Comparative analyses of intelligent scheduling optimization algorithms for the control schemes of water injection pumps on offshore crude oil production platform

Yuhang Yang, Ruijie Zhao, Desheng Zhang and Xikun Wang

Energy, 2025, vol. 328, issue C

Abstract: To address the inefficiency of long-term operation of water injection pumps on the offshore crude oil production platform and to achieve energy savings and emission reductions, this study conducts a comparative analysis of two types of optimization algorithms for optimizing the pump scheduling schemes of the water injection piping networks. One is genetic algorithm (GA), which is a heuristic algorithm, and the other is deep Q-network (DQN) algorithm, which is an artificial intelligent algorithm. Through computational analysis, both algorithms exhibit strong robustness. When disregarding the differences in motor energy efficiency, compared to manual control method, GA demonstrates an average energy-saving rate of 7.08 %, while DQN algorithm achieves 5.96 %. Both algorithms significantly enhance the stability of water injection piping networks. Although a few negative optimizations are found in the DQN algorithm, the optimized solutions are still at the boundary of the feasible domain and has no obvious effect on the stability of the system. DQN algorithm can quickly generate viable solutions regardless of problem size, the time taken is significantly less than that of the GA.

Keywords: Optimization; Reinforcement learning; Genetic algorithm; Pump scheduling; Energy efficiency (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225022625
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:328:y:2025:i:c:s0360544225022625

DOI: 10.1016/j.energy.2025.136620

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().