A Model Free Control Based on Machine Learning for Energy Converters in an Array
This paper introduces a machine learning based control strategy for energy converter arrays designed to work under realistic conditions where the optimal control parameter can not be obtained analytically. The control strategy neither relies on a mathematical model, nor does it need a priori informa...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/2/4/36 |
| _version_ | 1819078010037338112 |
|---|---|
| author | Simon Thomas Marianna Giassi Mikael Eriksson Malin Göteman Jan Isberg Edward Ransley Martyn Hann Jens Engström |
| author_facet | Simon Thomas Marianna Giassi Mikael Eriksson Malin Göteman Jan Isberg Edward Ransley Martyn Hann Jens Engström |
| author_sort | Simon Thomas |
| collection | DOAJ |
| description | This paper introduces a machine learning based control strategy for energy converter arrays designed to work under realistic conditions where the optimal control parameter can not be obtained analytically. The control strategy neither relies on a mathematical model, nor does it need a priori information about the energy medium. Therefore several identical energy converters are arranged so that they are affected simultaneously by the energy medium. Each device uses a different control strategy, of which at least one has to be the machine learning approach presented in this paper. During operation all energy converters record the absorbed power and control output; the machine learning device gets the data from the converter with the highest power absorption and so learns the best performing control strategy for each situation. Consequently, the overall network has a better overall performance than each individual strategy. This concept is evaluated for wave energy converters (WECs) with numerical simulations and experiments with physical scale models in a wave tank. In the first of two numerical simulations, the learnable WEC works in an array with four WECs applying a constant damping factor. In the second simulation, two learnable WECs were learning with each other. It showed that in the first test the WEC was able to absorb as much as the best constant damping WEC, while in the second run it could absorb even slightly more. During the physical model test, the ANN showed its ability to select the better of two possible damping coefficients based on real world input data. |
| first_indexed | 2024-12-21T19:06:17Z |
| format | Article |
| id | doaj.art-4cee996bb3154d27901d94435e3c39a1 |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-12-21T19:06:17Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-4cee996bb3154d27901d94435e3c39a12022-12-21T18:53:19ZengMDPI AGBig Data and Cognitive Computing2504-22892018-11-01243610.3390/bdcc2040036bdcc2040036A Model Free Control Based on Machine Learning for Energy Converters in an ArraySimon Thomas0Marianna Giassi1Mikael Eriksson2Malin Göteman3Jan Isberg4Edward Ransley5Martyn Hann6Jens Engström7Ångströmlaboratoriet, Division of Electricity, Uppsala University, Lägerhyddsvägen 1, 75237 Uppsala, SwedenÅngströmlaboratoriet, Division of Electricity, Uppsala University, Lägerhyddsvägen 1, 75237 Uppsala, SwedenÅngströmlaboratoriet, Division of Electricity, Uppsala University, Lägerhyddsvägen 1, 75237 Uppsala, SwedenÅngströmlaboratoriet, Division of Electricity, Uppsala University, Lägerhyddsvägen 1, 75237 Uppsala, SwedenÅngströmlaboratoriet, Division of Electricity, Uppsala University, Lägerhyddsvägen 1, 75237 Uppsala, SwedenSchool of Engineering, University of Plymouth, Drake Circuit, Plymouth PL4 8AA, UKSchool of Engineering, University of Plymouth, Drake Circuit, Plymouth PL4 8AA, UKÅngströmlaboratoriet, Division of Electricity, Uppsala University, Lägerhyddsvägen 1, 75237 Uppsala, SwedenThis paper introduces a machine learning based control strategy for energy converter arrays designed to work under realistic conditions where the optimal control parameter can not be obtained analytically. The control strategy neither relies on a mathematical model, nor does it need a priori information about the energy medium. Therefore several identical energy converters are arranged so that they are affected simultaneously by the energy medium. Each device uses a different control strategy, of which at least one has to be the machine learning approach presented in this paper. During operation all energy converters record the absorbed power and control output; the machine learning device gets the data from the converter with the highest power absorption and so learns the best performing control strategy for each situation. Consequently, the overall network has a better overall performance than each individual strategy. This concept is evaluated for wave energy converters (WECs) with numerical simulations and experiments with physical scale models in a wave tank. In the first of two numerical simulations, the learnable WEC works in an array with four WECs applying a constant damping factor. In the second simulation, two learnable WECs were learning with each other. It showed that in the first test the WEC was able to absorb as much as the best constant damping WEC, while in the second run it could absorb even slightly more. During the physical model test, the ANN showed its ability to select the better of two possible damping coefficients based on real world input data.https://www.mdpi.com/2504-2289/2/4/36machine learningwave energypower take-offartificial neural networkwave tank testphysical scale modelfloating point absorberdampingcontrolcollaborative |
| spellingShingle | Simon Thomas Marianna Giassi Mikael Eriksson Malin Göteman Jan Isberg Edward Ransley Martyn Hann Jens Engström A Model Free Control Based on Machine Learning for Energy Converters in an Array Big Data and Cognitive Computing machine learning wave energy power take-off artificial neural network wave tank test physical scale model floating point absorber damping control collaborative |
| title | A Model Free Control Based on Machine Learning for Energy Converters in an Array |
| title_full | A Model Free Control Based on Machine Learning for Energy Converters in an Array |
| title_fullStr | A Model Free Control Based on Machine Learning for Energy Converters in an Array |
| title_full_unstemmed | A Model Free Control Based on Machine Learning for Energy Converters in an Array |
| title_short | A Model Free Control Based on Machine Learning for Energy Converters in an Array |
| title_sort | model free control based on machine learning for energy converters in an array |
| topic | machine learning wave energy power take-off artificial neural network wave tank test physical scale model floating point absorber damping control collaborative |
| url | https://www.mdpi.com/2504-2289/2/4/36 |
| work_keys_str_mv | AT simonthomas amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT mariannagiassi amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT mikaeleriksson amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT malingoteman amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT janisberg amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT edwardransley amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT martynhann amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT jensengstrom amodelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT simonthomas modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT mariannagiassi modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT mikaeleriksson modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT malingoteman modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT janisberg modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT edwardransley modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT martynhann modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray AT jensengstrom modelfreecontrolbasedonmachinelearningforenergyconvertersinanarray |