Control of wave energy converters using machine learning strategies
Wave energy converters are devices that are designed to extract power from ocean waves. Existing wave energy converter technologies are not financially viable yet. Control systems have been identified as one of the areas that can contribute the most towards the increase in energy absorption and redu...
Main Author: | |
---|---|
Other Authors: | , , , |
Format: | Doctoral or Postdoctoral Thesis |
Language: | English |
Published: |
The University of Edinburgh
2018
|
Subjects: | |
Online Access: | http://hdl.handle.net/1842/31112 |
id |
ftunivedinburgh:oai:era.ed.ac.uk:1842/31112 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Edinburgh Research Archive (ERA - University of Edinburgh) |
op_collection_id |
ftunivedinburgh |
language |
English |
topic |
wave energy converters single isolated devices time-averaged approach control schemes linear hydrodynamics reinforcement learning |
spellingShingle |
wave energy converters single isolated devices time-averaged approach control schemes linear hydrodynamics reinforcement learning Anderlini, Enrico Control of wave energy converters using machine learning strategies |
topic_facet |
wave energy converters single isolated devices time-averaged approach control schemes linear hydrodynamics reinforcement learning |
description |
Wave energy converters are devices that are designed to extract power from ocean waves. Existing wave energy converter technologies are not financially viable yet. Control systems have been identified as one of the areas that can contribute the most towards the increase in energy absorption and reduction of loads acting on the structure, whilst incurring only minimal extra hardware costs. In this thesis, control schemes are developed for wave energy converters, with the focus on single isolated devices. Numerical models of increasing complexity are developed for the simulation of a point absorber, which is a type of wave energy converter with small dimensions with respect to the dominating wave length. After investigating state-of-the-art control schemes, the existing control strategies reported in the literature have been found to rely on the model of the system dynamics to determine the optimal control action. This is despite the fact that modelling errors can negatively affect the performance of the device, particularly in highly energetic waves when non-linear effects become more significant. Furthermore, the controller should be adaptive so that changes in the system dynamics, e.g. due to marine growth or non-critical subsystem failure, are accounted for. Hence, machine learning approaches have been investigated as an alternative, with a focus on neural networks and reinforcement learning for control applications. A time-averaged approach will be employed for the development of the control schemes to enable a practical implementation on WECs based on the standard in the industry at the moment. Neural networks are applied to the active control of a point absorber. They are used mainly for system identification, where the mean power is related to the current sea state and parameters of the power take-off unit. The developed control scheme presents a similar performance to optimal active control for the analysed simulations, which rely on linear hydrodynamics. Reinforcement learning is then applied to the ... |
author2 |
Forehand, David Ingram, David Abusara, Mohammad Engineering and Physical Sciences Research Council (EPSRC) |
format |
Doctoral or Postdoctoral Thesis |
author |
Anderlini, Enrico |
author_facet |
Anderlini, Enrico |
author_sort |
Anderlini, Enrico |
title |
Control of wave energy converters using machine learning strategies |
title_short |
Control of wave energy converters using machine learning strategies |
title_full |
Control of wave energy converters using machine learning strategies |
title_fullStr |
Control of wave energy converters using machine learning strategies |
title_full_unstemmed |
Control of wave energy converters using machine learning strategies |
title_sort |
control of wave energy converters using machine learning strategies |
publisher |
The University of Edinburgh |
publishDate |
2018 |
url |
http://hdl.handle.net/1842/31112 |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
Anderlini, E., Forehand, D. I. M., Stansell, P., Xiao, Q., and Abusara, M. (2016). "Control of a Point Absorber Using Reinforcement Learning". IEEE Transactions on Sustainable Energy, 7, 4, October, pp. 1681-1690. Anderlini, E., Forehand, D. I.M., Bannon, E., and Abusara,M. (2017). "Control of a Realistic Wave Energy Converter Model using Least-Squares Policy Iteration". IEEE Transactions on Sustainable Energy, 8, 4, October, pp. 1618 - 1628. Anderlini, E., Forehand, D. I. M., Bannon E., and Abusara, M. (2017). "Reactive Control of a Wave Energy Converter using Arti cial Neural Networks." Interna- tional Journal of Marine Energy, 19, September, pp. 207-220. Anderlini, E., Forehand, D. I. M., Stansell, Bannon, E., Xiao, Q., and Abusara, M. (2016). "Declutching Control of a Point Absorber based on Reinforcement Learning". Asian Wave and Tidal Energy Conference, Singapore, October Anderlini, E., Forehand, D. I. M., Bannon, E., and Abusara, M. (2017). "Constraints Implementation in the Application of Reinforcement learning to the reactive control of a point absorber". Conference on Ocean, O shore and Arctic Engineering, Trondheim, June. Nambiar, A. Anderlini, E., Payne, G., Forehand, D. I. M., Kiprakis, A., and Wallace, R. (2017). "Reinforcement Learning Based Maximum Power Point Tracking Control of Tidal Turbines". European Wave and Tidal Energy Conference, Cork, August. http://hdl.handle.net/1842/31112 |
_version_ |
1801371408603807744 |
spelling |
ftunivedinburgh:oai:era.ed.ac.uk:1842/31112 2024-06-09T07:42:39+00:00 Control of wave energy converters using machine learning strategies Anderlini, Enrico Forehand, David Ingram, David Abusara, Mohammad Engineering and Physical Sciences Research Council (EPSRC) 2018-07-04 application/pdf http://hdl.handle.net/1842/31112 en eng The University of Edinburgh Anderlini, E., Forehand, D. I. M., Stansell, P., Xiao, Q., and Abusara, M. (2016). "Control of a Point Absorber Using Reinforcement Learning". IEEE Transactions on Sustainable Energy, 7, 4, October, pp. 1681-1690. Anderlini, E., Forehand, D. I.M., Bannon, E., and Abusara,M. (2017). "Control of a Realistic Wave Energy Converter Model using Least-Squares Policy Iteration". IEEE Transactions on Sustainable Energy, 8, 4, October, pp. 1618 - 1628. Anderlini, E., Forehand, D. I. M., Bannon E., and Abusara, M. (2017). "Reactive Control of a Wave Energy Converter using Arti cial Neural Networks." Interna- tional Journal of Marine Energy, 19, September, pp. 207-220. Anderlini, E., Forehand, D. I. M., Stansell, Bannon, E., Xiao, Q., and Abusara, M. (2016). "Declutching Control of a Point Absorber based on Reinforcement Learning". Asian Wave and Tidal Energy Conference, Singapore, October Anderlini, E., Forehand, D. I. M., Bannon, E., and Abusara, M. (2017). "Constraints Implementation in the Application of Reinforcement learning to the reactive control of a point absorber". Conference on Ocean, O shore and Arctic Engineering, Trondheim, June. Nambiar, A. Anderlini, E., Payne, G., Forehand, D. I. M., Kiprakis, A., and Wallace, R. (2017). "Reinforcement Learning Based Maximum Power Point Tracking Control of Tidal Turbines". European Wave and Tidal Energy Conference, Cork, August. http://hdl.handle.net/1842/31112 wave energy converters single isolated devices time-averaged approach control schemes linear hydrodynamics reinforcement learning Thesis or Dissertation Doctoral PhD Doctor of Philosophy 2018 ftunivedinburgh 2024-05-10T03:12:17Z Wave energy converters are devices that are designed to extract power from ocean waves. Existing wave energy converter technologies are not financially viable yet. Control systems have been identified as one of the areas that can contribute the most towards the increase in energy absorption and reduction of loads acting on the structure, whilst incurring only minimal extra hardware costs. In this thesis, control schemes are developed for wave energy converters, with the focus on single isolated devices. Numerical models of increasing complexity are developed for the simulation of a point absorber, which is a type of wave energy converter with small dimensions with respect to the dominating wave length. After investigating state-of-the-art control schemes, the existing control strategies reported in the literature have been found to rely on the model of the system dynamics to determine the optimal control action. This is despite the fact that modelling errors can negatively affect the performance of the device, particularly in highly energetic waves when non-linear effects become more significant. Furthermore, the controller should be adaptive so that changes in the system dynamics, e.g. due to marine growth or non-critical subsystem failure, are accounted for. Hence, machine learning approaches have been investigated as an alternative, with a focus on neural networks and reinforcement learning for control applications. A time-averaged approach will be employed for the development of the control schemes to enable a practical implementation on WECs based on the standard in the industry at the moment. Neural networks are applied to the active control of a point absorber. They are used mainly for system identification, where the mean power is related to the current sea state and parameters of the power take-off unit. The developed control scheme presents a similar performance to optimal active control for the analysed simulations, which rely on linear hydrodynamics. Reinforcement learning is then applied to the ... Doctoral or Postdoctoral Thesis Arctic Edinburgh Research Archive (ERA - University of Edinburgh) |