Reinforcement learning-based control for waste biorefining processes under uncertainty
Abstract Waste biorefining processes face significant challenges related to the variability of feedstocks. The supply and composition of multiple feedstocks in these processes can be uncertain, making it difficult to achieve economically feasible and sustainable waste valorization for large-scale pr...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Communications Engineering |
| Online Access: | https://doi.org/10.1038/s44172-024-00183-7 |
| _version_ | 1797274457240240128 |
|---|---|
| author | Ji Gao Abigael Wahlen Caleb Ju Yongsheng Chen Guanghui Lan Zhaohui Tong |
| author_facet | Ji Gao Abigael Wahlen Caleb Ju Yongsheng Chen Guanghui Lan Zhaohui Tong |
| author_sort | Ji Gao |
| collection | DOAJ |
| description | Abstract Waste biorefining processes face significant challenges related to the variability of feedstocks. The supply and composition of multiple feedstocks in these processes can be uncertain, making it difficult to achieve economically feasible and sustainable waste valorization for large-scale production. Here, we introduce a reinforcement learning-based framework that aims to control these uncertainties and improve the efficiency of the process. The framework is tested on an anaerobic digestion process and is found to perform better than traditional control strategies. In the short term, it achieves faster target tracking with increased precision and accuracy, while in the long term, it shows adaptive and robust behavior even under additional seasonal supply variability, meeting downstream demand with high probability. This reinforcement learning-based framework offers a promising and scalable solution to address uncertainty issues in real-world biorefining processes. If implemented, this framework could contribute to sustainable waste management practices globally, making waste biorefining processes more economically viable and environmentally friendly. |
| first_indexed | 2024-03-07T14:58:38Z |
| format | Article |
| id | doaj.art-a1f5295be47744f9aed2bc09d9f07277 |
| institution | Directory Open Access Journal |
| issn | 2731-3395 |
| language | English |
| last_indexed | 2024-03-07T14:58:38Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Engineering |
| spelling | doaj.art-a1f5295be47744f9aed2bc09d9f072772024-03-05T19:17:04ZengNature PortfolioCommunications Engineering2731-33952024-02-013111010.1038/s44172-024-00183-7Reinforcement learning-based control for waste biorefining processes under uncertaintyJi Gao0Abigael Wahlen1Caleb Ju2Yongsheng Chen3Guanghui Lan4Zhaohui Tong5School of Chemical & Biomolecular Engineering, Georgia Institute of TechnologySchool of Chemical & Biomolecular Engineering, Georgia Institute of TechnologyH. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of TechnologySchool of Civil and Environmental Engineering, Georgia Institute of TechnologyH. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of TechnologySchool of Chemical & Biomolecular Engineering, Georgia Institute of TechnologyAbstract Waste biorefining processes face significant challenges related to the variability of feedstocks. The supply and composition of multiple feedstocks in these processes can be uncertain, making it difficult to achieve economically feasible and sustainable waste valorization for large-scale production. Here, we introduce a reinforcement learning-based framework that aims to control these uncertainties and improve the efficiency of the process. The framework is tested on an anaerobic digestion process and is found to perform better than traditional control strategies. In the short term, it achieves faster target tracking with increased precision and accuracy, while in the long term, it shows adaptive and robust behavior even under additional seasonal supply variability, meeting downstream demand with high probability. This reinforcement learning-based framework offers a promising and scalable solution to address uncertainty issues in real-world biorefining processes. If implemented, this framework could contribute to sustainable waste management practices globally, making waste biorefining processes more economically viable and environmentally friendly.https://doi.org/10.1038/s44172-024-00183-7 |
| spellingShingle | Ji Gao Abigael Wahlen Caleb Ju Yongsheng Chen Guanghui Lan Zhaohui Tong Reinforcement learning-based control for waste biorefining processes under uncertainty Communications Engineering |
| title | Reinforcement learning-based control for waste biorefining processes under uncertainty |
| title_full | Reinforcement learning-based control for waste biorefining processes under uncertainty |
| title_fullStr | Reinforcement learning-based control for waste biorefining processes under uncertainty |
| title_full_unstemmed | Reinforcement learning-based control for waste biorefining processes under uncertainty |
| title_short | Reinforcement learning-based control for waste biorefining processes under uncertainty |
| title_sort | reinforcement learning based control for waste biorefining processes under uncertainty |
| url | https://doi.org/10.1038/s44172-024-00183-7 |
| work_keys_str_mv | AT jigao reinforcementlearningbasedcontrolforwastebiorefiningprocessesunderuncertainty AT abigaelwahlen reinforcementlearningbasedcontrolforwastebiorefiningprocessesunderuncertainty AT calebju reinforcementlearningbasedcontrolforwastebiorefiningprocessesunderuncertainty AT yongshengchen reinforcementlearningbasedcontrolforwastebiorefiningprocessesunderuncertainty AT guanghuilan reinforcementlearningbasedcontrolforwastebiorefiningprocessesunderuncertainty AT zhaohuitong reinforcementlearningbasedcontrolforwastebiorefiningprocessesunderuncertainty |