Multi-stage stochastic programming for integrated optimization of ethylene production processes and utility systems under uncertainty

Liang Zhao, Jiyun Rong, Guofu Ma, Chen Liang and Jian Long

Energy, 2025, vol. 320, issue C

Abstract: Multiple time-scale uncertainties in equipment efficiency, process demand, and steam prices pose significant challenges to the modeling and optimization of ethylene production processes and utility systems. This paper introduces a novel multi-stage stochastic programming (MSSP) framework that integrates advanced linearization techniques and data augmentation via a Wasserstein generative adversarial network (WGAN), providing a robust solution for improving energy conversion efficiency and optimizing ethylene production processes with utility systems under uncertainty. A three-stage stochastic programming model addresses the impacts of uncertainties across different time scales. Nonlinear terms in the model are linearized using the McCormick envelope method to simplify the solution process, and a WGAN generates simulated data to augment the dataset. The effectiveness of the proposed method was validated in a real-world ethylene plant case study, where optimization results showed a 3.9 % increase in net profit, a 3.5 % increase in ethylene yield, and a 6.5 % decrease in the cost of the utility system compared to traditional methods.

Keywords: Integrated optimization; Multi-stage stochastic programming; Uncertainty set; Wasserstein generative adversarial network; 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/S0360544225009375
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:320:y:2025:i:c:s0360544225009375

DOI: 10.1016/j.energy.2025.135295

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 ().