Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods

<p dir="ltr">The reverse osmosis (RO) process is a well-established desalination technology, wherein energy-efficient techniques and advanced process control methods significantly reduce production costs. This study proposes an optimal real-time management method to minimize the tota...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Arash Golabi (21841484) (author)
مؤلفون آخرون: Abdelkarim Erradi (13475740) (author), Hazim Qiblawey (16030546) (author), Ashraf Tantawy (21841487) (author), Ahmed Bensaid (21259505) (author), Khaled Shaban (20074425) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513543044333568
author Arash Golabi (21841484)
author2 Abdelkarim Erradi (13475740)
Hazim Qiblawey (16030546)
Ashraf Tantawy (21841487)
Ahmed Bensaid (21259505)
Khaled Shaban (20074425)
author2_role author
author
author
author
author
author_facet Arash Golabi (21841484)
Abdelkarim Erradi (13475740)
Hazim Qiblawey (16030546)
Ashraf Tantawy (21841487)
Ahmed Bensaid (21259505)
Khaled Shaban (20074425)
author_role author
dc.creator.none.fl_str_mv Arash Golabi (21841484)
Abdelkarim Erradi (13475740)
Hazim Qiblawey (16030546)
Ashraf Tantawy (21841487)
Ahmed Bensaid (21259505)
Khaled Shaban (20074425)
dc.date.none.fl_str_mv 2024-05-13T09:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s10489-024-05452-8
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Optimal_operation_of_reverse_osmosis_desalination_process_with_deep_reinforcement_learning_methods/29715005
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Engineering practice and education
Environmental engineering
Information and computing sciences
Machine learning
Reinforcement learning
Reverse osmosis
Desalination process
Dynamic modeling
Deep deterministic policy gradient
Deep Q-Network
Optimal management
Data-driven controller
dc.title.none.fl_str_mv Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The reverse osmosis (RO) process is a well-established desalination technology, wherein energy-efficient techniques and advanced process control methods significantly reduce production costs. This study proposes an optimal real-time management method to minimize the total daily operation cost of an RO desalination plant, integrating a storage tank system to meet varying daily freshwater demand. Utilizing the dynamic model of the RO process, a cascade structure with two reinforcement learning (RL) agents, namely the deep deterministic policy gradient (DDPG) and deep Q-Network (DQN), is developed to optimize the operation of the RO plant. The DDPG agent, manipulating the high-pressure pump, controls the permeate flow rate to track a reference setpoint value. Simultaneously, the DQN agent selects the optimal setpoint value and communicates it to the DDPG controller to minimize the plant’s operation cost. Monitoring storage tanks, permeate flow rates, and water demand enables the DQN agent to determine the required amount of permeate water, optimizing water quality and energy consumption. Additionally, the DQN agent monitors the storage tank’s water level to prevent overflow or underflow of permeate water. Simulation results demonstrate the effectiveness and practicality of the designed RL agents.</p><h2>Other Information</h2><p dir="ltr">Published in: Applied Intelligence<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s10489-024-05452-8" target="_blank">https://dx.doi.org/10.1007/s10489-024-05452-8</a></p>
eu_rights_str_mv openAccess
id Manara2_c18bcd2fbec6eab3929e130dbef15ddf
identifier_str_mv 10.1007/s10489-024-05452-8
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29715005
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Optimal operation of reverse osmosis desalination process with deep reinforcement learning methodsArash Golabi (21841484)Abdelkarim Erradi (13475740)Hazim Qiblawey (16030546)Ashraf Tantawy (21841487)Ahmed Bensaid (21259505)Khaled Shaban (20074425)EngineeringEngineering practice and educationEnvironmental engineeringInformation and computing sciencesMachine learningReinforcement learningReverse osmosisDesalination processDynamic modelingDeep deterministic policy gradientDeep Q-NetworkOptimal managementData-driven controller<p dir="ltr">The reverse osmosis (RO) process is a well-established desalination technology, wherein energy-efficient techniques and advanced process control methods significantly reduce production costs. This study proposes an optimal real-time management method to minimize the total daily operation cost of an RO desalination plant, integrating a storage tank system to meet varying daily freshwater demand. Utilizing the dynamic model of the RO process, a cascade structure with two reinforcement learning (RL) agents, namely the deep deterministic policy gradient (DDPG) and deep Q-Network (DQN), is developed to optimize the operation of the RO plant. The DDPG agent, manipulating the high-pressure pump, controls the permeate flow rate to track a reference setpoint value. Simultaneously, the DQN agent selects the optimal setpoint value and communicates it to the DDPG controller to minimize the plant’s operation cost. Monitoring storage tanks, permeate flow rates, and water demand enables the DQN agent to determine the required amount of permeate water, optimizing water quality and energy consumption. Additionally, the DQN agent monitors the storage tank’s water level to prevent overflow or underflow of permeate water. Simulation results demonstrate the effectiveness and practicality of the designed RL agents.</p><h2>Other Information</h2><p dir="ltr">Published in: Applied Intelligence<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s10489-024-05452-8" target="_blank">https://dx.doi.org/10.1007/s10489-024-05452-8</a></p>2024-05-13T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s10489-024-05452-8https://figshare.com/articles/journal_contribution/Optimal_operation_of_reverse_osmosis_desalination_process_with_deep_reinforcement_learning_methods/29715005CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/297150052024-05-13T09:00:00Z
spellingShingle Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
Arash Golabi (21841484)
Engineering
Engineering practice and education
Environmental engineering
Information and computing sciences
Machine learning
Reinforcement learning
Reverse osmosis
Desalination process
Dynamic modeling
Deep deterministic policy gradient
Deep Q-Network
Optimal management
Data-driven controller
status_str publishedVersion
title Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
title_full Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
title_fullStr Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
title_full_unstemmed Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
title_short Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
title_sort Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods
topic Engineering
Engineering practice and education
Environmental engineering
Information and computing sciences
Machine learning
Reinforcement learning
Reverse osmosis
Desalination process
Dynamic modeling
Deep deterministic policy gradient
Deep Q-Network
Optimal management
Data-driven controller