TEAMER: Experimental Validation and Analysis of Deep Reinforcement Learning Control for Wave Energy Converters
Through this TEAMER project, Michigan Technological University (MTU) collaborated with Oregon State University (OSU) to test the performance of a Deep Reinforcement Learning (DRL) control in the wave tank. Unlike model-based controls, DRL control is model-free and can directly maximize the performance of the Wave Energy Converter (WEC) in terms of power production, regardless of system complexity. While DRL control has demonstrated promising performance in previous studies, this project aimed to (1) evaluate the practical performance of DRL control and (2) identify the challenges and limitations associated with its practical implementation.
To investigate the real-world performance of DRL-based control, the controller was trained with the LUPA numerical model using MATLAB/Simulink Deep Learning Toolbox and implemented on the Laboratory Upgrade Point Absorber (LUPA) device developed by the facility at OSU. A series of regular and irregular wave tests were conducted to evaluate the power harvested by the DRL control across different wave conditions, using various observation state selections, and incorporating a reward function that includes a penalty on the PTO force.
The dataset consists of six main parts:
(1) the Post Access Report
(2) the test log containing the test ID, description, test data filename, wave data filename, wave condition, test notes for all conducted LUPA Testing Data
(3) the tank testing results as described in the DRL Test Log
(4) the model used for retraining the DRL control and associated results
(5) the model used for pre-training the DRL control and associated results
(6) the scripts used for processing the data
(7) A readme file to indicate the folder contents and structure within the resources "LUPA Pretraining Data.zip", "LUPA Retraining Data.zip", and "ScriptsForPostProcessing.zip"
This testing was funded by TEAMER RFTS 10 (request for technical support) program.
Citation Formats
TY - DATA
AB - Through this TEAMER project, Michigan Technological University (MTU) collaborated with Oregon State University (OSU) to test the performance of a Deep Reinforcement Learning (DRL) control in the wave tank. Unlike model-based controls, DRL control is model-free and can directly maximize the performance of the Wave Energy Converter (WEC) in terms of power production, regardless of system complexity. While DRL control has demonstrated promising performance in previous studies, this project aimed to (1) evaluate the practical performance of DRL control and (2) identify the challenges and limitations associated with its practical implementation.
To investigate the real-world performance of DRL-based control, the controller was trained with the LUPA numerical model using MATLAB/Simulink Deep Learning Toolbox and implemented on the Laboratory Upgrade Point Absorber (LUPA) device developed by the facility at OSU. A series of regular and irregular wave tests were conducted to evaluate the power harvested by the DRL control across different wave conditions, using various observation state selections, and incorporating a reward function that includes a penalty on the PTO force.
The dataset consists of six main parts:
(1) the Post Access Report
(2) the test log containing the test ID, description, test data filename, wave data filename, wave condition, test notes for all conducted LUPA Testing Data
(3) the tank testing results as described in the DRL Test Log
(4) the model used for retraining the DRL control and associated results
(5) the model used for pre-training the DRL control and associated results
(6) the scripts used for processing the data
(7) A readme file to indicate the folder contents and structure within the resources "LUPA Pretraining Data.zip", "LUPA Retraining Data.zip", and "ScriptsForPostProcessing.zip"
This testing was funded by TEAMER RFTS 10 (request for technical support) program.
AU - Zou, Shangyan
A2 - Subramanian, Abishek
A3 - Bosma, Bret
A4 - Lou, Junhui
A5 - Beringer, Courtney
A6 - Robertson, Bryson
A7 - Lomonaco, Pedro
DB - Open Energy Data Initiative (OEDI)
DP - Open EI | National Renewable Energy Laboratory
DO -
KW - MHK
KW - Marine
KW - Wave Energy
KW - Deep Reinforcement Learning
KW - PTO control
KW - TEAMER
KW - validation
KW - DRL
KW - Wave Energy Converter
KW - WEC
KW - RFTS10
KW - code
KW - processed data
KW - pertaining data
KW - retraining data
KW - wave tank
KW - source code
KW - performance
KW - DRL control
KW - LUPA
KW - Laboratory Upgrade Point Absorber
KW - regular wave
KW - irregular wave
LA - English
DA - 2025/03/07
PY - 2025
PB - Michigan Technological University
T1 - TEAMER: Experimental Validation and Analysis of Deep Reinforcement Learning Control for Wave Energy Converters
UR - https://data.openei.org/submissions/8436
ER -
Zou, Shangyan, et al. TEAMER: Experimental Validation and Analysis of Deep Reinforcement Learning Control for Wave Energy Converters. Michigan Technological University, 7 March, 2025, MHKDR. https://mhkdr.openei.org/submissions/628.
Zou, S., Subramanian, A., Bosma, B., Lou, J., Beringer, C., Robertson, B., & Lomonaco, P. (2025). TEAMER: Experimental Validation and Analysis of Deep Reinforcement Learning Control for Wave Energy Converters. [Data set]. MHKDR. Michigan Technological University. https://mhkdr.openei.org/submissions/628
Zou, Shangyan, Abishek Subramanian, Bret Bosma, Junhui Lou, Courtney Beringer, Bryson Robertson, and Pedro Lomonaco. TEAMER: Experimental Validation and Analysis of Deep Reinforcement Learning Control for Wave Energy Converters. Michigan Technological University, March, 7, 2025. Distributed by MHKDR. https://mhkdr.openei.org/submissions/628
@misc{OEDI_Dataset_8436,
title = {TEAMER: Experimental Validation and Analysis of Deep Reinforcement Learning Control for Wave Energy Converters},
author = {Zou, Shangyan and Subramanian, Abishek and Bosma, Bret and Lou, Junhui and Beringer, Courtney and Robertson, Bryson and Lomonaco, Pedro},
abstractNote = {Through this TEAMER project, Michigan Technological University (MTU) collaborated with Oregon State University (OSU) to test the performance of a Deep Reinforcement Learning (DRL) control in the wave tank. Unlike model-based controls, DRL control is model-free and can directly maximize the performance of the Wave Energy Converter (WEC) in terms of power production, regardless of system complexity. While DRL control has demonstrated promising performance in previous studies, this project aimed to (1) evaluate the practical performance of DRL control and (2) identify the challenges and limitations associated with its practical implementation.
To investigate the real-world performance of DRL-based control, the controller was trained with the LUPA numerical model using MATLAB/Simulink Deep Learning Toolbox and implemented on the Laboratory Upgrade Point Absorber (LUPA) device developed by the facility at OSU. A series of regular and irregular wave tests were conducted to evaluate the power harvested by the DRL control across different wave conditions, using various observation state selections, and incorporating a reward function that includes a penalty on the PTO force.
The dataset consists of six main parts:
(1) the Post Access Report
(2) the test log containing the test ID, description, test data filename, wave data filename, wave condition, test notes for all conducted LUPA Testing Data
(3) the tank testing results as described in the DRL Test Log
(4) the model used for retraining the DRL control and associated results
(5) the model used for pre-training the DRL control and associated results
(6) the scripts used for processing the data
(7) A readme file to indicate the folder contents and structure within the resources "LUPA Pretraining Data.zip", "LUPA Retraining Data.zip", and "ScriptsForPostProcessing.zip"
This testing was funded by TEAMER RFTS 10 (request for technical support) program.},
url = {https://mhkdr.openei.org/submissions/628},
year = {2025},
howpublished = {MHKDR, Michigan Technological University, https://mhkdr.openei.org/submissions/628},
note = {Accessed: 2025-06-16}
}
Details
Data from Mar 7, 2025
Last updated Jun 16, 2025
Submitted May 21, 2025
Organization
Michigan Technological University
Contact
Shangyan Zou
Authors
Original Source
https://mhkdr.openei.org/submissions/628Research Areas
Keywords
MHK, Marine, Wave Energy, Deep Reinforcement Learning, PTO control, TEAMER, validation, DRL, Wave Energy Converter, WEC, RFTS10, code, processed data, pertaining data, retraining data, wave tank, source code, performance, DRL control, LUPA, Laboratory Upgrade Point Absorber, regular wave, irregular waveDOE Project Details
Project Name Testing Expertise and Access for Marine Energy Research
Project Lead Lauren Ruedy
Project Number EE0008895
