Source code and data for the experiments presented in Deep Reinforcement Learning for Active Wake Control (software)

Source code and data for the experiments presented in Deep Reinforcement Learning for Active Wake Control

doi: 10.4121/19107257.v1

The doi above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
doi: 10.4121/19107257

Datacite citation style:

Neustroev, Greg; de Weerdt, Mathijs; Remco Verzijbergh; Sytze Andringa (2022): Source code and data for the experiments presented in Deep Reinforcement Learning for Active Wake Control. Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/19107257.v1

Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite

Software

usage stats

812

views

136

downloads

categories

keywords

active wake control, deep learning, reinforcement learning

licence

MIT

export as...

RefWorks, BibTeX, Reference Manager, Endnote, DataCite, NLM, DC, CFF

by Greg Neustroev

, Mathijs de Weerdt

, Remco Verzijbergh, Sytze Andringa

This is a simulation study to illustrate benefits of reinforcement learning (RL) for active wake control in wind farms. The repository includes a simulator (./code/wind_farm_gym), implementation of RL agents (./code/agent), and configurations for the experiments presented in the paper (./code/configs), as well as the simulation results (./data). For more detailed instructions, see README.md.

history