2018, Pekan, Pahang, Malaysia (pp. 427-437). Springer Singapore.

Muduli, R., Jena, D., & Moger, T. (2024). Application of reinforcement learning-based adaptive PID controller for automatic generation control of multi-area power system. IEEE Transactions on Automation Science and Engineering, 22, 1057-1068.

Muhammad, R. D., & Nasrun, K. (2021). Optimal tuning of the PSS-PID controller on the Single Machine Infinite Bus system uses Ant Colony Optimization. Journal of Science and Technology, 10(1).

Regad, M., Helaimi, M., Taleb, R., Gabbar, H. A., & Othman, A. M. (2019, August). Fractional order PID control of hybrid power system with renewable generation using genetic algorithm. In 2019 IEEE 7th International Conference on Smart Energy Grid Engineering (SEGE) (pp. 139-144). IEEE.

Rusydi, M. I. (2016). Optimization of PID Controllers on Autopilot Aircraft Based on Genetic Algorithms. National Journal of Electrical Engineering, 5(2), 217-223.

Wang, L., et al. (2022). Operational Cost Reduction in Gas-Powered Industrial Plants through Load Optimization. Applied Energy, 309, 118374.

Yusuf, A. A. M., Agung, N. J., & Unang, S. (2015, August). Implementation real value genetic algorithm to determine three PID parameter. In 2015 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC) (pp. 198-202). IEEE.

Zhao, X., et al. (2021). Optimization of Gas Engine Efficiency for Industrial Power Generation. Energy Reports, 7, 2114-2128.