Research on the Design Optimization Algorithm of Intelligent Production Allocation System in Gas Field Development

Panpan Han

doi:10.6911/

Authors

Panpan Han Daqing Oilfield Gas Production Company, Daqing, China

DOI:

https://doi.org/10.6911/

Keywords:

Intelligent production allocation; deep reinforcement learning; deep Q network; gas field development; optimization algorithm; production scheduling.

Abstract

A new algorithm based on DRL is proposed. It aims at optimizing gas field resource allocation and production scheduling by DQN. Through interaction with environment, the algorithm learns optimization strategy, automatically adjusts decision based on reward mechanism so as to improve system adaptability and self-optimization. Firstly, a mathematical model is set up to deal with production allocation problems in gas field development. The objective functions and constraints of resource allocation are clarified. After that, a deep reinforcement learning optimization algorithm was designed to solve the problem, and the DQN was used as the training method. Experimental results show that compared with traditional optimization algorithms, this algorithm has significant improvement on resource utilization and production efficiency, and improves production scheduling efficiency by 18%. It is shown that deep reinforcement learning is able to deal with complex resource scheduling problems effectively, provide technical support for intelligent production scheduling in gas field and provide new thinking for related research.

Downloads

Download data is not yet available.

References

[1] Xu, F., Yan, X., Lin, Z., Li, S., Xiong, X., Yan, D., ... & Mei, Y. (2022). Research progress and development direction of key technologies for efficient development of coalbed methane in China. Coalfield Geology and Exploration, 50, 1–14.

[2] Feng, X., Peng, X., Li, L., Mei, Q., Zhao, Z., Li, Y., ... & Qi, T. (2023). Application prospects of artificial intelligence technology in gas reservoir engineering. Natural Gas Exploration and Development, 46, 65–76.

[3] He, C., Zhao, Y., Li, N., Yang, J., Cao, H., & Tang, R. (2025). Intelligent production adjustment and early warning of shale gas wells based on fuzzy logic control. Oil and Gas Reservoir Evaluation and Development, 15, 152–160.

[4] Sun, Y., Zheng, H., & Kong, H. (2022). Research and prospect of key technologies for coal-to-electricity transformation under carbon neutrality. Journal of Power Engineering, 42, 1013–1023.

[5] Dong, S., Zeng, L., Che, X., Du, X., Xu, H., Ji, C., ... & Li, Z. (2023). Application of artificial intelligence in fracture logging identification of tight reservoirs. Earth Science, 48, 2443–2461.

[6] Gao, L., & Cao, J. (2021). Research progress on two difficult problems in pipeline leak detection. Science Technology and Engineering, 21, 13203–13210.

[7] Li, T. (2023). Research and application of overseas oil and gas effective production decision model. Journal of Engineering Science, 45, 1771–1781.

[8] Pan, C., Li, Y., Li, N., Li, T., Jin, T., & Qin, J. (2021). A review and bibliometric analysis of thermal runaway of lithium-ion batteries. Science, Technology and Engineering, 21, 10099–10107.

[9] Bai, X., Mi, J., Wang, X., Zhang, G., Qiao, Y., Xu, S., & Zhang, M. (2022). Research progress of pull-out piles in anti-floating engineering. Science, Technology and Engineering, 22, 6781–6789.

[10] Kang, Q., Wu, H., Zhang, R., Fan, D., Li, X., Wang, W., & Gong, J. (2021). Development of process simulation software for gathering and transportation pipeline network for intelligent oilfields. Oil and Gas Storage and Transportation, 40, 277–286.

[11] Zhao, Q., Tan, H., Wang, X., & Teng, K. (2021). Research progress of EEG acquisition electrodes. Science, Technology and Engineering, 21, 6097–6104.

[12] He, D., Jia, C., Zhao, W., Xu, F., Luo, X., Liu, W., ... & Zheng, N. (2023). Research progress and key issues in ultra-deep oil and gas exploration in China. Petroleum Exploration and Development, 50, 1162–1172.

[13] Liu, H., Xu, Q., & Ye, S. (2022). Research progress on continuous estimation method of heat transfer factor of calorimetric reactor. Science Technology and Engineering, 22, 10355–10368.