Applying real options with reinforcement learning to assess commercial CCU deployment
Carbon capture and utilization (CCU), which emerged as a means to reduce anthropogenic carbon emissions, has been highlighted to close the carbon cycle and combat climate change. CCU involves utilizing or converting captured CO2 to create value-added products that can replace or supplement fossil fu...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-11-01
|
Series: | Journal of CO2 Utilization |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S221298202300224X |
_version_ | 1797597998663860224 |
---|---|
author | Jeehwan S. Lee Woopill Chun Kosan Roh Seongmin Heo Jay H. Lee |
author_facet | Jeehwan S. Lee Woopill Chun Kosan Roh Seongmin Heo Jay H. Lee |
author_sort | Jeehwan S. Lee |
collection | DOAJ |
description | Carbon capture and utilization (CCU), which emerged as a means to reduce anthropogenic carbon emissions, has been highlighted to close the carbon cycle and combat climate change. CCU involves utilizing or converting captured CO2 to create value-added products that can replace or supplement fossil fuel-derived products. In order to meet climate goals, commercial-scale CCU facilities need to be built and their capacities increased, but barriers to large-scale CCU deployment still exist, primarily caused by large uncertainties in product/energy prices, markets, technologies, and policies. Conventional techno-economic analysis (TEA) methods cannot appropriately assess viability of CCU deployment projects which include dynamic uncertainties and deployment strategies. More flexible methods that can account for both time-varying uncertainties and dynamic capacity building are needed. We propose a systematic framework for the evaluation of commercial CCU deployment using the theory of real options and reinforcement learning (RL). RL is needed as considering options of adding capacities or delaying/abandoning the project at multiple time points under dynamic uncertainties lead to a large-scale stochastic optimal control problem which cannot be solved using conventional optimization methods like stochastic programming. The framework consists of three steps: surrogate modeling, uncertainty modeling, and assessment modeling. The framework is dependent on the type of CCU technology, uncertainties, real options and RL algorithm. We demonstrate the application of the framework through a case study of CO2 hydrogenation-to-methanol process in Europe, which is a late-stage, i.e., high technology readiness level (TRL), technology. |
first_indexed | 2024-03-11T03:13:12Z |
format | Article |
id | doaj.art-2a1120f778174ee7b9d54de9c947eec0 |
institution | Directory Open Access Journal |
issn | 2212-9839 |
language | English |
last_indexed | 2024-03-11T03:13:12Z |
publishDate | 2023-11-01 |
publisher | Elsevier |
record_format | Article |
series | Journal of CO2 Utilization |
spelling | doaj.art-2a1120f778174ee7b9d54de9c947eec02023-11-18T04:28:41ZengElsevierJournal of CO2 Utilization2212-98392023-11-0177102613Applying real options with reinforcement learning to assess commercial CCU deploymentJeehwan S. Lee0Woopill Chun1Kosan Roh2Seongmin Heo3Jay H. Lee4Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, the Republic of KoreaDepartment of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, the Republic of KoreaDepartment of Chemical Engineering and Applied Chemistry, Chungnam National University, Daejeon 34141, the Republic of KoreaDepartment of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, the Republic of Korea; Corresponding authors.Department of Chemical Engineering & Materials Science, University of Southern California, Los Angeles, CA 90089, USA; Corresponding authors.Carbon capture and utilization (CCU), which emerged as a means to reduce anthropogenic carbon emissions, has been highlighted to close the carbon cycle and combat climate change. CCU involves utilizing or converting captured CO2 to create value-added products that can replace or supplement fossil fuel-derived products. In order to meet climate goals, commercial-scale CCU facilities need to be built and their capacities increased, but barriers to large-scale CCU deployment still exist, primarily caused by large uncertainties in product/energy prices, markets, technologies, and policies. Conventional techno-economic analysis (TEA) methods cannot appropriately assess viability of CCU deployment projects which include dynamic uncertainties and deployment strategies. More flexible methods that can account for both time-varying uncertainties and dynamic capacity building are needed. We propose a systematic framework for the evaluation of commercial CCU deployment using the theory of real options and reinforcement learning (RL). RL is needed as considering options of adding capacities or delaying/abandoning the project at multiple time points under dynamic uncertainties lead to a large-scale stochastic optimal control problem which cannot be solved using conventional optimization methods like stochastic programming. The framework consists of three steps: surrogate modeling, uncertainty modeling, and assessment modeling. The framework is dependent on the type of CCU technology, uncertainties, real options and RL algorithm. We demonstrate the application of the framework through a case study of CO2 hydrogenation-to-methanol process in Europe, which is a late-stage, i.e., high technology readiness level (TRL), technology.http://www.sciencedirect.com/science/article/pii/S221298202300224XCarbon capture and utilizationMulti-period deploymentReal options theoryReinforcement learningDynamic uncertainty |
spellingShingle | Jeehwan S. Lee Woopill Chun Kosan Roh Seongmin Heo Jay H. Lee Applying real options with reinforcement learning to assess commercial CCU deployment Journal of CO2 Utilization Carbon capture and utilization Multi-period deployment Real options theory Reinforcement learning Dynamic uncertainty |
title | Applying real options with reinforcement learning to assess commercial CCU deployment |
title_full | Applying real options with reinforcement learning to assess commercial CCU deployment |
title_fullStr | Applying real options with reinforcement learning to assess commercial CCU deployment |
title_full_unstemmed | Applying real options with reinforcement learning to assess commercial CCU deployment |
title_short | Applying real options with reinforcement learning to assess commercial CCU deployment |
title_sort | applying real options with reinforcement learning to assess commercial ccu deployment |
topic | Carbon capture and utilization Multi-period deployment Real options theory Reinforcement learning Dynamic uncertainty |
url | http://www.sciencedirect.com/science/article/pii/S221298202300224X |
work_keys_str_mv | AT jeehwanslee applyingrealoptionswithreinforcementlearningtoassesscommercialccudeployment AT woopillchun applyingrealoptionswithreinforcementlearningtoassesscommercialccudeployment AT kosanroh applyingrealoptionswithreinforcementlearningtoassesscommercialccudeployment AT seongminheo applyingrealoptionswithreinforcementlearningtoassesscommercialccudeployment AT jayhlee applyingrealoptionswithreinforcementlearningtoassesscommercialccudeployment |